Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+sd3_pipeline/mmdit-x.png filter=lfs diff=lfs merge=lfs -text
+sd3_pipeline/sd3.5_medium_demo.jpg filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

added_tokens.json

@@ -0,0 +1,29 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<image_gen>": 151669,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

bsq_encoder/config.json

@@ -0,0 +1,30 @@
+{
+  "depth": 27,
+  "hidden_size": 1152,
+  "hidden_act": "gelu_pytorch_tanh",
+  "intermediate_size": 4304,
+  "num_heads": 16,
+  "in_channels": 3,
+  "patch_size": 16,
+  "spatial_merge_size": 2,
+  "temporal_patch_size": 2,
+  "out_hidden_size": 4096,
+  "initializer_range": 0.02,
+  "use_bsq": true,
+  "bsq_dim": 64,
+  "bsq_hidden_dim": 8192,
+  "bsq_skip_final_layernorm": true,
+  "vistok_pred": false,
+  "vistok_pred_layernorm": false,
+  "vistok_pred_transformer_head": false,
+  "architectures": [
+    "UniARVisionModel"
+  ],
+  "model_type": "uniar_vision",
+  "deepstack_visual_indexes": [
+    8,
+    16,
+    24
+  ],
+  "num_position_embeddings": 2304
+}

bsq_encoder/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a07a8018053621883d0a988c7ba7d974a1941922d1cb1fe27d76c6420664ad0a
+size 1312361072

chat_template.jinja

@@ -0,0 +1,7 @@
+{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system
+You are a helpful assistant.<|im_end|>
+{% endif %}<|im_start|>{{ message['role'] }}
+{% if message['content'] is string %}{{ message['content'] }}<|im_end|>
+{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>
+{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant
+{% endif %}

config.json

@@ -0,0 +1,68 @@
+{
+  "architectures": [
+    "UniARForConditionalGeneration"
+  ],
+  "model_type": "uniar",
+  "text_config": {
+    "vocab_size": 151936,
+    "hidden_size": 4096,
+    "intermediate_size": 12288,
+    "num_hidden_layers": 36,
+    "num_attention_heads": 32,
+    "num_key_value_heads": 8,
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "max_position_embeddings": 32768,
+    "initializer_range": 0.02,
+    "rms_norm_eps": 1e-06,
+    "use_cache": true,
+    "rope_theta": 1000000,
+    "rope_scaling": {
+      "mrope_section": [
+        24,
+        20,
+        20
+      ],
+      "rope_type": "default"
+    },
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "tie_word_embeddings": false
+  },
+  "vision_config": {
+    "depth": 27,
+    "hidden_size": 1152,
+    "hidden_act": "gelu_pytorch_tanh",
+    "intermediate_size": 4304,
+    "num_heads": 16,
+    "in_channels": 3,
+    "patch_size": 16,
+    "spatial_merge_size": 2,
+    "temporal_patch_size": 2,
+    "out_hidden_size": 4096,
+    "initializer_range": 0.02,
+    "use_bsq": true,
+    "bsq_dim": 64,
+    "bsq_hidden_dim": 8192,
+    "bsq_skip_final_layernorm": true,
+    "vistok_pred": false,
+    "vistok_pred_layernorm": false,
+    "vistok_pred_transformer_head": false,
+    "num_position_embeddings": 2304,
+    "deepstack_visual_indexes": [
+      8,
+      16,
+      24
+    ]
+  },
+  "vistok_pred": true,
+  "vistok_pred_layernorm": true,
+  "vistok_pred_use_mlp": false,
+  "visual_transformer_decoder": true,
+  "image_token_id": 151655,
+  "video_token_id": 151656,
+  "vision_start_token_id": 151652,
+  "vision_end_token_id": 151653,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16"
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "transformers_version": "4.53.0.dev0"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bfc3ce6379861b9bd928ff49915a5b97187ef7c770303d140b69be1ad8a1535
+size 4956280080

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cb214416ab4e233422b61cf4fc6380824861083354b04dad7eacaa935d2fc2b
+size 4983070560

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:481e4f80640b2f84bf938366789fe10703a9218069b11d7d925352de964d8fc8
+size 4999848448

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:becf34aaabfc23e0af53f629f5bade2b18dd11a1327a98462145e2db3df3d070
+size 4315053008

model.safetensors.index.json

@@ -0,0 +1,853 @@
+{
+  "metadata": {
+    "total_size": 19254148584
+  },
+  "weight_map": {
+    "model.visual.bsq.basis": "model-00001-of-00004.safetensors",
+    "model.visual.bsq.group_basis": "model-00001-of-00004.safetensors",
+    "model.language_model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.0.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.0.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.1.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.1.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.2.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.2.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.3.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.3.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.4.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.4.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.5.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.5.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.6.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.6.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.0.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.0.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.0.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.0.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.0.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.0.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.0.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.0.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.0.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.0.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.0.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.0.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.1.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.1.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.1.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.1.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.1.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.1.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.1.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.1.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.1.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.1.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.1.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.1.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.10.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.10.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.10.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.10.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.10.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.10.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.10.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.10.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.10.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.10.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.10.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.10.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.11.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.11.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.11.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.11.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.11.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.11.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.11.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.11.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.11.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.11.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.11.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.11.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.12.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.12.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.12.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.12.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.12.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.12.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.12.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.12.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.12.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.12.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.12.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.12.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.13.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.13.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.13.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.13.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.13.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.13.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.13.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.13.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.13.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.13.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.13.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.13.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.14.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.14.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.14.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.14.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.14.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.14.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.14.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.14.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.14.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.14.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.14.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.14.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.15.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.15.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.15.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.15.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.15.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.15.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.15.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.15.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.15.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.15.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.15.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.15.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.16.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.16.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.16.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.16.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.16.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.16.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.16.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.16.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.16.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.16.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.16.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.16.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.17.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.17.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.17.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.17.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.17.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.17.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.17.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.17.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.17.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.17.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.17.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.17.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.18.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.18.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.18.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.18.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.18.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.18.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.18.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.18.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.18.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.18.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.18.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.18.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.19.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.19.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.19.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.19.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.19.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.19.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.19.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.19.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.19.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.19.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.19.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.19.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.2.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.2.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.2.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.2.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.2.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.2.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.2.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.2.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.2.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.2.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.2.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.2.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.20.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.20.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.20.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.20.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.20.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.20.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.20.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.20.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.20.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.20.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.20.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.20.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.21.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.21.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.21.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.21.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.21.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.21.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.21.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.21.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.21.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.21.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.21.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.21.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.22.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.22.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.22.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.22.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.22.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.22.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.22.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.22.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.22.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.22.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.22.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.22.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.23.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.23.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.23.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.23.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.23.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.23.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.23.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.23.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.23.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.23.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.23.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.23.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.24.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.24.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.24.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.24.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.24.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.24.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.24.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.24.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.24.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.24.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.24.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.24.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.25.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.25.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.25.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.25.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.25.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.25.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.25.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.25.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.25.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.25.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.25.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.25.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.26.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.26.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.26.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.26.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.26.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.26.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.26.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.26.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.26.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.26.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.26.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.26.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.3.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.3.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.3.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.3.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.3.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.3.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.3.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.3.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.3.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.3.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.3.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.3.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.4.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.4.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.4.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.4.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.4.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.4.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.4.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.4.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.4.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.4.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.4.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.4.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.5.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.5.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.5.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.5.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.5.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.5.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.5.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.5.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.5.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.5.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.5.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.5.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.6.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.6.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.6.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.6.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.6.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.6.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.6.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.6.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.6.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.6.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.6.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.6.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.7.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.7.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.7.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.7.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.7.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.7.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.7.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.7.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.7.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.7.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.7.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.7.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.8.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.8.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.8.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.8.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.8.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.8.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.8.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.8.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.8.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.8.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.8.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.8.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.9.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.9.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.9.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.9.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.9.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.9.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.9.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.9.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.9.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.9.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.9.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.9.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.bsq_input_proj.norm.bias": "model-00001-of-00004.safetensors",
+    "model.visual.bsq_input_proj.norm.weight": "model-00001-of-00004.safetensors",
+    "model.visual.bsq_input_proj.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.bsq_input_proj.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.bsq_input_proj.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.bsq_input_proj.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.bsq_input_proj_list_0.norm.bias": "model-00001-of-00004.safetensors",
+    "model.visual.bsq_input_proj_list_0.norm.weight": "model-00001-of-00004.safetensors",
+    "model.visual.bsq_input_proj_list_0.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.bsq_input_proj_list_0.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.bsq_input_proj_list_0.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.bsq_input_proj_list_0.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.bsq_input_proj_list_1.norm.bias": "model-00001-of-00004.safetensors",
+    "model.visual.bsq_input_proj_list_1.norm.weight": "model-00001-of-00004.safetensors",
+    "model.visual.bsq_input_proj_list_1.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.bsq_input_proj_list_1.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.bsq_input_proj_list_1.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.bsq_input_proj_list_1.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.bsq_input_proj_list_2.norm.bias": "model-00001-of-00004.safetensors",
+    "model.visual.bsq_input_proj_list_2.norm.weight": "model-00001-of-00004.safetensors",
+    "model.visual.bsq_input_proj_list_2.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.bsq_input_proj_list_2.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.bsq_input_proj_list_2.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.bsq_input_proj_list_2.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.bsq_output_proj.norm.bias": "model-00001-of-00004.safetensors",
+    "model.visual.bsq_output_proj.norm.weight": "model-00001-of-00004.safetensors",
+    "model.visual.bsq_output_proj.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.bsq_output_proj.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.bsq_output_proj.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.bsq_output_proj.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.bsq_output_proj_list_0.norm.bias": "model-00001-of-00004.safetensors",
+    "model.visual.bsq_output_proj_list_0.norm.weight": "model-00001-of-00004.safetensors",
+    "model.visual.bsq_output_proj_list_0.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.bsq_output_proj_list_0.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.bsq_output_proj_list_0.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.bsq_output_proj_list_0.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.bsq_output_proj_list_1.norm.bias": "model-00001-of-00004.safetensors",
+    "model.visual.bsq_output_proj_list_1.norm.weight": "model-00001-of-00004.safetensors",
+    "model.visual.bsq_output_proj_list_1.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.bsq_output_proj_list_1.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.bsq_output_proj_list_1.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.bsq_output_proj_list_1.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.bsq_output_proj_list_2.norm.bias": "model-00001-of-00004.safetensors",
+    "model.visual.bsq_output_proj_list_2.norm.weight": "model-00001-of-00004.safetensors",
+    "model.visual.bsq_output_proj_list_2.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.bsq_output_proj_list_2.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.bsq_output_proj_list_2.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.bsq_output_proj_list_2.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.merger.norm.bias": "model-00001-of-00004.safetensors",
+    "model.visual.merger.norm.weight": "model-00001-of-00004.safetensors",
+    "model.visual.merger.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.merger.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.merger.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.merger.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.deepstack_merger_list.0.norm.bias": "model-00001-of-00004.safetensors",
+    "model.visual.deepstack_merger_list.0.norm.weight": "model-00001-of-00004.safetensors",
+    "model.visual.deepstack_merger_list.0.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.deepstack_merger_list.0.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.deepstack_merger_list.0.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.deepstack_merger_list.0.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.deepstack_merger_list.1.norm.bias": "model-00001-of-00004.safetensors",
+    "model.visual.deepstack_merger_list.1.norm.weight": "model-00001-of-00004.safetensors",
+    "model.visual.deepstack_merger_list.1.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.deepstack_merger_list.1.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.deepstack_merger_list.1.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.deepstack_merger_list.1.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.deepstack_merger_list.2.norm.bias": "model-00001-of-00004.safetensors",
+    "model.visual.deepstack_merger_list.2.norm.weight": "model-00001-of-00004.safetensors",
+    "model.visual.deepstack_merger_list.2.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.deepstack_merger_list.2.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.deepstack_merger_list.2.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.deepstack_merger_list.2.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.patch_embed.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.patch_embed.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.pos_embed.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.10.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.10.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.11.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.11.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.12.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.12.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.13.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.13.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.14.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.14.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.15.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.15.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.16.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.16.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.17.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.17.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.18.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.18.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.6.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.7.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.7.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.8.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.8.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.9.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.9.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.19.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.19.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.20.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.20.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.21.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.21.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.22.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.22.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.23.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.23.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.24.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.24.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.25.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.25.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.26.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.26.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.27.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.27.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.28.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.28.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.29.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.29.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.30.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.30.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.31.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.31.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.32.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.32.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.32.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.32.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.32.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.32.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.32.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.32.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.32.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.32.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.33.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.33.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.33.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.33.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.33.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.33.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.33.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.33.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.33.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.33.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.33.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.34.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.34.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.34.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.34.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.34.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.34.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.34.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.34.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.34.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.34.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.34.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.35.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.35.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.35.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.35.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.35.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.35.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.35.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.35.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.35.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.norm.weight": "model-00004-of-00004.safetensors",
+    "output_layer_vistok.0.weight": "model-00004-of-00004.safetensors",
+    "output_layer_vistok.1.weight": "model-00004-of-00004.safetensors",
+    "visual_decoder.0.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "visual_decoder.0.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "visual_decoder.0.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "visual_decoder.0.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "visual_decoder.0.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "visual_decoder.0.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
+    "visual_decoder.0.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "visual_decoder.0.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "visual_decoder.0.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
+    "visual_decoder.0.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "visual_decoder.0.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "visual_decoder.1.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "visual_decoder.1.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "visual_decoder.1.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "visual_decoder.1.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "visual_decoder.1.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "visual_decoder.1.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
+    "visual_decoder.1.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "visual_decoder.1.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "visual_decoder.1.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
+    "visual_decoder.1.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "visual_decoder.1.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "visual_decoder.2.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "visual_decoder.2.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "visual_decoder.2.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "visual_decoder.2.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "visual_decoder.2.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "visual_decoder.2.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
+    "visual_decoder.2.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "visual_decoder.2.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "visual_decoder.2.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
+    "visual_decoder.2.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "visual_decoder.2.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "visual_decoder.3.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "visual_decoder.3.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "visual_decoder.3.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "visual_decoder.3.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "visual_decoder.3.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "visual_decoder.3.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
+    "visual_decoder.3.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "visual_decoder.3.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "visual_decoder.3.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
+    "visual_decoder.3.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "visual_decoder.3.self_attn.v_proj.weight": "model-00004-of-00004.safetensors"
+  }
+}

preprocessor_config.json

@@ -0,0 +1,29 @@
+{
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "Qwen2VLImageProcessor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "max_pixels": 16777216,
+  "merge_size": 2,
+  "min_pixels": 4096,
+  "patch_size": 16,
+  "processor_class": "Qwen3VLProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "longest_edge": 16777216,
+    "shortest_edge": 4096
+  },
+  "temporal_patch_size": 2
+}

sd3_pipeline/.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

sd3_pipeline/LICENSE.md

@@ -0,0 +1,51 @@
+STABILITY AI COMMUNITY LICENSE AGREEMENT
+Last Updated: July 5, 2024
+
+
+I. INTRODUCTION
+
+This Agreement applies to any individual person or entity ("You", "Your" or "Licensee") that uses or distributes any portion or element of the Stability AI Materials  or Derivative Works thereof for any Research & Non-Commercial or Commercial purpose. Capitalized terms not otherwise defined herein are defined in Section V below.
+
+
+This Agreement is intended to allow research, non-commercial, and limited commercial uses of the Models free of charge. In order to ensure that certain limited commercial uses of the Models continue to be allowed, this Agreement  preserves free access to the Models for people or organizations  generating annual revenue of less than US $1,000,000 (or local currency equivalent).  
+
+
+By clicking "I Accept"  or by using or distributing or using any portion or element of the Stability Materials or Derivative Works, You agree that You have read, understood and are bound by the terms of this Agreement. If You are acting on behalf of a company, organization or other entity, then "You" includes you and that entity, and You agree that You: (i) are an authorized representative of such entity with the authority to bind such entity to this Agreement, and (ii) You agree to the terms of this Agreement on that entity's behalf. 
+
+II. RESEARCH & NON-COMMERCIAL USE LICENSE
+
+Subject to the terms of this Agreement, Stability AI grants You a non-exclusive, worldwide, non-transferable, non-sublicensable, revocable and royalty-free limited license under Stability AI's intellectual property or other rights owned by Stability AI embodied in the Stability AI Materials to use, reproduce, distribute, and create Derivative Works of, and make modifications to, the Stability AI Materials for any Research or Non-Commercial Purpose. "Research Purpose" means academic or scientific advancement, and in each case, is not primarily intended for commercial advantage or monetary compensation to You or others. "Non-Commercial Purpose" means any purpose other than a Research Purpose that is not primarily intended for commercial advantage or monetary compensation to You or others, such as personal use (i.e., hobbyist) or evaluation and testing.  
+
+III. COMMERCIAL USE LICENSE
+
+Subject to the terms of this Agreement (including the remainder of this Section III), Stability AI grants You a non-exclusive, worldwide, non-transferable, non-sublicensable, revocable and royalty-free limited license under Stability AI's intellectual property or other rights owned by Stability AI embodied in the Stability AI Materials to use, reproduce, distribute, and create Derivative Works of, and make modifications to, the Stability AI Materials for any Commercial Purpose. "Commercial Purpose" means any purpose other than a Research Purpose or Non-Commercial Purpose that is primarily intended for commercial advantage or monetary compensation to You or others, including but not limited to, (i) creating, modifying, or distributing Your product or service, including via a hosted service or application programming interface, and (ii) for Your business's or organization's internal operations. 
+If You are using or distributing the Stability AI Materials for a Commercial Purpose, You must register with Stability AI at (https://stability.ai/community-license). If at any time You or Your Affiliate(s), either individually or in aggregate, generate more than USD $1,000,000 in annual revenue (or the equivalent thereof in Your local currency), regardless of whether that revenue is generated directly or indirectly from the Stability AI Materials or Derivative Works, any licenses granted to You under this Agreement shall terminate as of such date. You must request a license from Stability AI at (https://stability.ai/enterprise) , which Stability AI may grant to You in its sole discretion. If you receive Stability AI Materials, or any Derivative Works thereof, from a Licensee as part of an integrated end user product, then Section III of this Agreement will not apply to you.
+
+IV. GENERAL TERMS
+
+Your Research, Non-Commercial, and Commercial License(s) under this Agreement are subject to the following terms.
+a.  Distribution & Attribution. If You distribute or make available the Stability AI Materials or a Derivative Work to a third party, or a product or service that uses any portion of them, You shall: (i) provide a copy of this Agreement to that third party, (ii) retain the following attribution notice within a "Notice" text file distributed as a part of such copies: "This Stability AI Model is licensed under the Stability AI Community License, Copyright ©  Stability AI Ltd. All Rights Reserved", and (iii) prominently display "Powered by Stability AI" on a related website, user interface, blogpost, about page, or product documentation.  If You create a Derivative Work, You may add your own attribution notice(s) to the "Notice" text file included with that Derivative Work, provided that You clearly indicate which attributions apply to the Stability AI Materials and state in the "Notice" text file that You changed the Stability AI Materials and how it was modified.
+b.  Use Restrictions. Your use of the Stability AI Materials and Derivative Works, including any output or results of the Stability AI Materials or Derivative Works, must comply with applicable laws and regulations (including Trade Control Laws and equivalent regulations) and adhere to the Documentation and Stability AI's AUP, which is hereby incorporated by reference. Furthermore, You will not use the Stability AI Materials or Derivative Works, or any output or results of the Stability AI Materials or Derivative Works, to create or improve any foundational generative AI model (excluding the Models or Derivative Works). 
+c.  Intellectual Property. 
+(i) Trademark License.  No trademark licenses are granted under this Agreement, and in connection with the Stability AI Materials or Derivative Works, You may not use any name or mark owned by or associated with Stability AI or any of its Affiliates, except as required under Section IV(a) herein.
+(ii)  Ownership of Derivative Works.  As between You and Stability AI, You are the owner of Derivative Works You create, subject to Stability AI's ownership of the Stability AI Materials and any Derivative Works made by or for Stability AI.
+(iii)  Ownership of Outputs. As between You and Stability AI, You own any outputs generated from the Models or Derivative Works to the extent permitted by applicable law. 
+(iv)  Disputes.  If You or Your Affiliate(s) institute litigation or other proceedings against Stability AI (including a cross-claim or counterclaim in a lawsuit) alleging that the Stability AI Materials, Derivative Works or associated outputs or results, or any portion of any of the foregoing, constitutes infringement of intellectual property or other rights owned or licensable by You, then any licenses granted to You under this Agreement shall terminate as of the date such litigation or claim is filed or instituted. You will indemnify and hold harmless Stability AI from and against any claim by any third party arising out of or related to Your use or distribution of the Stability AI Materials or Derivative Works in violation of this Agreement.
+(v)  Feedback.  From time to time, You may provide Stability AI with verbal and/or written suggestions, comments or other feedback related to Stability AI's existing or prospective technology, products or services (collectively, "Feedback"). You are not obligated to provide Stability AI with Feedback, but to the extent that You do, You hereby grant Stability AI a perpetual, irrevocable, royalty-free, fully-paid, sub-licensable, transferable, non-exclusive, worldwide right and license to exploit the Feedback in any manner without restriction. Your Feedback is provided "AS IS" and You make no warranties whatsoever about any Feedback.
+d.  Disclaimer Of Warranty. UNLESS REQUIRED BY APPLICABLE LAW, THE STABILITY AI MATERIALS AND ANY OUTPUT AND RESULTS THEREFROM ARE PROVIDED ON AN "AS IS" BASIS, WITHOUT WARRANTIES OF ANY KIND, EITHER EXPRESS OR IMPLIED, INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES OF TITLE, NON-INFRINGEMENT, MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE FOR DETERMINING THE APPROPRIATENESS OR LAWFULNESS OF USING OR REDISTRIBUTING THE STABILITY AI MATERIALS, DERIVATIVE WORKS OR ANY OUTPUT OR RESULTS AND ASSUME ANY RISKS ASSOCIATED WITH YOUR USE OF THE STABILITY AI MATERIALS, DERIVATIVE WORKS AND ANY OUTPUT AND RESULTS.
+e.  Limitation Of Liability. IN NO EVENT WILL STABILITY AI OR ITS AFFILIATES BE LIABLE UNDER ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, TORT, NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING OUT OF THIS AGREEMENT, FOR ANY LOST PROFITS OR ANY DIRECT, INDIRECT, SPECIAL, CONSEQUENTIAL, INCIDENTAL, EXEMPLARY OR PUNITIVE DAMAGES, EVEN IF STABILITY AI OR ITS AFFILIATES HAVE BEEN ADVISED OF THE POSSIBILITY OF ANY OF THE FOREGOING.
+f.  Term And Termination. The term of this Agreement will commence upon Your acceptance of this Agreement or access to the Stability AI Materials and will continue in full force and effect until terminated in accordance with the terms and conditions herein. Stability AI may terminate this Agreement if You are in breach of any term or condition of this Agreement. Upon termination of this Agreement, You shall delete and cease use of any Stability AI Materials or Derivative Works. Section IV(d), (e), and (g) shall survive the termination of this Agreement.
+g.  Governing Law.  This Agreement will be governed by and constructed in accordance with the laws of the United States and the State of California without regard to choice of law principles, and the UN Convention on Contracts for International Sale of Goods does not apply to this Agreement.
+
+V. DEFINITIONS 
+
+"Affiliate(s)" means any entity that directly or indirectly controls, is controlled by, or is under common control with the subject entity; for purposes of this definition, "control" means direct or indirect ownership or control of more than 50% of the voting interests of the subject entity.
+"Agreement" means this Stability AI Community License Agreement.
+"AUP" means the Stability AI Acceptable Use Policy available at https://stability.ai/use-policy, as may be updated from time to time.
+"Derivative Work(s)" means (a) any derivative work of the Stability AI Materials as recognized by U.S. copyright laws and (b) any modifications to a Model, and any other model created which is based on or derived from the Model or the Model's output, including"fine tune" and "low-rank adaptation" models derived from a Model or a Model's output, but do not include the output of any Model.
+"Documentation" means any specifications, manuals, documentation, and other written information provided by Stability AI related to the Software or Models.
+"Model(s)" means, collectively, Stability AI's proprietary models and algorithms, including machine-learning models, trained model weights and other elements of the foregoing listed on Stability's Core Models Webpage available at, https://stability.ai/core-models, as may be updated from time to time.
+"Stability AI" or "we" means Stability AI Ltd. and its Affiliates.
+"Software" means Stability AI's proprietary software made available under this Agreement now or in the future.
+"Stability AI Materials" means, collectively, Stability's proprietary Models, Software and Documentation (and any portion or combination thereof) made available under this Agreement. 
+"Trade Control Laws" means any applicable U.S. and non-U.S. export control and trade sanctions laws and regulations.

sd3_pipeline/README.md

@@ -0,0 +1,256 @@
+---
+license: other
+license_name: stabilityai-ai-community
+license_link: LICENSE.md
+tags:
+- text-to-image
+- stable-diffusion
+- diffusers
+inference: true
+extra_gated_prompt: >-
+  By clicking "Agree", you agree to the [License
+  Agreement](https://huggingface.co/stabilityai/stable-diffusion-3.5-medium/blob/main/LICENSE.md)
+  and acknowledge Stability AI's [Privacy
+  Policy](https://stability.ai/privacy-policy).
+extra_gated_fields:
+  Name: text
+  Email: text
+  Country: country
+  Organization or Affiliation: text
+  Receive email updates and promotions on Stability AI products, services, and research?:
+    type: select
+    options:
+    - 'Yes'
+    - 'No'
+  What do you intend to use the model for?: 
+    type: select
+    options:
+    - Research
+    - Personal use
+    - Creative Professional
+    - Startup
+    - Enterprise
+  I agree to the License Agreement and acknowledge Stability AI's Privacy Policy: checkbox
+
+language:
+- en
+pipeline_tag: text-to-image
+---
+
+# Stable Diffusion 3.5 Medium
+![3.5 Medium Demo Image](sd3.5_medium_demo.jpg)
+
+## Model
+
+![MMDiT-X](mmdit-x.png)
+
+[Stable Diffusion 3.5 Medium](https://stability.ai/news/introducing-stable-diffusion-3-5) is a Multimodal Diffusion Transformer with improvements (MMDiT-X) text-to-image model that features improved performance in image quality, typography, complex prompt understanding, and resource-efficiency.
+
+Please note: This model is released under the [Stability Community License](https://stability.ai/community-license-agreement). Visit [Stability AI](https://stability.ai/license) to learn or [contact us](https://stability.ai/enterprise) for commercial licensing details.
+
+
+### Model Description
+
+- **Developed by:** Stability AI
+- **Model type:** MMDiT-X text-to-image generative model
+- **Model Description:**  This model generates images based on text prompts. It is a Multimodal Diffusion Transformer
+(https://arxiv.org/abs/2403.03206) with improvements that use three fixed, pretrained text encoders, with QK-normalization to improve training stability, and dual attention blocks in the first 12 transformer layers.
+
+### License
+
+- **Community License:**  Free for research, non-commercial, and commercial use for organizations or individuals with less than $1M in total annual revenue. More details can be found in the [Community License Agreement](https://stability.ai/community-license-agreement). Read more at https://stability.ai/license.
+- **For individuals and organizations with annual revenue above $1M**: please [contact us](https://stability.ai/enterprise) to get an Enterprise License.
+
+### Model Sources
+
+For local or self-hosted use, we recommend [ComfyUI](https://github.com/comfyanonymous/ComfyUI) for node-based UI inference, or [diffusers](https://github.com/huggingface/diffusers) or [GitHub](https://github.com/Stability-AI/sd3.5) for programmatic use.
+
+- **ComfyUI:** [Github](https://github.com/comfyanonymous/ComfyUI), [Example Workflow](https://comfyanonymous.github.io/ComfyUI_examples/sd3/)
+- **Huggingface Space:** [Space](https://huggingface.co/spaces/stabilityai/stable-diffusion-3.5-medium)
+- **Diffusers**: [See below](#using-with-diffusers).
+- **GitHub**: [GitHub](https://github.com/Stability-AI/sd3.5).
+
+- **API Endpoints:**
+  - [Stability AI API](https://platform.stability.ai/docs/api-reference#tag/Generate/paths/~1v2beta~1stable-image~1generate~1sd3/post)
+
+
+### Implementation Details
+
+- **MMDiT-X:** Introduces self-attention modules in the first 13 layers of the transformer, enhancing multi-resolution generation and overall image coherence.
+
+- **QK Normalization:** Implements the QK normalization technique to improve training Stability.
+
+- **Mixed-Resolution Training:** 
+  - Progressive training stages: 256 → 512 → 768 → 1024 → 1440 resolution
+  - The final stage included mixed-scale image training to boost multi-resolution generation performance
+  - Extended positional embedding space to 384x384 (latent) at lower resolution stages
+  - Employed random crop augmentation on positional embeddings to enhance transformer layer robustness across the entire range of mixed resolutions and aspect ratios. For example, given a 64x64 latent image, we add a randomly cropped 64x64 embedding from the 192x192 embedding space during training as the input to the x stream.
+
+These enhancements collectively contribute to the model's improved performance in multi-resolution image generation, coherence, and adaptability across various text-to-image tasks.
+
+- **Text Encoders：**
+    - CLIPs: [OpenCLIP-ViT/G](https://github.com/mlfoundations/open_clip), [CLIP-ViT/L](https://github.com/openai/CLIP/tree/main), context length 77 tokens
+    - T5: [T5-xxl](https://huggingface.co/google/t5-v1_1-xxl), context length 77/256 tokens at different stages of training
+
+- **Training Data and Strategy:**
+    
+    This model was trained on a wide variety of data, including synthetic data and filtered publicly available data. 
+
+For more technical details of the original MMDiT architecture, please refer to the [Research paper](https://stability.ai/news/stable-diffusion-3-research-paper).
+
+### Usage & Limitations
+- While this model can handle long prompts, you may observe artifacts on the edge of generations when T5 tokens go over 256. Pay attention to the token limits when using this model in your workflow, and shortern prompts if artifacts becomes too obvious.
+- The medium model has a different training data distribution than the large model, so it may not respond to the same prompt similarly.
+- We recommend sampling with **[Skip Layer Guidance](https://github.com/comfyanonymous/ComfyUI/pull/5404)** for better structure and anatomy coherency.
+
+### Model Performance
+
+See [blog](https://stability.ai/news/introducing-stable-diffusion-3-5) for our study about comparative performance in prompt adherence and aesthetic quality. 
+
+
+## File Structure
+
+Click here to access the [Files and versions tab](https://huggingface.co/stabilityai/stable-diffusion-3.5-medium/tree/main)
+
+```│
+├── text_encoders/  
+│   ├── README.md
+│   ├── clip_g.safetensors
+│   ├── clip_l.safetensors
+│   ├── t5xxl_fp16.safetensors
+│   └── t5xxl_fp8_e4m3fn.safetensors
+│
+├── README.md
+├── LICENSE
+├── sd3.5_medium.safetensors
+├── SD3.5M_example_workflow.json
+├── SD3.5M_SLG_example_workflow.json
+├── SD3.5L_plus_SD3.5M_upscaling_example_workflow.json
+└── sd3_medium_demo.jpg
+
+** File structure below is for diffusers integration**
+├── scheduler/
+├── text_encoder/
+├── text_encoder_2/
+├── text_encoder_3/
+├── tokenizer/
+├── tokenizer_2/
+├── tokenizer_3/
+├── transformer/
+├── vae/
+└── model_index.json
+```
+
+## Using with Diffusers
+Upgrade to the latest version of the [🧨 diffusers library](https://github.com/huggingface/diffusers)
+```
+pip install -U diffusers
+```
+
+and then you can run
+```py
+import torch
+from diffusers import StableDiffusion3Pipeline
+
+pipe = StableDiffusion3Pipeline.from_pretrained("stabilityai/stable-diffusion-3.5-medium", torch_dtype=torch.bfloat16)
+pipe = pipe.to("cuda")
+
+image = pipe(
+    "A capybara holding a sign that reads Hello World",
+    num_inference_steps=40,
+    guidance_scale=4.5,
+).images[0]
+image.save("capybara.png")
+```
+
+### Quantizing the model with diffusers
+
+Reduce your VRAM usage and have the model fit on 🤏 VRAM GPUs
+
+```
+pip install bitsandbytes
+```
+
+```py
+from diffusers import BitsAndBytesConfig, SD3Transformer2DModel
+from diffusers import StableDiffusion3Pipeline
+import torch
+
+model_id = "stabilityai/stable-diffusion-3.5-medium"
+
+nf4_config = BitsAndBytesConfig(
+    load_in_4bit=True,
+    bnb_4bit_quant_type="nf4",
+    bnb_4bit_compute_dtype=torch.bfloat16
+)
+model_nf4 = SD3Transformer2DModel.from_pretrained(
+    model_id,
+    subfolder="transformer",
+    quantization_config=nf4_config,
+    torch_dtype=torch.bfloat16
+)
+
+pipeline = StableDiffusion3Pipeline.from_pretrained(
+    model_id, 
+    transformer=model_nf4,
+    torch_dtype=torch.bfloat16
+)
+pipeline.enable_model_cpu_offload()
+
+prompt = "A whimsical and creative image depicting a hybrid creature that is a mix of a waffle and a hippopotamus, basking in a river of melted butter amidst a breakfast-themed landscape. It features the distinctive, bulky body shape of a hippo. However, instead of the usual grey skin, the creature's body resembles a golden-brown, crispy waffle fresh off the griddle. The skin is textured with the familiar grid pattern of a waffle, each square filled with a glistening sheen of syrup. The environment combines the natural habitat of a hippo with elements of a breakfast table setting, a river of warm, melted butter, with oversized utensils or plates peeking out from the lush, pancake-like foliage in the background, a towering pepper mill standing in for a tree.  As the sun rises in this fantastical world, it casts a warm, buttery glow over the scene. The creature, content in its butter river, lets out a yawn. Nearby, a flock of birds take flight"
+
+image = pipeline(
+    prompt=prompt,
+    num_inference_steps=40,
+    guidance_scale=4.5,
+    max_sequence_length=512,
+).images[0]
+image.save("whimsical.png")
+```
+
+### Fine-tuning
+
+Please see the fine-tuning guide [here](https://stabilityai.notion.site/Stable-Diffusion-3-5-Large-Fine-tuning-Tutorial-11a61cdcd1968027a15bdbd7c40be8c6).
+
+
+## Uses
+
+### Intended Uses
+
+Intended uses include the following:
+* Generation of artworks and use in design and other artistic processes.
+* Applications in educational or creative tools.
+* Research on generative models, including understanding the limitations of generative models.
+
+All uses of the model must be in accordance with our [Acceptable Use Policy](https://stability.ai/use-policy).
+
+### Out-of-Scope Uses
+
+The model was not trained to be factual or true representations of people or events.  As such, using the model to generate such content is out-of-scope of the abilities of this model.
+
+## Safety
+
+As part of our safety-by-design and responsible AI deployment approach, we take deliberate measures to ensure Integrity starts at the early stages of development. We implement safety measures throughout the development of our models. We have implemented safety mitigations that are intended to reduce the risk of certain harms, however we recommend that developers conduct their own testing and apply additional mitigations based on their specific use cases.  
+For more about our approach to Safety, please visit our [Safety page](https://stability.ai/safety).
+
+### Integrity Evaluation
+
+Our integrity evaluation methods include structured evaluations and red-teaming testing for certain harms.  Testing was conducted primarily in English and may not cover all possible harms.  
+
+### Risks identified and mitigations:
+
+* Harmful content:  We have used filtered data sets when training our models and implemented safeguards that attempt to strike the right balance between usefulness and preventing harm. However, this does not guarantee that all possible harmful content has been removed. TAll developers and deployers should exercise caution and implement content safety guardrails based on their specific product policies and application use cases.
+* Misuse: Technical limitations and developer and end-user education can help mitigate against malicious applications of models. All users are required to adhere to our [Acceptable Use Policy](https://stability.ai/use-policy), including when applying fine-tuning and prompt engineering mechanisms. Please reference the Stability AI Acceptable Use Policy for information on violative uses of our products.
+* Privacy violations: Developers and deployers are encouraged to adhere to privacy regulations with techniques that respect data privacy.
+
+### Contact
+
+Please report any issues with the model or contact us:
+
+* Safety issues:  safety@stability.ai
+* Security issues:  security@stability.ai
+* Privacy issues:  privacy@stability.ai
+* License and general: https://stability.ai/license
+* Enterprise license: https://stability.ai/enterprise
+
+

sd3_pipeline/SD3.5L_plus_SD3.5M_upscaling_example_workflow.json

@@ -0,0 +1,1235 @@
+{
+  "last_node_id": 331,
+  "last_link_id": 672,
+  "nodes": [
+    {
+      "id": 68,
+      "type": "ConditioningSetTimestepRange",
+      "pos": [
+        756,
+        1008
+      ],
+      "size": {
+        "0": 317.4000244140625,
+        "1": 82
+      },
+      "flags": {},
+      "order": 14,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "conditioning",
+          "type": "CONDITIONING",
+          "link": 90
+        }
+      ],
+      "outputs": [
+        {
+          "name": "CONDITIONING",
+          "type": "CONDITIONING",
+          "links": [
+            91
+          ],
+          "shape": 3,
+          "slot_index": 0
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "ConditioningSetTimestepRange"
+      },
+      "widgets_values": [
+        0.1,
+        1
+      ]
+    },
+    {
+      "id": 67,
+      "type": "ConditioningZeroOut",
+      "pos": [
+        504,
+        1008
+      ],
+      "size": {
+        "0": 211.60000610351562,
+        "1": 26
+      },
+      "flags": {},
+      "order": 13,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "conditioning",
+          "type": "CONDITIONING",
+          "link": 597
+        }
+      ],
+      "outputs": [
+        {
+          "name": "CONDITIONING",
+          "type": "CONDITIONING",
+          "links": [
+            90
+          ],
+          "shape": 3,
+          "slot_index": 0
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "ConditioningZeroOut"
+      }
+    },
+    {
+      "id": 11,
+      "type": "TripleCLIPLoader",
+      "pos": [
+        -1386,
+        756
+      ],
+      "size": {
+        "0": 315,
+        "1": 106
+      },
+      "flags": {},
+      "order": 0,
+      "mode": 0,
+      "outputs": [
+        {
+          "name": "CLIP",
+          "type": "CLIP",
+          "links": [
+            5,
+            94,
+            662
+          ],
+          "shape": 3,
+          "slot_index": 0
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "TripleCLIPLoader"
+      },
+      "widgets_values": [
+        "clip_g_sdxl_base.safetensors",
+        "clip_l_sdxl_base.safetensors",
+        "t5xxl.safetensors"
+      ]
+    },
+    {
+      "id": 69,
+      "type": "ConditioningCombine",
+      "pos": [
+        1134,
+        1008
+      ],
+      "size": {
+        "0": 228.39999389648438,
+        "1": 46
+      },
+      "flags": {},
+      "order": 15,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "conditioning_1",
+          "type": "CONDITIONING",
+          "link": 91
+        },
+        {
+          "name": "conditioning_2",
+          "type": "CONDITIONING",
+          "link": 92
+        }
+      ],
+      "outputs": [
+        {
+          "name": "CONDITIONING",
+          "type": "CONDITIONING",
+          "links": [
+            604,
+            622
+          ],
+          "shape": 3,
+          "slot_index": 0
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "ConditioningCombine"
+      }
+    },
+    {
+      "id": 4,
+      "type": "CheckpointLoaderSimple",
+      "pos": [
+        -1386,
+        252
+      ],
+      "size": {
+        "0": 632.6060180664062,
+        "1": 98
+      },
+      "flags": {},
+      "order": 1,
+      "mode": 0,
+      "outputs": [
+        {
+          "name": "MODEL",
+          "type": "MODEL",
+          "links": [
+            445
+          ],
+          "shape": 3,
+          "slot_index": 0
+        },
+        {
+          "name": "CLIP",
+          "type": "CLIP",
+          "links": null,
+          "shape": 3
+        },
+        {
+          "name": "VAE",
+          "type": "VAE",
+          "links": [
+            605,
+            616,
+            617
+          ],
+          "shape": 3,
+          "slot_index": 2
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "CheckpointLoaderSimple"
+      },
+      "widgets_values": [
+        "sd3.5_large.safetensors"
+      ]
+    },
+    {
+      "id": 8,
+      "type": "VAEDecode",
+      "pos": [
+        2015,
+        536
+      ],
+      "size": {
+        "0": 210,
+        "1": 46
+      },
+      "flags": {},
+      "order": 17,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "samples",
+          "type": "LATENT",
+          "link": 572
+        },
+        {
+          "name": "vae",
+          "type": "VAE",
+          "link": 605
+        }
+      ],
+      "outputs": [
+        {
+          "name": "IMAGE",
+          "type": "IMAGE",
+          "links": [
+            274,
+            660
+          ],
+          "shape": 3,
+          "slot_index": 0
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "VAEDecode"
+      }
+    },
+    {
+      "id": 294,
+      "type": "KSampler",
+      "pos": [
+        1512,
+        378
+      ],
+      "size": {
+        "0": 378,
+        "1": 504
+      },
+      "flags": {},
+      "order": 16,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "model",
+          "type": "MODEL",
+          "link": 568
+        },
+        {
+          "name": "positive",
+          "type": "CONDITIONING",
+          "link": 569
+        },
+        {
+          "name": "negative",
+          "type": "CONDITIONING",
+          "link": 604
+        },
+        {
+          "name": "latent_image",
+          "type": "LATENT",
+          "link": 598
+        }
+      ],
+      "outputs": [
+        {
+          "name": "LATENT",
+          "type": "LATENT",
+          "links": [
+            572
+          ],
+          "shape": 3,
+          "slot_index": 0
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "KSampler"
+      },
+      "widgets_values": [
+        339087769667945,
+        "fixed",
+        40,
+        4.5,
+        "dpmpp_2m",
+        "sgm_uniform",
+        1
+      ]
+    },
+    {
+      "id": 70,
+      "type": "ConditioningSetTimestepRange",
+      "pos": [
+        756,
+        1134
+      ],
+      "size": {
+        "0": 317.4000244140625,
+        "1": 82
+      },
+      "flags": {},
+      "order": 12,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "conditioning",
+          "type": "CONDITIONING",
+          "link": 93,
+          "slot_index": 0
+        }
+      ],
+      "outputs": [
+        {
+          "name": "CONDITIONING",
+          "type": "CONDITIONING",
+          "links": [
+            92
+          ],
+          "shape": 3,
+          "slot_index": 0
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "ConditioningSetTimestepRange"
+      },
+      "widgets_values": [
+        0,
+        0.1
+      ]
+    },
+    {
+      "id": 50,
+      "type": "PreviewImage",
+      "pos": [
+        2394,
+        378
+      ],
+      "size": {
+        "0": 616.689697265625,
+        "1": 613.84130859375
+      },
+      "flags": {},
+      "order": 18,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "images",
+          "type": "IMAGE",
+          "link": 274
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "PreviewImage"
+      }
+    },
+    {
+      "id": 308,
+      "type": "VAEEncode",
+      "pos": [
+        3150,
+        378
+      ],
+      "size": {
+        "0": 210,
+        "1": 46
+      },
+      "flags": {},
+      "order": 21,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "pixels",
+          "type": "IMAGE",
+          "link": 671
+        },
+        {
+          "name": "vae",
+          "type": "VAE",
+          "link": 616
+        }
+      ],
+      "outputs": [
+        {
+          "name": "LATENT",
+          "type": "LATENT",
+          "links": [
+            623
+          ],
+          "shape": 3,
+          "slot_index": 0
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "VAEEncode"
+      }
+    },
+    {
+      "id": 310,
+      "type": "KSamplerAdvanced",
+      "pos": [
+        3402,
+        378
+      ],
+      "size": {
+        "0": 378,
+        "1": 546
+      },
+      "flags": {},
+      "order": 22,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "model",
+          "type": "MODEL",
+          "link": 620
+        },
+        {
+          "name": "positive",
+          "type": "CONDITIONING",
+          "link": 665
+        },
+        {
+          "name": "negative",
+          "type": "CONDITIONING",
+          "link": 622
+        },
+        {
+          "name": "latent_image",
+          "type": "LATENT",
+          "link": 623
+        },
+        {
+          "name": "start_at_step",
+          "type": "INT",
+          "link": 672,
+          "widget": {
+            "name": "start_at_step"
+          }
+        }
+      ],
+      "outputs": [
+        {
+          "name": "LATENT",
+          "type": "LATENT",
+          "links": [
+            624
+          ],
+          "shape": 3,
+          "slot_index": 0
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "KSamplerAdvanced"
+      },
+      "widgets_values": [
+        "enable",
+        383006107596742,
+        "increment",
+        42,
+        4.5,
+        "dpmpp_2m",
+        "sgm_uniform",
+        30,
+        10000,
+        "disable"
+      ]
+    },
+    {
+      "id": 305,
+      "type": "VAEDecode",
+      "pos": [
+        3906,
+        378
+      ],
+      "size": {
+        "0": 210,
+        "1": 46
+      },
+      "flags": {},
+      "order": 23,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "samples",
+          "type": "LATENT",
+          "link": 624
+        },
+        {
+          "name": "vae",
+          "type": "VAE",
+          "link": 617
+        }
+      ],
+      "outputs": [
+        {
+          "name": "IMAGE",
+          "type": "IMAGE",
+          "links": [
+            670
+          ],
+          "shape": 3,
+          "slot_index": 0
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "VAEDecode"
+      }
+    },
+    {
+      "id": 306,
+      "type": "PreviewImage",
+      "pos": [
+        4284,
+        378
+      ],
+      "size": {
+        "0": 616.689697265625,
+        "1": 613.84130859375
+      },
+      "flags": {},
+      "order": 24,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "images",
+          "type": "IMAGE",
+          "link": 670
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "PreviewImage"
+      }
+    },
+    {
+      "id": 309,
+      "type": "PreviewImage",
+      "pos": [
+        4032,
+        630
+      ],
+      "size": {
+        "0": 210,
+        "1": 246
+      },
+      "flags": {},
+      "order": 20,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "images",
+          "type": "IMAGE",
+          "link": 619
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "PreviewImage"
+      }
+    },
+    {
+      "id": 105,
+      "type": "Note",
+      "pos": [
+        -630,
+        630
+      ],
+      "size": {
+        "0": 210,
+        "1": 110.18948364257812
+      },
+      "flags": {},
+      "order": 2,
+      "mode": 0,
+      "properties": {
+        "text": ""
+      },
+      "widgets_values": [
+        "Make sure the resolution is multiple of 64 pixels and adds up to around 1 megapixel. "
+      ],
+      "color": "#432",
+      "bgcolor": "#653"
+    },
+    {
+      "id": 302,
+      "type": "ModelSamplingSD3",
+      "pos": [
+        756,
+        504
+      ],
+      "size": {
+        "0": 315,
+        "1": 58
+      },
+      "flags": {
+        "collapsed": false
+      },
+      "order": 11,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "model",
+          "type": "MODEL",
+          "link": 606
+        }
+      ],
+      "outputs": [
+        {
+          "name": "MODEL",
+          "type": "MODEL",
+          "links": [
+            620
+          ],
+          "shape": 3,
+          "slot_index": 0
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "ModelSamplingSD3"
+      },
+      "widgets_values": [
+        3
+      ]
+    },
+    {
+      "id": 13,
+      "type": "ModelSamplingSD3",
+      "pos": [
+        756,
+        252
+      ],
+      "size": {
+        "0": 315,
+        "1": 58
+      },
+      "flags": {
+        "collapsed": false
+      },
+      "order": 10,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "model",
+          "type": "MODEL",
+          "link": 445
+        }
+      ],
+      "outputs": [
+        {
+          "name": "MODEL",
+          "type": "MODEL",
+          "links": [
+            568
+          ],
+          "shape": 3,
+          "slot_index": 0
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "ModelSamplingSD3"
+      },
+      "widgets_values": [
+        3
+      ]
+    },
+    {
+      "id": 307,
+      "type": "ImageScaleBy",
+      "pos": [
+        2394,
+        252
+      ],
+      "size": {
+        "0": 315,
+        "1": 82
+      },
+      "flags": {},
+      "order": 19,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "image",
+          "type": "IMAGE",
+          "link": 660
+        }
+      ],
+      "outputs": [
+        {
+          "name": "IMAGE",
+          "type": "IMAGE",
+          "links": [
+            619,
+            671
+          ],
+          "shape": 3,
+          "slot_index": 0
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "ImageScaleBy"
+      },
+      "widgets_values": [
+        "lanczos",
+        1.4000000000000001
+      ]
+    },
+    {
+      "id": 330,
+      "type": "PrimitiveNode",
+      "pos": [
+        3150,
+        504
+      ],
+      "size": {
+        "0": 210,
+        "1": 82
+      },
+      "flags": {},
+      "order": 3,
+      "mode": 0,
+      "outputs": [
+        {
+          "name": "INT",
+          "type": "INT",
+          "links": [
+            672
+          ],
+          "slot_index": 0,
+          "widget": {
+            "name": "start_at_step"
+          }
+        }
+      ],
+      "title": "Start at Step",
+      "properties": {
+        "Run widget replace on values": false
+      },
+      "widgets_values": [
+        30,
+        "fixed"
+      ]
+    },
+    {
+      "id": 135,
+      "type": "EmptySD3LatentImage",
+      "pos": [
+        -378,
+        630
+      ],
+      "size": {
+        "0": 315,
+        "1": 106
+      },
+      "flags": {},
+      "order": 4,
+      "mode": 0,
+      "inputs": [],
+      "outputs": [
+        {
+          "name": "LATENT",
+          "type": "LATENT",
+          "links": [
+            598
+          ],
+          "shape": 3,
+          "slot_index": 0
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "EmptySD3LatentImage"
+      },
+      "widgets_values": [
+        1152,
+        896,
+        1
+      ]
+    },
+    {
+      "id": 301,
+      "type": "CheckpointLoaderSimple",
+      "pos": [
+        -1386,
+        504
+      ],
+      "size": {
+        "0": 632.6060180664062,
+        "1": 98
+      },
+      "flags": {},
+      "order": 5,
+      "mode": 0,
+      "outputs": [
+        {
+          "name": "MODEL",
+          "type": "MODEL",
+          "links": [
+            606
+          ],
+          "shape": 3,
+          "slot_index": 0
+        },
+        {
+          "name": "CLIP",
+          "type": "CLIP",
+          "links": null,
+          "shape": 3
+        },
+        {
+          "name": "VAE",
+          "type": "VAE",
+          "links": [],
+          "shape": 3,
+          "slot_index": 2
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "CheckpointLoaderSimple"
+      },
+      "widgets_values": [
+        "sd3.5_medium.safetensors"
+      ]
+    },
+    {
+      "id": 71,
+      "type": "CLIPTextEncode",
+      "pos": [
+        -378,
+        1260
+      ],
+      "size": {
+        "0": 351.8130798339844,
+        "1": 195.57545471191406
+      },
+      "flags": {},
+      "order": 8,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "clip",
+          "type": "CLIP",
+          "link": 94
+        }
+      ],
+      "outputs": [
+        {
+          "name": "CONDITIONING",
+          "type": "CONDITIONING",
+          "links": [
+            93,
+            597
+          ],
+          "shape": 3,
+          "slot_index": 0
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "CLIPTextEncode"
+      },
+      "widgets_values": [
+        ""
+      ],
+      "color": "#322",
+      "bgcolor": "#533"
+    },
+    {
+      "id": 6,
+      "type": "CLIPTextEncode",
+      "pos": [
+        -378,
+        882
+      ],
+      "size": [
+        342.21509258248534,
+        195.87930444715585
+      ],
+      "flags": {},
+      "order": 7,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "clip",
+          "type": "CLIP",
+          "link": 5
+        }
+      ],
+      "outputs": [
+        {
+          "name": "CONDITIONING",
+          "type": "CONDITIONING",
+          "links": [
+            569
+          ],
+          "shape": 3,
+          "slot_index": 0
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "CLIPTextEncode"
+      },
+      "widgets_values": [
+        "cinematic film still, epic, photo of a woman wearing sunglasses"
+      ],
+      "color": "#232",
+      "bgcolor": "#353"
+    },
+    {
+      "id": 324,
+      "type": "CLIPTextEncode",
+      "pos": [
+        -378,
+        1134
+      ],
+      "size": [
+        346.27611650227504,
+        80.0318642466309
+      ],
+      "flags": {},
+      "order": 9,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "clip",
+          "type": "CLIP",
+          "link": 662
+        }
+      ],
+      "outputs": [
+        {
+          "name": "CONDITIONING",
+          "type": "CONDITIONING",
+          "links": [
+            665
+          ],
+          "shape": 3,
+          "slot_index": 0
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "CLIPTextEncode"
+      },
+      "widgets_values": [
+        "cinematic film still, epic, photo of a woman wearing sunglasses"
+      ],
+      "color": "#232",
+      "bgcolor": "#353"
+    },
+    {
+      "id": 329,
+      "type": "Note",
+      "pos": [
+        -630,
+        1134
+      ],
+      "size": [
+        222.24755928435616,
+        69.25623726364165
+      ],
+      "flags": {},
+      "order": 6,
+      "mode": 0,
+      "properties": {
+        "text": ""
+      },
+      "widgets_values": [
+        "Medium has a token limit on T5. Use a shorter version of the prompt limited to ~70 words or truncate"
+      ],
+      "color": "#432",
+      "bgcolor": "#653"
+    }
+  ],
+  "links": [
+    [
+      5,
+      11,
+      0,
+      6,
+      0,
+      "CLIP"
+    ],
+    [
+      90,
+      67,
+      0,
+      68,
+      0,
+      "CONDITIONING"
+    ],
+    [
+      91,
+      68,
+      0,
+      69,
+      0,
+      "CONDITIONING"
+    ],
+    [
+      92,
+      70,
+      0,
+      69,
+      1,
+      "CONDITIONING"
+    ],
+    [
+      93,
+      71,
+      0,
+      70,
+      0,
+      "CONDITIONING"
+    ],
+    [
+      94,
+      11,
+      0,
+      71,
+      0,
+      "CLIP"
+    ],
+    [
+      274,
+      8,
+      0,
+      50,
+      0,
+      "IMAGE"
+    ],
+    [
+      445,
+      4,
+      0,
+      13,
+      0,
+      "MODEL"
+    ],
+    [
+      568,
+      13,
+      0,
+      294,
+      0,
+      "MODEL"
+    ],
+    [
+      569,
+      6,
+      0,
+      294,
+      1,
+      "CONDITIONING"
+    ],
+    [
+      572,
+      294,
+      0,
+      8,
+      0,
+      "LATENT"
+    ],
+    [
+      597,
+      71,
+      0,
+      67,
+      0,
+      "CONDITIONING"
+    ],
+    [
+      598,
+      135,
+      0,
+      294,
+      3,
+      "LATENT"
+    ],
+    [
+      604,
+      69,
+      0,
+      294,
+      2,
+      "CONDITIONING"
+    ],
+    [
+      605,
+      4,
+      2,
+      8,
+      1,
+      "VAE"
+    ],
+    [
+      606,
+      301,
+      0,
+      302,
+      0,
+      "MODEL"
+    ],
+    [
+      616,
+      4,
+      2,
+      308,
+      1,
+      "VAE"
+    ],
+    [
+      617,
+      4,
+      2,
+      305,
+      1,
+      "VAE"
+    ],
+    [
+      619,
+      307,
+      0,
+      309,
+      0,
+      "IMAGE"
+    ],
+    [
+      620,
+      302,
+      0,
+      310,
+      0,
+      "MODEL"
+    ],
+    [
+      622,
+      69,
+      0,
+      310,
+      2,
+      "CONDITIONING"
+    ],
+    [
+      623,
+      308,
+      0,
+      310,
+      3,
+      "LATENT"
+    ],
+    [
+      624,
+      310,
+      0,
+      305,
+      0,
+      "LATENT"
+    ],
+    [
+      660,
+      8,
+      0,
+      307,
+      0,
+      "IMAGE"
+    ],
+    [
+      662,
+      11,
+      0,
+      324,
+      0,
+      "CLIP"
+    ],
+    [
+      665,
+      324,
+      0,
+      310,
+      1,
+      "CONDITIONING"
+    ],
+    [
+      670,
+      305,
+      0,
+      306,
+      0,
+      "IMAGE"
+    ],
+    [
+      671,
+      307,
+      0,
+      308,
+      0,
+      "IMAGE"
+    ],
+    [
+      672,
+      330,
+      0,
+      310,
+      4,
+      "INT"
+    ]
+  ],
+  "groups": [],
+  "config": {},
+  "extra": {
+    "ds": {
+      "scale": 0.3797498335833178,
+      "offset": [
+        2577.2791383634726,
+        94.5657992857425
+      ]
+    }
+  },
+  "version": 0.4
+}

sd3_pipeline/SD3.5M_SLG_example_workflow.json

@@ -0,0 +1,1006 @@
+{
+  "last_node_id": 305,
+  "last_link_id": 627,
+  "nodes": [
+    {
+      "id": 11,
+      "type": "TripleCLIPLoader",
+      "pos": {
+        "0": -2016,
+        "1": -252
+      },
+      "size": {
+        "0": 315,
+        "1": 106
+      },
+      "flags": {},
+      "order": 0,
+      "mode": 0,
+      "inputs": [],
+      "outputs": [
+        {
+          "name": "CLIP",
+          "type": "CLIP",
+          "links": [
+            5,
+            94
+          ],
+          "slot_index": 0,
+          "shape": 3
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "TripleCLIPLoader"
+      },
+      "widgets_values": [
+        "sdv3/clip_g.safetensors",
+        "sdv3/clip_l.safetensors",
+        "sdv3/t5xxl_fp16.safetensors"
+      ]
+    },
+    {
+      "id": 303,
+      "type": "VAEDecode",
+      "pos": {
+        "0": 1381,
+        "1": 233
+      },
+      "size": {
+        "0": 210,
+        "1": 46
+      },
+      "flags": {},
+      "order": 15,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "samples",
+          "type": "LATENT",
+          "link": 612
+        },
+        {
+          "name": "vae",
+          "type": "VAE",
+          "link": 614
+        }
+      ],
+      "outputs": [
+        {
+          "name": "IMAGE",
+          "type": "IMAGE",
+          "links": [
+            613
+          ],
+          "slot_index": 0,
+          "shape": 3
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "VAEDecode"
+      },
+      "widgets_values": []
+    },
+    {
+      "id": 105,
+      "type": "Note",
+      "pos": {
+        "0": -1484,
+        "1": -249
+      },
+      "size": {
+        "0": 210,
+        "1": 110.18948364257812
+      },
+      "flags": {},
+      "order": 1,
+      "mode": 0,
+      "inputs": [],
+      "outputs": [],
+      "properties": {
+        "text": ""
+      },
+      "widgets_values": [
+        "Make sure the resolution is multiple of 64 pixels and adds up to around 1 megapixel. "
+      ],
+      "color": "#432",
+      "bgcolor": "#653"
+    },
+    {
+      "id": 304,
+      "type": "PreviewImage",
+      "pos": {
+        "0": 1758,
+        "1": 150
+      },
+      "size": {
+        "0": 616.689697265625,
+        "1": 613.84130859375
+      },
+      "flags": {},
+      "order": 17,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "images",
+          "type": "IMAGE",
+          "link": 613
+        }
+      ],
+      "outputs": [],
+      "properties": {
+        "Node name for S&R": "PreviewImage"
+      },
+      "widgets_values": []
+    },
+    {
+      "id": 50,
+      "type": "PreviewImage",
+      "pos": {
+        "0": 1764,
+        "1": -504
+      },
+      "size": {
+        "0": 616.689697265625,
+        "1": 613.84130859375
+      },
+      "flags": {},
+      "order": 18,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "images",
+          "type": "IMAGE",
+          "link": 274
+        }
+      ],
+      "outputs": [],
+      "properties": {
+        "Node name for S&R": "PreviewImage"
+      },
+      "widgets_values": []
+    },
+    {
+      "id": 67,
+      "type": "ConditioningZeroOut",
+      "pos": {
+        "0": -1103,
+        "1": 454
+      },
+      "size": {
+        "0": 211.60000610351562,
+        "1": 26
+      },
+      "flags": {},
+      "order": 8,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "conditioning",
+          "type": "CONDITIONING",
+          "link": 597
+        }
+      ],
+      "outputs": [
+        {
+          "name": "CONDITIONING",
+          "type": "CONDITIONING",
+          "links": [
+            90
+          ],
+          "slot_index": 0,
+          "shape": 3
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "ConditioningZeroOut"
+      },
+      "widgets_values": []
+    },
+    {
+      "id": 68,
+      "type": "ConditioningSetTimestepRange",
+      "pos": {
+        "0": -839,
+        "1": 442
+      },
+      "size": {
+        "0": 317.4000244140625,
+        "1": 82
+      },
+      "flags": {},
+      "order": 11,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "conditioning",
+          "type": "CONDITIONING",
+          "link": 90
+        }
+      ],
+      "outputs": [
+        {
+          "name": "CONDITIONING",
+          "type": "CONDITIONING",
+          "links": [
+            91
+          ],
+          "slot_index": 0,
+          "shape": 3
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "ConditioningSetTimestepRange"
+      },
+      "widgets_values": [
+        0.1,
+        1
+      ]
+    },
+    {
+      "id": 69,
+      "type": "ConditioningCombine",
+      "pos": {
+        "0": -129,
+        "1": 290
+      },
+      "size": {
+        "0": 228.39999389648438,
+        "1": 46
+      },
+      "flags": {},
+      "order": 12,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "conditioning_1",
+          "type": "CONDITIONING",
+          "link": 91
+        },
+        {
+          "name": "conditioning_2",
+          "type": "CONDITIONING",
+          "link": 92
+        }
+      ],
+      "outputs": [
+        {
+          "name": "CONDITIONING",
+          "type": "CONDITIONING",
+          "links": [
+            621,
+            625
+          ],
+          "slot_index": 0,
+          "shape": 3
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "ConditioningCombine"
+      },
+      "widgets_values": []
+    },
+    {
+      "id": 13,
+      "type": "ModelSamplingSD3",
+      "pos": {
+        "0": -424,
+        "1": -516
+      },
+      "size": {
+        "0": 315,
+        "1": 58
+      },
+      "flags": {
+        "collapsed": false
+      },
+      "order": 7,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "model",
+          "type": "MODEL",
+          "link": 445
+        }
+      ],
+      "outputs": [
+        {
+          "name": "MODEL",
+          "type": "MODEL",
+          "links": [
+            606,
+            618
+          ],
+          "slot_index": 0,
+          "shape": 3
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "ModelSamplingSD3"
+      },
+      "widgets_values": [
+        3
+      ]
+    },
+    {
+      "id": 135,
+      "type": "EmptySD3LatentImage",
+      "pos": {
+        "0": -1195,
+        "1": -251
+      },
+      "size": {
+        "0": 315,
+        "1": 106
+      },
+      "flags": {},
+      "order": 2,
+      "mode": 0,
+      "inputs": [],
+      "outputs": [
+        {
+          "name": "LATENT",
+          "type": "LATENT",
+          "links": [
+            598,
+            611
+          ],
+          "slot_index": 0,
+          "shape": 3
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "EmptySD3LatentImage"
+      },
+      "widgets_values": [
+        1280,
+        768,
+        1
+      ]
+    },
+    {
+      "id": 8,
+      "type": "VAEDecode",
+      "pos": {
+        "0": 1387,
+        "1": -415
+      },
+      "size": {
+        "0": 210,
+        "1": 46
+      },
+      "flags": {},
+      "order": 16,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "samples",
+          "type": "LATENT",
+          "link": 572
+        },
+        {
+          "name": "vae",
+          "type": "VAE",
+          "link": 605
+        }
+      ],
+      "outputs": [
+        {
+          "name": "IMAGE",
+          "type": "IMAGE",
+          "links": [
+            274
+          ],
+          "slot_index": 0,
+          "shape": 3
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "VAEDecode"
+      },
+      "widgets_values": []
+    },
+    {
+      "id": 4,
+      "type": "CheckpointLoaderSimple",
+      "pos": {
+        "0": -2016,
+        "1": -504
+      },
+      "size": [
+        311.9781150464221,
+        99.19846549382407
+      ],
+      "flags": {},
+      "order": 3,
+      "mode": 0,
+      "inputs": [],
+      "outputs": [
+        {
+          "name": "MODEL",
+          "type": "MODEL",
+          "links": [
+            445
+          ],
+          "slot_index": 0,
+          "shape": 3
+        },
+        {
+          "name": "CLIP",
+          "type": "CLIP",
+          "links": null,
+          "shape": 3
+        },
+        {
+          "name": "VAE",
+          "type": "VAE",
+          "links": [
+            605,
+            614
+          ],
+          "slot_index": 2,
+          "shape": 3
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "CheckpointLoaderSimple"
+      },
+      "widgets_values": [
+        "sd3.5_medium.safetensors"
+      ]
+    },
+    {
+      "id": 302,
+      "type": "KSampler",
+      "pos": {
+        "0": 962,
+        "1": 236
+      },
+      "size": {
+        "0": 378,
+        "1": 504
+      },
+      "flags": {},
+      "order": 13,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "model",
+          "type": "MODEL",
+          "link": 618
+        },
+        {
+          "name": "positive",
+          "type": "CONDITIONING",
+          "link": 610
+        },
+        {
+          "name": "negative",
+          "type": "CONDITIONING",
+          "link": 621
+        },
+        {
+          "name": "latent_image",
+          "type": "LATENT",
+          "link": 611
+        },
+        {
+          "name": "seed",
+          "type": "INT",
+          "link": 617,
+          "widget": {
+            "name": "seed"
+          }
+        }
+      ],
+      "outputs": [
+        {
+          "name": "LATENT",
+          "type": "LATENT",
+          "links": [
+            612
+          ],
+          "slot_index": 0,
+          "shape": 3
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "KSampler"
+      },
+      "widgets_values": [
+        42,
+        "randomize",
+        50,
+        5,
+        "dpmpp_2m",
+        "sgm_uniform",
+        1
+      ]
+    },
+    {
+      "id": 301,
+      "type": "SkipLayerGuidanceSD3",
+      "pos": {
+        "0": 234,
+        "1": -513
+      },
+      "size": {
+        "0": 315,
+        "1": 130
+      },
+      "flags": {},
+      "order": 10,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "model",
+          "type": "MODEL",
+          "link": 606
+        }
+      ],
+      "outputs": [
+        {
+          "name": "MODEL",
+          "type": "MODEL",
+          "links": [
+            607
+          ],
+          "slot_index": 0
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "SkipLayerGuidanceSD3"
+      },
+      "widgets_values": [
+        "7,8,9",
+        2,
+        0.01,
+        0.15
+      ]
+    },
+    {
+      "id": 70,
+      "type": "ConditioningSetTimestepRange",
+      "pos": {
+        "0": -851,
+        "1": 274
+      },
+      "size": {
+        "0": 317.4000244140625,
+        "1": 82
+      },
+      "flags": {},
+      "order": 9,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "conditioning",
+          "type": "CONDITIONING",
+          "link": 627,
+          "slot_index": 0
+        }
+      ],
+      "outputs": [
+        {
+          "name": "CONDITIONING",
+          "type": "CONDITIONING",
+          "links": [
+            92
+          ],
+          "slot_index": 0,
+          "shape": 3
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "ConditioningSetTimestepRange"
+      },
+      "widgets_values": [
+        0,
+        0.1
+      ]
+    },
+    {
+      "id": 71,
+      "type": "CLIPTextEncode",
+      "pos": {
+        "0": -1547,
+        "1": 348
+      },
+      "size": {
+        "0": 351.8130798339844,
+        "1": 195.57545471191406
+      },
+      "flags": {},
+      "order": 6,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "clip",
+          "type": "CLIP",
+          "link": 94
+        }
+      ],
+      "outputs": [
+        {
+          "name": "CONDITIONING",
+          "type": "CONDITIONING",
+          "links": [
+            597,
+            627
+          ],
+          "slot_index": 0,
+          "shape": 3
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "CLIPTextEncode"
+      },
+      "widgets_values": [
+        ""
+      ],
+      "color": "#322",
+      "bgcolor": "#533"
+    },
+    {
+      "id": 294,
+      "type": "KSampler",
+      "pos": {
+        "0": 969,
+        "1": -417
+      },
+      "size": {
+        "0": 378,
+        "1": 504
+      },
+      "flags": {},
+      "order": 14,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "model",
+          "type": "MODEL",
+          "link": 607
+        },
+        {
+          "name": "positive",
+          "type": "CONDITIONING",
+          "link": 626
+        },
+        {
+          "name": "negative",
+          "type": "CONDITIONING",
+          "link": 625
+        },
+        {
+          "name": "latent_image",
+          "type": "LATENT",
+          "link": 598
+        },
+        {
+          "name": "seed",
+          "type": "INT",
+          "link": 616,
+          "widget": {
+            "name": "seed"
+          }
+        }
+      ],
+      "outputs": [
+        {
+          "name": "LATENT",
+          "type": "LATENT",
+          "links": [
+            572
+          ],
+          "slot_index": 0,
+          "shape": 3
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "KSampler"
+      },
+      "widgets_values": [
+        42,
+        "randomize",
+        50,
+        4,
+        "dpmpp_2m",
+        "sgm_uniform",
+        1
+      ]
+    },
+    {
+      "id": 305,
+      "type": "PrimitiveNode",
+      "pos": {
+        "0": -155,
+        "1": -674
+      },
+      "size": {
+        "0": 285.3897399902344,
+        "1": 86.61906433105469
+      },
+      "flags": {},
+      "order": 4,
+      "mode": 0,
+      "inputs": [],
+      "outputs": [
+        {
+          "name": "INT",
+          "type": "INT",
+          "links": [
+            616,
+            617
+          ],
+          "slot_index": 0,
+          "widget": {
+            "name": "seed"
+          }
+        }
+      ],
+      "title": "seed",
+      "properties": {
+        "Run widget replace on values": false
+      },
+      "widgets_values": [
+        42,
+        "fixed"
+      ]
+    },
+    {
+      "id": 6,
+      "type": "CLIPTextEncode",
+      "pos": {
+        "0": -1547,
+        "1": 123
+      },
+      "size": {
+        "0": 342.8335266113281,
+        "1": 177.20867919921875
+      },
+      "flags": {},
+      "order": 5,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "clip",
+          "type": "CLIP",
+          "link": 5
+        }
+      ],
+      "outputs": [
+        {
+          "name": "CONDITIONING",
+          "type": "CONDITIONING",
+          "links": [
+            610,
+            626
+          ],
+          "slot_index": 0,
+          "shape": 3
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "CLIPTextEncode"
+      },
+      "widgets_values": [
+        "photorealistic photography girl floating in air in white dress\n"
+      ],
+      "color": "#232",
+      "bgcolor": "#353"
+    }
+  ],
+  "links": [
+    [
+      5,
+      11,
+      0,
+      6,
+      0,
+      "CLIP"
+    ],
+    [
+      90,
+      67,
+      0,
+      68,
+      0,
+      "CONDITIONING"
+    ],
+    [
+      91,
+      68,
+      0,
+      69,
+      0,
+      "CONDITIONING"
+    ],
+    [
+      92,
+      70,
+      0,
+      69,
+      1,
+      "CONDITIONING"
+    ],
+    [
+      94,
+      11,
+      0,
+      71,
+      0,
+      "CLIP"
+    ],
+    [
+      274,
+      8,
+      0,
+      50,
+      0,
+      "IMAGE"
+    ],
+    [
+      445,
+      4,
+      0,
+      13,
+      0,
+      "MODEL"
+    ],
+    [
+      572,
+      294,
+      0,
+      8,
+      0,
+      "LATENT"
+    ],
+    [
+      597,
+      71,
+      0,
+      67,
+      0,
+      "CONDITIONING"
+    ],
+    [
+      598,
+      135,
+      0,
+      294,
+      3,
+      "LATENT"
+    ],
+    [
+      605,
+      4,
+      2,
+      8,
+      1,
+      "VAE"
+    ],
+    [
+      606,
+      13,
+      0,
+      301,
+      0,
+      "MODEL"
+    ],
+    [
+      607,
+      301,
+      0,
+      294,
+      0,
+      "MODEL"
+    ],
+    [
+      610,
+      6,
+      0,
+      302,
+      1,
+      "CONDITIONING"
+    ],
+    [
+      611,
+      135,
+      0,
+      302,
+      3,
+      "LATENT"
+    ],
+    [
+      612,
+      302,
+      0,
+      303,
+      0,
+      "LATENT"
+    ],
+    [
+      613,
+      303,
+      0,
+      304,
+      0,
+      "IMAGE"
+    ],
+    [
+      614,
+      4,
+      2,
+      303,
+      1,
+      "VAE"
+    ],
+    [
+      616,
+      305,
+      0,
+      294,
+      4,
+      "INT"
+    ],
+    [
+      617,
+      305,
+      0,
+      302,
+      4,
+      "INT"
+    ],
+    [
+      618,
+      13,
+      0,
+      302,
+      0,
+      "MODEL"
+    ],
+    [
+      621,
+      69,
+      0,
+      302,
+      2,
+      "CONDITIONING"
+    ],
+    [
+      625,
+      69,
+      0,
+      294,
+      2,
+      "CONDITIONING"
+    ],
+    [
+      626,
+      6,
+      0,
+      294,
+      1,
+      "CONDITIONING"
+    ],
+    [
+      627,
+      71,
+      0,
+      70,
+      0,
+      "CONDITIONING"
+    ]
+  ],
+  "groups": [],
+  "config": {},
+  "extra": {
+    "ds": {
+      "scale": 1.0834705943388945,
+      "offset": [
+        2786.463291970421,
+        276.88316957958125
+      ]
+    }
+  },
+  "version": 0.4
+}

sd3_pipeline/SD3.5M_example_workflow.json

@@ -0,0 +1,697 @@
+{
+  "last_node_id": 300,
+  "last_link_id": 605,
+  "nodes": [
+    {
+      "id": 67,
+      "type": "ConditioningZeroOut",
+      "pos": {
+        "0": -126,
+        "1": 126
+      },
+      "size": {
+        "0": 211.60000610351562,
+        "1": 26
+      },
+      "flags": {},
+      "order": 8,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "conditioning",
+          "type": "CONDITIONING",
+          "link": 597
+        }
+      ],
+      "outputs": [
+        {
+          "name": "CONDITIONING",
+          "type": "CONDITIONING",
+          "links": [
+            90
+          ],
+          "slot_index": 0,
+          "shape": 3
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "ConditioningZeroOut"
+      },
+      "widgets_values": []
+    },
+    {
+      "id": 71,
+      "type": "CLIPTextEncode",
+      "pos": {
+        "0": -1010,
+        "1": 252
+      },
+      "size": {
+        "0": 351.8130798339844,
+        "1": 195.57545471191406
+      },
+      "flags": {},
+      "order": 6,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "clip",
+          "type": "CLIP",
+          "link": 94
+        }
+      ],
+      "outputs": [
+        {
+          "name": "CONDITIONING",
+          "type": "CONDITIONING",
+          "links": [
+            93,
+            597
+          ],
+          "slot_index": 0,
+          "shape": 3
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "CLIPTextEncode"
+      },
+      "widgets_values": [
+        ""
+      ],
+      "color": "#322",
+      "bgcolor": "#533"
+    },
+    {
+      "id": 6,
+      "type": "CLIPTextEncode",
+      "pos": {
+        "0": -1008,
+        "1": 2
+      },
+      "size": {
+        "0": 342.8335266113281,
+        "1": 177.20867919921875
+      },
+      "flags": {},
+      "order": 5,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "clip",
+          "type": "CLIP",
+          "link": 5
+        }
+      ],
+      "outputs": [
+        {
+          "name": "CONDITIONING",
+          "type": "CONDITIONING",
+          "links": [
+            569
+          ],
+          "slot_index": 0,
+          "shape": 3
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "CLIPTextEncode"
+      },
+      "widgets_values": [
+        "beautiful scenery nature glass bottle landscape, purple galaxy bottle,"
+      ],
+      "color": "#232",
+      "bgcolor": "#353"
+    },
+    {
+      "id": 69,
+      "type": "ConditioningCombine",
+      "pos": {
+        "0": 504,
+        "1": 126
+      },
+      "size": {
+        "0": 228.39999389648438,
+        "1": 46
+      },
+      "flags": {},
+      "order": 10,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "conditioning_1",
+          "type": "CONDITIONING",
+          "link": 91
+        },
+        {
+          "name": "conditioning_2",
+          "type": "CONDITIONING",
+          "link": 92
+        }
+      ],
+      "outputs": [
+        {
+          "name": "CONDITIONING",
+          "type": "CONDITIONING",
+          "links": [
+            604
+          ],
+          "slot_index": 0,
+          "shape": 3
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "ConditioningCombine"
+      },
+      "widgets_values": []
+    },
+    {
+      "id": 8,
+      "type": "VAEDecode",
+      "pos": {
+        "0": 1386,
+        "1": -504
+      },
+      "size": {
+        "0": 210,
+        "1": 46
+      },
+      "flags": {},
+      "order": 12,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "samples",
+          "type": "LATENT",
+          "link": 572
+        },
+        {
+          "name": "vae",
+          "type": "VAE",
+          "link": 605
+        }
+      ],
+      "outputs": [
+        {
+          "name": "IMAGE",
+          "type": "IMAGE",
+          "links": [
+            274
+          ],
+          "slot_index": 0,
+          "shape": 3
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "VAEDecode"
+      },
+      "widgets_values": []
+    },
+    {
+      "id": 50,
+      "type": "PreviewImage",
+      "pos": {
+        "0": 1764,
+        "1": -504
+      },
+      "size": {
+        "0": 616.689697265625,
+        "1": 613.84130859375
+      },
+      "flags": {},
+      "order": 13,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "images",
+          "type": "IMAGE",
+          "link": 274
+        }
+      ],
+      "outputs": [],
+      "properties": {
+        "Node name for S&R": "PreviewImage"
+      },
+      "widgets_values": []
+    },
+    {
+      "id": 68,
+      "type": "ConditioningSetTimestepRange",
+      "pos": {
+        "0": 126,
+        "1": 126
+      },
+      "size": {
+        "0": 317.4000244140625,
+        "1": 82
+      },
+      "flags": {},
+      "order": 9,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "conditioning",
+          "type": "CONDITIONING",
+          "link": 90
+        }
+      ],
+      "outputs": [
+        {
+          "name": "CONDITIONING",
+          "type": "CONDITIONING",
+          "links": [
+            91
+          ],
+          "slot_index": 0,
+          "shape": 3
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "ConditioningSetTimestepRange"
+      },
+      "widgets_values": [
+        0.2,
+        1
+      ]
+    },
+    {
+      "id": 70,
+      "type": "ConditioningSetTimestepRange",
+      "pos": {
+        "0": 126,
+        "1": 252
+      },
+      "size": {
+        "0": 317.4000244140625,
+        "1": 82
+      },
+      "flags": {},
+      "order": 7,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "conditioning",
+          "type": "CONDITIONING",
+          "link": 93,
+          "slot_index": 0
+        }
+      ],
+      "outputs": [
+        {
+          "name": "CONDITIONING",
+          "type": "CONDITIONING",
+          "links": [
+            92
+          ],
+          "slot_index": 0,
+          "shape": 3
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "ConditioningSetTimestepRange"
+      },
+      "widgets_values": [
+        0,
+        0.2
+      ]
+    },
+    {
+      "id": 4,
+      "type": "CheckpointLoaderSimple",
+      "pos": {
+        "0": -2016,
+        "1": -504
+      },
+      "size": {
+        "0": 632.6060180664062,
+        "1": 98
+      },
+      "flags": {},
+      "order": 0,
+      "mode": 0,
+      "inputs": [],
+      "outputs": [
+        {
+          "name": "MODEL",
+          "type": "MODEL",
+          "links": [
+            445
+          ],
+          "slot_index": 0,
+          "shape": 3
+        },
+        {
+          "name": "CLIP",
+          "type": "CLIP",
+          "links": null,
+          "shape": 3
+        },
+        {
+          "name": "VAE",
+          "type": "VAE",
+          "links": [
+            605
+          ],
+          "slot_index": 2,
+          "shape": 3
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "CheckpointLoaderSimple"
+      },
+      "widgets_values": [
+        "sd3.5_medium.safetensors"
+      ]
+    },
+    {
+      "id": 11,
+      "type": "TripleCLIPLoader",
+      "pos": {
+        "0": -2016,
+        "1": -252
+      },
+      "size": {
+        "0": 315,
+        "1": 106
+      },
+      "flags": {},
+      "order": 1,
+      "mode": 0,
+      "inputs": [],
+      "outputs": [
+        {
+          "name": "CLIP",
+          "type": "CLIP",
+          "links": [
+            5,
+            94
+          ],
+          "slot_index": 0,
+          "shape": 3
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "TripleCLIPLoader"
+      },
+      "widgets_values": [
+        "sdv3/clip_g.safetensors",
+        "sdv3/clip_l.safetensors",
+        "sdv3/t5xxl_fp16.safetensors"
+      ]
+    },
+    {
+      "id": 105,
+      "type": "Note",
+      "pos": {
+        "0": -1260,
+        "1": -252
+      },
+      "size": {
+        "0": 210,
+        "1": 110.18948364257812
+      },
+      "flags": {},
+      "order": 2,
+      "mode": 0,
+      "inputs": [],
+      "outputs": [],
+      "properties": {
+        "text": ""
+      },
+      "widgets_values": [
+        "Make sure the resolution is multiple of 64 pixels and adds up to around 1 megapixel. "
+      ],
+      "color": "#432",
+      "bgcolor": "#653"
+    },
+    {
+      "id": 135,
+      "type": "EmptySD3LatentImage",
+      "pos": {
+        "0": -1008,
+        "1": -252
+      },
+      "size": {
+        "0": 315,
+        "1": 106
+      },
+      "flags": {},
+      "order": 3,
+      "mode": 0,
+      "inputs": [],
+      "outputs": [
+        {
+          "name": "LATENT",
+          "type": "LATENT",
+          "links": [
+            598
+          ],
+          "slot_index": 0,
+          "shape": 3
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "EmptySD3LatentImage"
+      },
+      "widgets_values": [
+        1280,
+        768,
+        1
+      ]
+    },
+    {
+      "id": 294,
+      "type": "KSampler",
+      "pos": {
+        "0": 882,
+        "1": -504
+      },
+      "size": {
+        "0": 378,
+        "1": 504
+      },
+      "flags": {},
+      "order": 11,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "model",
+          "type": "MODEL",
+          "link": 568
+        },
+        {
+          "name": "positive",
+          "type": "CONDITIONING",
+          "link": 569
+        },
+        {
+          "name": "negative",
+          "type": "CONDITIONING",
+          "link": 604
+        },
+        {
+          "name": "latent_image",
+          "type": "LATENT",
+          "link": 598
+        }
+      ],
+      "outputs": [
+        {
+          "name": "LATENT",
+          "type": "LATENT",
+          "links": [
+            572
+          ],
+          "slot_index": 0,
+          "shape": 3
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "KSampler"
+      },
+      "widgets_values": [
+        193277626003815,
+        "randomize",
+        40,
+        5.5,
+        "dpmpp_2m",
+        "sgm_uniform",
+        1
+      ]
+    },
+    {
+      "id": 13,
+      "type": "ModelSamplingSD3",
+      "pos": {
+        "0": -192,
+        "1": -507
+      },
+      "size": {
+        "0": 315,
+        "1": 58
+      },
+      "flags": {
+        "collapsed": false
+      },
+      "order": 4,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "model",
+          "type": "MODEL",
+          "link": 445
+        }
+      ],
+      "outputs": [
+        {
+          "name": "MODEL",
+          "type": "MODEL",
+          "links": [
+            568
+          ],
+          "slot_index": 0,
+          "shape": 3
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "ModelSamplingSD3"
+      },
+      "widgets_values": [
+        3
+      ]
+    }
+  ],
+  "links": [
+    [
+      5,
+      11,
+      0,
+      6,
+      0,
+      "CLIP"
+    ],
+    [
+      90,
+      67,
+      0,
+      68,
+      0,
+      "CONDITIONING"
+    ],
+    [
+      91,
+      68,
+      0,
+      69,
+      0,
+      "CONDITIONING"
+    ],
+    [
+      92,
+      70,
+      0,
+      69,
+      1,
+      "CONDITIONING"
+    ],
+    [
+      93,
+      71,
+      0,
+      70,
+      0,
+      "CONDITIONING"
+    ],
+    [
+      94,
+      11,
+      0,
+      71,
+      0,
+      "CLIP"
+    ],
+    [
+      274,
+      8,
+      0,
+      50,
+      0,
+      "IMAGE"
+    ],
+    [
+      445,
+      4,
+      0,
+      13,
+      0,
+      "MODEL"
+    ],
+    [
+      568,
+      13,
+      0,
+      294,
+      0,
+      "MODEL"
+    ],
+    [
+      569,
+      6,
+      0,
+      294,
+      1,
+      "CONDITIONING"
+    ],
+    [
+      572,
+      294,
+      0,
+      8,
+      0,
+      "LATENT"
+    ],
+    [
+      597,
+      71,
+      0,
+      67,
+      0,
+      "CONDITIONING"
+    ],
+    [
+      598,
+      135,
+      0,
+      294,
+      3,
+      "LATENT"
+    ],
+    [
+      604,
+      69,
+      0,
+      294,
+      2,
+      "CONDITIONING"
+    ],
+    [
+      605,
+      4,
+      2,
+      8,
+      1,
+      "VAE"
+    ]
+  ],
+  "groups": [],
+  "config": {},
+  "extra": {
+    "ds": {
+      "scale": 0.6727499949325626,
+      "offset": [
+        2163.0604070128397,
+        1105.036283731024
+      ]
+    }
+  },
+  "version": 0.4
+}

sd3_pipeline/model_index.json

@@ -0,0 +1,40 @@
+{
+  "_class_name": "StableDiffusion3Pipeline",
+  "_diffusers_version": "0.30.3.dev0",
+  "scheduler": [
+    "diffusers",
+    "FlowMatchEulerDiscreteScheduler"
+  ],
+  "text_encoder": [
+    "transformers",
+    "CLIPTextModelWithProjection"
+  ],
+  "text_encoder_2": [
+    "transformers",
+    "CLIPTextModelWithProjection"
+  ],
+  "text_encoder_3": [
+    "transformers",
+    "T5EncoderModel"
+  ],
+  "tokenizer": [
+    "transformers",
+    "CLIPTokenizer"
+  ],
+  "tokenizer_2": [
+    "transformers",
+    "CLIPTokenizer"
+  ],
+  "tokenizer_3": [
+    "transformers",
+    "T5TokenizerFast"
+  ],
+  "transformer": [
+    "diffusers",
+    "SD3Transformer2DModel"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKL"
+  ]
+}

sd3_pipeline/scheduler/scheduler_config.json

@@ -0,0 +1,6 @@
+{
+  "_class_name": "FlowMatchEulerDiscreteScheduler",
+  "_diffusers_version": "0.29.0.dev0",
+  "num_train_timesteps": 1000,
+  "shift": 3.0
+}

sd3_pipeline/sd3.5_medium.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11fe06e22364b823dfeedc275912336b932b32a293a0b2f35ffac071990cc4de
+size 5107104286

sd3_pipeline/text_encoder/config.json

@@ -0,0 +1,24 @@
+{
+  "architectures": [
+    "CLIPTextModelWithProjection"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "dropout": 0.0,
+  "eos_token_id": 2,
+  "hidden_act": "quick_gelu",
+  "hidden_size": 768,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 77,
+  "model_type": "clip_text_model",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "projection_dim": 768,
+  "torch_dtype": "float16",
+  "transformers_version": "4.41.2",
+  "vocab_size": 49408
+}

sd3_pipeline/text_encoder/model.fp16.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71e183d11db0c6b6282a4d9e0abb74125edc8692393e89ed8ee5571005f35cb1
+size 247323896

sd3_pipeline/text_encoder/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71e183d11db0c6b6282a4d9e0abb74125edc8692393e89ed8ee5571005f35cb1
+size 247323896

sd3_pipeline/text_encoder_2/config.json

@@ -0,0 +1,24 @@
+{
+  "architectures": [
+    "CLIPTextModelWithProjection"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "dropout": 0.0,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_size": 1280,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 5120,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 77,
+  "model_type": "clip_text_model",
+  "num_attention_heads": 20,
+  "num_hidden_layers": 32,
+  "pad_token_id": 1,
+  "projection_dim": 1280,
+  "torch_dtype": "float16",
+  "transformers_version": "4.41.2",
+  "vocab_size": 49408
+}

sd3_pipeline/text_encoder_2/model.fp16.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec310df2af79c318e24d20511b601a591ca8cd4f1fce1d8dff822a356bcdb1f4
+size 1389382176

sd3_pipeline/text_encoder_2/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec310df2af79c318e24d20511b601a591ca8cd4f1fce1d8dff822a356bcdb1f4
+size 1389382176

sd3_pipeline/text_encoder_3/config.json

@@ -0,0 +1,31 @@
+{
+  "architectures": [
+    "T5EncoderModel"
+  ],
+  "classifier_dropout": 0.0,
+  "d_ff": 10240,
+  "d_kv": 64,
+  "d_model": 4096,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "gelu_new",
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "gated-gelu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": true,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "num_decoder_layers": 24,
+  "num_heads": 64,
+  "num_layers": 24,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.41.2",
+  "use_cache": true,
+  "vocab_size": 32128
+}

sd3_pipeline/text_encoder_3/model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f2751ceeb2a96edd693e539dc5d6bba0b8d3814f49a9b3798403a0cec4b2e3d
+size 4994582104

sd3_pipeline/text_encoder_3/model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f63154532130422309532ff56f11945fbea8266c958e3133e8e5aef85c6293c7
+size 4530066248

sd3_pipeline/text_encoder_3/model.fp16-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f2751ceeb2a96edd693e539dc5d6bba0b8d3814f49a9b3798403a0cec4b2e3d
+size 4994582104

sd3_pipeline/text_encoder_3/model.fp16-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f63154532130422309532ff56f11945fbea8266c958e3133e8e5aef85c6293c7
+size 4530066248

sd3_pipeline/text_encoder_3/model.safetensors.index.fp16.json

@@ -0,0 +1,226 @@
+{
+  "metadata": {
+    "total_size": 9524621312
+  },
+  "weight_map": {
+    "encoder.block.0.layer.0.SelfAttention.k.weight": "model.fp16-00001-of-00002.safetensors",
+    "encoder.block.0.layer.0.SelfAttention.o.weight": "model.fp16-00001-of-00002.safetensors",
+    "encoder.block.0.layer.0.SelfAttention.q.weight": "model.fp16-00001-of-00002.safetensors",
+    "encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "model.fp16-00001-of-00002.safetensors",
+    "encoder.block.0.layer.0.SelfAttention.v.weight": "model.fp16-00001-of-00002.safetensors",
+    "encoder.block.0.layer.0.layer_norm.weight": "model.fp16-00001-of-00002.safetensors",
+    "encoder.block.0.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00001-of-00002.safetensors",
+    "encoder.block.0.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00001-of-00002.safetensors",
+    "encoder.block.0.layer.1.DenseReluDense.wo.weight": "model.fp16-00001-of-00002.safetensors",
+    "encoder.block.0.layer.1.layer_norm.weight": "model.fp16-00001-of-00002.safetensors",
+    "encoder.block.1.layer.0.SelfAttention.k.weight": "model.fp16-00001-of-00002.safetensors",
+    "encoder.block.1.layer.0.SelfAttention.o.weight": "model.fp16-00001-of-00002.safetensors",
+    "encoder.block.1.layer.0.SelfAttention.q.weight": "model.fp16-00001-of-00002.safetensors",
+    "encoder.block.1.layer.0.SelfAttention.v.weight": "model.fp16-00001-of-00002.safetensors",
+    "encoder.block.1.layer.0.layer_norm.weight": "model.fp16-00001-of-00002.safetensors",
+    "encoder.block.1.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00001-of-00002.safetensors",
+    "encoder.block.1.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00001-of-00002.safetensors",
+    "encoder.block.1.layer.1.DenseReluDense.wo.weight": "model.fp16-00001-of-00002.safetensors",
+    "encoder.block.1.layer.1.layer_norm.weight": "model.fp16-00001-of-00002.safetensors",
+    "encoder.block.10.layer.0.SelfAttention.k.weight": "model.fp16-00001-of-00002.safetensors",
+    "encoder.block.10.layer.0.SelfAttention.o.weight": "model.fp16-00001-of-00002.safetensors",
+    "encoder.block.10.layer.0.SelfAttention.q.weight": "model.fp16-00001-of-00002.safetensors",
+    "encoder.block.10.layer.0.SelfAttention.v.weight": "model.fp16-00001-of-00002.safetensors",
+    "encoder.block.10.layer.0.layer_norm.weight": "model.fp16-00001-of-00002.safetensors",
+    "encoder.block.10.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00001-of-00002.safetensors",
+    "encoder.block.10.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00001-of-00002.safetensors",
+    "encoder.block.10.layer.1.DenseReluDense.wo.weight": "model.fp16-00001-of-00002.safetensors",
+    "encoder.block.10.layer.1.layer_norm.weight": "model.fp16-00001-of-00002.safetensors",
+    "encoder.block.11.layer.0.SelfAttention.k.weight": "model.fp16-00001-of-00002.safetensors",
+    "encoder.block.11.layer.0.SelfAttention.o.weight": "model.fp16-00001-of-00002.safetensors",
+    "encoder.block.11.layer.0.SelfAttention.q.weight": "model.fp16-00001-of-00002.safetensors",
+    "encoder.block.11.layer.0.SelfAttention.v.weight": "model.fp16-00001-of-00002.safetensors",
+    "encoder.block.11.layer.0.layer_norm.weight": "model.fp16-00001-of-00002.safetensors",
+    "encoder.block.11.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00001-of-00002.safetensors",
+    "encoder.block.11.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00001-of-00002.safetensors",
+    "encoder.block.11.layer.1.DenseReluDense.wo.weight": "model.fp16-00001-of-00002.safetensors",
+    "encoder.block.11.layer.1.layer_norm.weight": "model.fp16-00001-of-00002.safetensors",
+    "encoder.block.12.layer.0.SelfAttention.k.weight": "model.fp16-00001-of-00002.safetensors",
+    "encoder.block.12.layer.0.SelfAttention.o.weight": "model.fp16-00002-of-00002.safetensors",
+    "encoder.block.12.layer.0.SelfAttention.q.weight": "model.fp16-00001-of-00002.safetensors",
+    "encoder.block.12.layer.0.SelfAttention.v.weight": "model.fp16-00001-of-00002.safetensors",
+    "encoder.block.12.layer.0.layer_norm.weight": "model.fp16-00002-of-00002.safetensors",
+    "encoder.block.12.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00002-of-00002.safetensors",
+    "encoder.block.12.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00002-of-00002.safetensors",
+    "encoder.block.12.layer.1.DenseReluDense.wo.weight": "model.fp16-00002-of-00002.safetensors",
+    "encoder.block.12.layer.1.layer_norm.weight": "model.fp16-00002-of-00002.safetensors",
+    "encoder.block.13.layer.0.SelfAttention.k.weight": "model.fp16-00002-of-00002.safetensors",
+    "encoder.block.13.layer.0.SelfAttention.o.weight": "model.fp16-00002-of-00002.safetensors",
+    "encoder.block.13.layer.0.SelfAttention.q.weight": "model.fp16-00002-of-00002.safetensors",
+    "encoder.block.13.layer.0.SelfAttention.v.weight": "model.fp16-00002-of-00002.safetensors",
+    "encoder.block.13.layer.0.layer_norm.weight": "model.fp16-00002-of-00002.safetensors",
+    "encoder.block.13.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00002-of-00002.safetensors",
+    "encoder.block.13.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00002-of-00002.safetensors",
+    "encoder.block.13.layer.1.DenseReluDense.wo.weight": "model.fp16-00002-of-00002.safetensors",
+    "encoder.block.13.layer.1.layer_norm.weight": "model.fp16-00002-of-00002.safetensors",
+    "encoder.block.14.layer.0.SelfAttention.k.weight": "model.fp16-00002-of-00002.safetensors",
+    "encoder.block.14.layer.0.SelfAttention.o.weight": "model.fp16-00002-of-00002.safetensors",
+    "encoder.block.14.layer.0.SelfAttention.q.weight": "model.fp16-00002-of-00002.safetensors",
+    "encoder.block.14.layer.0.SelfAttention.v.weight": "model.fp16-00002-of-00002.safetensors",
+    "encoder.block.14.layer.0.layer_norm.weight": "model.fp16-00002-of-00002.safetensors",
+    "encoder.block.14.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00002-of-00002.safetensors",
+    "encoder.block.14.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00002-of-00002.safetensors",
+    "encoder.block.14.layer.1.DenseReluDense.wo.weight": "model.fp16-00002-of-00002.safetensors",
+    "encoder.block.14.layer.1.layer_norm.weight": "model.fp16-00002-of-00002.safetensors",
+    "encoder.block.15.layer.0.SelfAttention.k.weight": "model.fp16-00002-of-00002.safetensors",
+    "encoder.block.15.layer.0.SelfAttention.o.weight": "model.fp16-00002-of-00002.safetensors",
+    "encoder.block.15.layer.0.SelfAttention.q.weight": "model.fp16-00002-of-00002.safetensors",
+    "encoder.block.15.layer.0.SelfAttention.v.weight": "model.fp16-00002-of-00002.safetensors",
+    "encoder.block.15.layer.0.layer_norm.weight": "model.fp16-00002-of-00002.safetensors",
+    "encoder.block.15.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00002-of-00002.safetensors",
+    "encoder.block.15.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00002-of-00002.safetensors",
+    "encoder.block.15.layer.1.DenseReluDense.wo.weight": "model.fp16-00002-of-00002.safetensors",
+    "encoder.block.15.layer.1.layer_norm.weight": "model.fp16-00002-of-00002.safetensors",
+    "encoder.block.16.layer.0.SelfAttention.k.weight": "model.fp16-00002-of-00002.safetensors",
+    "encoder.block.16.layer.0.SelfAttention.o.weight": "model.fp16-00002-of-00002.safetensors",
+    "encoder.block.16.layer.0.SelfAttention.q.weight": "model.fp16-00002-of-00002.safetensors",
+    "encoder.block.16.layer.0.SelfAttention.v.weight": "model.fp16-00002-of-00002.safetensors",
+    "encoder.block.16.layer.0.layer_norm.weight": "model.fp16-00002-of-00002.safetensors",
+    "encoder.block.16.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00002-of-00002.safetensors",
+    "encoder.block.16.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00002-of-00002.safetensors",
+    "encoder.block.16.layer.1.DenseReluDense.wo.weight": "model.fp16-00002-of-00002.safetensors",
+    "encoder.block.16.layer.1.layer_norm.weight": "model.fp16-00002-of-00002.safetensors",
+    "encoder.block.17.layer.0.SelfAttention.k.weight": "model.fp16-00002-of-00002.safetensors",
+    "encoder.block.17.layer.0.SelfAttention.o.weight": "model.fp16-00002-of-00002.safetensors",
+    "encoder.block.17.layer.0.SelfAttention.q.weight": "model.fp16-00002-of-00002.safetensors",
+    "encoder.block.17.layer.0.SelfAttention.v.weight": "model.fp16-00002-of-00002.safetensors",
+    "encoder.block.17.layer.0.layer_norm.weight": "model.fp16-00002-of-00002.safetensors",
+    "encoder.block.17.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00002-of-00002.safetensors",
+    "encoder.block.17.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00002-of-00002.safetensors",
+    "encoder.block.17.layer.1.DenseReluDense.wo.weight": "model.fp16-00002-of-00002.safetensors",
+    "encoder.block.17.layer.1.layer_norm.weight": "model.fp16-00002-of-00002.safetensors",
+    "encoder.block.18.layer.0.SelfAttention.k.weight": "model.fp16-00002-of-00002.safetensors",
+    "encoder.block.18.layer.0.SelfAttention.o.weight": "model.fp16-00002-of-00002.safetensors",
+    "encoder.block.18.layer.0.SelfAttention.q.weight": "model.fp16-00002-of-00002.safetensors",
+    "encoder.block.18.layer.0.SelfAttention.v.weight": "model.fp16-00002-of-00002.safetensors",
+    "encoder.block.18.layer.0.layer_norm.weight": "model.fp16-00002-of-00002.safetensors",
+    "encoder.block.18.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00002-of-00002.safetensors",
+    "encoder.block.18.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00002-of-00002.safetensors",
+    "encoder.block.18.layer.1.DenseReluDense.wo.weight": "model.fp16-00002-of-00002.safetensors",
+    "encoder.block.18.layer.1.layer_norm.weight": "model.fp16-00002-of-00002.safetensors",
+    "encoder.block.19.layer.0.SelfAttention.k.weight": "model.fp16-00002-of-00002.safetensors",
+    "encoder.block.19.layer.0.SelfAttention.o.weight": "model.fp16-00002-of-00002.safetensors",
+    "encoder.block.19.layer.0.SelfAttention.q.weight": "model.fp16-00002-of-00002.safetensors",
+    "encoder.block.19.layer.0.SelfAttention.v.weight": "model.fp16-00002-of-00002.safetensors",
+    "encoder.block.19.layer.0.layer_norm.weight": "model.fp16-00002-of-00002.safetensors",
+    "encoder.block.19.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00002-of-00002.safetensors",
+    "encoder.block.19.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00002-of-00002.safetensors",
+    "encoder.block.19.layer.1.DenseReluDense.wo.weight": "model.fp16-00002-of-00002.safetensors",
+    "encoder.block.19.layer.1.layer_norm.weight": "model.fp16-00002-of-00002.safetensors",
+    "encoder.block.2.layer.0.SelfAttention.k.weight": "model.fp16-00001-of-00002.safetensors",
+    "encoder.block.2.layer.0.SelfAttention.o.weight": "model.fp16-00001-of-00002.safetensors",
+    "encoder.block.2.layer.0.SelfAttention.q.weight": "model.fp16-00001-of-00002.safetensors",
+    "encoder.block.2.layer.0.SelfAttention.v.weight": "model.fp16-00001-of-00002.safetensors",
+    "encoder.block.2.layer.0.layer_norm.weight": "model.fp16-00001-of-00002.safetensors",
+    "encoder.block.2.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00001-of-00002.safetensors",
+    "encoder.block.2.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00001-of-00002.safetensors",
+    "encoder.block.2.layer.1.DenseReluDense.wo.weight": "model.fp16-00001-of-00002.safetensors",
+    "encoder.block.2.layer.1.layer_norm.weight": "model.fp16-00001-of-00002.safetensors",
+    "encoder.block.20.layer.0.SelfAttention.k.weight": "model.fp16-00002-of-00002.safetensors",
+    "encoder.block.20.layer.0.SelfAttention.o.weight": "model.fp16-00002-of-00002.safetensors",
+    "encoder.block.20.layer.0.SelfAttention.q.weight": "model.fp16-00002-of-00002.safetensors",
+    "encoder.block.20.layer.0.SelfAttention.v.weight": "model.fp16-00002-of-00002.safetensors",
+    "encoder.block.20.layer.0.layer_norm.weight": "model.fp16-00002-of-00002.safetensors",
+    "encoder.block.20.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00002-of-00002.safetensors",
+    "encoder.block.20.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00002-of-00002.safetensors",
+    "encoder.block.20.layer.1.DenseReluDense.wo.weight": "model.fp16-00002-of-00002.safetensors",
+    "encoder.block.20.layer.1.layer_norm.weight": "model.fp16-00002-of-00002.safetensors",
+    "encoder.block.21.layer.0.SelfAttention.k.weight": "model.fp16-00002-of-00002.safetensors",
+    "encoder.block.21.layer.0.SelfAttention.o.weight": "model.fp16-00002-of-00002.safetensors",
+    "encoder.block.21.layer.0.SelfAttention.q.weight": "model.fp16-00002-of-00002.safetensors",
+    "encoder.block.21.layer.0.SelfAttention.v.weight": "model.fp16-00002-of-00002.safetensors",
+    "encoder.block.21.layer.0.layer_norm.weight": "model.fp16-00002-of-00002.safetensors",
+    "encoder.block.21.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00002-of-00002.safetensors",
+    "encoder.block.21.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00002-of-00002.safetensors",
+    "encoder.block.21.layer.1.DenseReluDense.wo.weight": "model.fp16-00002-of-00002.safetensors",
+    "encoder.block.21.layer.1.layer_norm.weight": "model.fp16-00002-of-00002.safetensors",
+    "encoder.block.22.layer.0.SelfAttention.k.weight": "model.fp16-00002-of-00002.safetensors",
+    "encoder.block.22.layer.0.SelfAttention.o.weight": "model.fp16-00002-of-00002.safetensors",
+    "encoder.block.22.layer.0.SelfAttention.q.weight": "model.fp16-00002-of-00002.safetensors",
+    "encoder.block.22.layer.0.SelfAttention.v.weight": "model.fp16-00002-of-00002.safetensors",
+    "encoder.block.22.layer.0.layer_norm.weight": "model.fp16-00002-of-00002.safetensors",
+    "encoder.block.22.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00002-of-00002.safetensors",
+    "encoder.block.22.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00002-of-00002.safetensors",
+    "encoder.block.22.layer.1.DenseReluDense.wo.weight": "model.fp16-00002-of-00002.safetensors",
+    "encoder.block.22.layer.1.layer_norm.weight": "model.fp16-00002-of-00002.safetensors",
+    "encoder.block.23.layer.0.SelfAttention.k.weight": "model.fp16-00002-of-00002.safetensors",
+    "encoder.block.23.layer.0.SelfAttention.o.weight": "model.fp16-00002-of-00002.safetensors",
+    "encoder.block.23.layer.0.SelfAttention.q.weight": "model.fp16-00002-of-00002.safetensors",
+    "encoder.block.23.layer.0.SelfAttention.v.weight": "model.fp16-00002-of-00002.safetensors",
+    "encoder.block.23.layer.0.layer_norm.weight": "model.fp16-00002-of-00002.safetensors",
+    "encoder.block.23.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00002-of-00002.safetensors",
+    "encoder.block.23.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00002-of-00002.safetensors",
+    "encoder.block.23.layer.1.DenseReluDense.wo.weight": "model.fp16-00002-of-00002.safetensors",
+    "encoder.block.23.layer.1.layer_norm.weight": "model.fp16-00002-of-00002.safetensors",
+    "encoder.block.3.layer.0.SelfAttention.k.weight": "model.fp16-00001-of-00002.safetensors",
+    "encoder.block.3.layer.0.SelfAttention.o.weight": "model.fp16-00001-of-00002.safetensors",
+    "encoder.block.3.layer.0.SelfAttention.q.weight": "model.fp16-00001-of-00002.safetensors",
+    "encoder.block.3.layer.0.SelfAttention.v.weight": "model.fp16-00001-of-00002.safetensors",
+    "encoder.block.3.layer.0.layer_norm.weight": "model.fp16-00001-of-00002.safetensors",
+    "encoder.block.3.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00001-of-00002.safetensors",
+    "encoder.block.3.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00001-of-00002.safetensors",
+    "encoder.block.3.layer.1.DenseReluDense.wo.weight": "model.fp16-00001-of-00002.safetensors",
+    "encoder.block.3.layer.1.layer_norm.weight": "model.fp16-00001-of-00002.safetensors",
+    "encoder.block.4.layer.0.SelfAttention.k.weight": "model.fp16-00001-of-00002.safetensors",
+    "encoder.block.4.layer.0.SelfAttention.o.weight": "model.fp16-00001-of-00002.safetensors",
+    "encoder.block.4.layer.0.SelfAttention.q.weight": "model.fp16-00001-of-00002.safetensors",
+    "encoder.block.4.layer.0.SelfAttention.v.weight": "model.fp16-00001-of-00002.safetensors",
+    "encoder.block.4.layer.0.layer_norm.weight": "model.fp16-00001-of-00002.safetensors",
+    "encoder.block.4.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00001-of-00002.safetensors",
+    "encoder.block.4.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00001-of-00002.safetensors",
+    "encoder.block.4.layer.1.DenseReluDense.wo.weight": "model.fp16-00001-of-00002.safetensors",
+    "encoder.block.4.layer.1.layer_norm.weight": "model.fp16-00001-of-00002.safetensors",
+    "encoder.block.5.layer.0.SelfAttention.k.weight": "model.fp16-00001-of-00002.safetensors",
+    "encoder.block.5.layer.0.SelfAttention.o.weight": "model.fp16-00001-of-00002.safetensors",
+    "encoder.block.5.layer.0.SelfAttention.q.weight": "model.fp16-00001-of-00002.safetensors",
+    "encoder.block.5.layer.0.SelfAttention.v.weight": "model.fp16-00001-of-00002.safetensors",
+    "encoder.block.5.layer.0.layer_norm.weight": "model.fp16-00001-of-00002.safetensors",
+    "encoder.block.5.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00001-of-00002.safetensors",
+    "encoder.block.5.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00001-of-00002.safetensors",
+    "encoder.block.5.layer.1.DenseReluDense.wo.weight": "model.fp16-00001-of-00002.safetensors",
+    "encoder.block.5.layer.1.layer_norm.weight": "model.fp16-00001-of-00002.safetensors",
+    "encoder.block.6.layer.0.SelfAttention.k.weight": "model.fp16-00001-of-00002.safetensors",
+    "encoder.block.6.layer.0.SelfAttention.o.weight": "model.fp16-00001-of-00002.safetensors",
+    "encoder.block.6.layer.0.SelfAttention.q.weight": "model.fp16-00001-of-00002.safetensors",
+    "encoder.block.6.layer.0.SelfAttention.v.weight": "model.fp16-00001-of-00002.safetensors",
+    "encoder.block.6.layer.0.layer_norm.weight": "model.fp16-00001-of-00002.safetensors",
+    "encoder.block.6.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00001-of-00002.safetensors",
+    "encoder.block.6.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00001-of-00002.safetensors",
+    "encoder.block.6.layer.1.DenseReluDense.wo.weight": "model.fp16-00001-of-00002.safetensors",
+    "encoder.block.6.layer.1.layer_norm.weight": "model.fp16-00001-of-00002.safetensors",
+    "encoder.block.7.layer.0.SelfAttention.k.weight": "model.fp16-00001-of-00002.safetensors",
+    "encoder.block.7.layer.0.SelfAttention.o.weight": "model.fp16-00001-of-00002.safetensors",
+    "encoder.block.7.layer.0.SelfAttention.q.weight": "model.fp16-00001-of-00002.safetensors",
+    "encoder.block.7.layer.0.SelfAttention.v.weight": "model.fp16-00001-of-00002.safetensors",
+    "encoder.block.7.layer.0.layer_norm.weight": "model.fp16-00001-of-00002.safetensors",
+    "encoder.block.7.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00001-of-00002.safetensors",
+    "encoder.block.7.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00001-of-00002.safetensors",
+    "encoder.block.7.layer.1.DenseReluDense.wo.weight": "model.fp16-00001-of-00002.safetensors",
+    "encoder.block.7.layer.1.layer_norm.weight": "model.fp16-00001-of-00002.safetensors",
+    "encoder.block.8.layer.0.SelfAttention.k.weight": "model.fp16-00001-of-00002.safetensors",
+    "encoder.block.8.layer.0.SelfAttention.o.weight": "model.fp16-00001-of-00002.safetensors",
+    "encoder.block.8.layer.0.SelfAttention.q.weight": "model.fp16-00001-of-00002.safetensors",
+    "encoder.block.8.layer.0.SelfAttention.v.weight": "model.fp16-00001-of-00002.safetensors",
+    "encoder.block.8.layer.0.layer_norm.weight": "model.fp16-00001-of-00002.safetensors",
+    "encoder.block.8.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00001-of-00002.safetensors",
+    "encoder.block.8.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00001-of-00002.safetensors",
+    "encoder.block.8.layer.1.DenseReluDense.wo.weight": "model.fp16-00001-of-00002.safetensors",
+    "encoder.block.8.layer.1.layer_norm.weight": "model.fp16-00001-of-00002.safetensors",
+    "encoder.block.9.layer.0.SelfAttention.k.weight": "model.fp16-00001-of-00002.safetensors",
+    "encoder.block.9.layer.0.SelfAttention.o.weight": "model.fp16-00001-of-00002.safetensors",
+    "encoder.block.9.layer.0.SelfAttention.q.weight": "model.fp16-00001-of-00002.safetensors",
+    "encoder.block.9.layer.0.SelfAttention.v.weight": "model.fp16-00001-of-00002.safetensors",
+    "encoder.block.9.layer.0.layer_norm.weight": "model.fp16-00001-of-00002.safetensors",
+    "encoder.block.9.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00001-of-00002.safetensors",
+    "encoder.block.9.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00001-of-00002.safetensors",
+    "encoder.block.9.layer.1.DenseReluDense.wo.weight": "model.fp16-00001-of-00002.safetensors",
+    "encoder.block.9.layer.1.layer_norm.weight": "model.fp16-00001-of-00002.safetensors",
+    "encoder.final_layer_norm.weight": "model.fp16-00002-of-00002.safetensors",
+    "shared.weight": "model.fp16-00001-of-00002.safetensors"
+  }
+}

sd3_pipeline/text_encoder_3/model.safetensors.index.json

@@ -0,0 +1,226 @@
+{
+  "metadata": {
+    "total_size": 9524621312
+  },
+  "weight_map": {
+    "encoder.block.0.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.0.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.0.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.0.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.0.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.0.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.0.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.0.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.0.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.1.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.1.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.1.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.1.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.1.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.1.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.1.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.1.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.1.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.10.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.10.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.10.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.10.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.10.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.10.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.10.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.10.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.10.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.11.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.11.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.11.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.11.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.11.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.11.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.11.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.11.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.11.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.12.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.12.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.12.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.12.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.12.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.12.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.12.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.12.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.12.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.13.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.13.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.13.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.13.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.13.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.13.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.13.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.13.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.13.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.14.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.14.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.14.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.14.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.14.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.14.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.14.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.14.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.14.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.15.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.15.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.15.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.15.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.15.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.15.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.15.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.15.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.15.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.16.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.16.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.16.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.16.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.16.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.16.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.16.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.16.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.16.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.17.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.17.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.17.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.17.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.17.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.17.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.17.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.17.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.17.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.18.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.18.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.18.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.18.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.18.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.18.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.18.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.18.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.18.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.19.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.19.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.19.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.19.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.19.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.19.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.19.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.19.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.19.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.2.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.2.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.2.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.2.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.2.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.2.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.2.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.2.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.2.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.20.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.20.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.20.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.20.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.20.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.20.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.20.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.20.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.20.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.21.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.21.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.21.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.21.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.21.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.21.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.21.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.21.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.21.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.22.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.22.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.22.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.22.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.22.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.22.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.22.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.22.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.22.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.23.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.23.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.23.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.23.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.23.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.23.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.23.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.23.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.23.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.3.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.3.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.3.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.3.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.3.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.3.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.3.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.3.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.3.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.4.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.4.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.4.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.4.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.4.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.4.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.4.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.4.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.4.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.5.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.5.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.5.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.5.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.5.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.5.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.5.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.5.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.5.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.6.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.6.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.6.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.6.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.6.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.6.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.6.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.6.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.6.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.7.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.7.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.7.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.7.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.7.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.7.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.7.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.7.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.7.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.8.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.8.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.8.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.8.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.8.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.8.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.8.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.8.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.8.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.9.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.9.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.9.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.9.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.9.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.9.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.9.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.9.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.9.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.final_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "shared.weight": "model-00001-of-00002.safetensors"
+  }
+}

sd3_pipeline/text_encoders/README.md

@@ -0,0 +1,11 @@
+CLIP-ViT/L: 
+* [https://huggingface.co/openai/clip-vit-large-patch14](https://huggingface.co/openai/clip-vit-large-patch14/blob/main/README.md) 
+* [MIT License](https://github.com/openai/CLIP/blob/main/LICENSE)
+
+OpenCLIP-ViT/G: 
+* [https://huggingface.co/laion/CLIP-ViT-bigG-14-laion2B-39B-b160k](https://huggingface.co/laion/CLIP-ViT-bigG-14-laion2B-39B-b160k/blob/main/README.md)
+* [MIT License](https://choosealicense.com/licenses/mit)
+
+T5 Version 1.1:
+* [https://huggingface.co/google/t5-v1_1-xxl](https://huggingface.co/google/t5-v1_1-xxl/blob/main/README.md)
+* [Apache License 2.0](https://choosealicense.com/licenses/apache-2.0)

sd3_pipeline/text_encoders/clip_g.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec310df2af79c318e24d20511b601a591ca8cd4f1fce1d8dff822a356bcdb1f4
+size 1389382176

sd3_pipeline/text_encoders/clip_l.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:660c6f5b1abae9dc498ac2d21e1347d2abdb0cf6c0c0c8576cd796491d9a6cdd
+size 246144152

sd3_pipeline/text_encoders/t5xxl_fp16.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e480b09fae049a72d2a8c5fbccb8d3e92febeb233bbe9dfe7256958a9167635
+size 9787841024

sd3_pipeline/text_encoders/t5xxl_fp8_e4m3fn.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d330da4816157540d6bb7838bf63a0f02f573fc48ca4d8de34bb0cbfd514f09
+size 4893934904

sd3_pipeline/tokenizer/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

sd3_pipeline/tokenizer/tokenizer_config.json

@@ -0,0 +1,30 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "49406": {
+      "content": "<|startoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49407": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|startoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": true,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 77,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "CLIPTokenizer",
+  "unk_token": "<|endoftext|>"
+}

sd3_pipeline/tokenizer_2/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "!",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

sd3_pipeline/tokenizer_2/tokenizer_config.json

@@ -0,0 +1,38 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "!",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49406": {
+      "content": "<|startoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49407": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|startoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": true,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 77,
+  "pad_token": "!",
+  "tokenizer_class": "CLIPTokenizer",
+  "unk_token": "<|endoftext|>"
+}