Add tiny random Qwen-Image-2.1 (t2i + i2i, non-collapsing outputs)

.gitattributes

@@ -33,3 +33,4 @@ 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
+processor/tokenizer.json filter=lfs diff=lfs merge=lfs -text

model_index.json

@@ -0,0 +1,24 @@
+{
+  "_class_name": "QwenImage21Pipeline",
+  "_diffusers_version": "0.41.0.dev0",
+  "processor": [
+    "transformers",
+    "Qwen3VLProcessor"
+  ],
+  "scheduler": [
+    "diffusers",
+    "FlowMatchEulerDiscreteScheduler"
+  ],
+  "text_encoder": [
+    "transformers",
+    "Qwen3VLForConditionalGeneration"
+  ],
+  "transformer": [
+    "diffusers",
+    "QwenImage21Transformer2DModel"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKLQwenImage21"
+  ]
+}

processor/chat_template.jinja

@@ -0,0 +1,120 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {%- if messages[0].content is string %}
+            {{- messages[0].content }}
+        {%- else %}
+            {%- for content in messages[0].content %}
+                {%- if 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' }}
+        {%- if messages[0].content is string %}
+            {{- messages[0].content }}
+        {%- else %}
+            {%- for content in messages[0].content %}
+                {%- if 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- for message in messages %}
+    {%- if message.role == "user" %}
+        {{- '<|im_start|>' + message.role + '\n' }}
+        {%- if message.content is string %}
+            {{- message.content }}
+        {%- 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 %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role + '\n' }}
+        {%- if message.content is string %}
+            {{- message.content }}
+        {%- else %}
+            {%- for content_item in message.content %}
+                {%- if 'text' in content_item %}
+                    {{- content_item.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and message.content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {%- if message.content is string %}
+            {{- message.content }}
+        {%- 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 %}
+        {%- endif %}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

processor/processor_config.json

@@ -0,0 +1,64 @@
+{
+  "image_processor": {
+    "data_format": "channels_first",
+    "default_to_square": true,
+    "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
+    ],
+    "merge_size": 2,
+    "patch_size": 16,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "size": {
+      "longest_edge": 16777216,
+      "shortest_edge": 65536
+    },
+    "temporal_patch_size": 2
+  },
+  "processor_class": "Qwen3VLProcessor",
+  "video_processor": {
+    "data_format": "channels_first",
+    "default_to_square": true,
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "do_sample_frames": true,
+    "fps": 2,
+    "image_mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "image_std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "max_frames": 768,
+    "merge_size": 2,
+    "min_frames": 4,
+    "patch_size": 16,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "return_metadata": false,
+    "size": {
+      "longest_edge": 25165824,
+      "shortest_edge": 4096
+    },
+    "temporal_patch_size": 2,
+    "video_processor_type": "Qwen3VLVideoProcessor"
+  }
+}

processor/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
+size 11422650

processor/tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "is_local": true,
+  "local_files_only": true,
+  "model_max_length": 262144,
+  "pad_token": "<|endoftext|>",
+  "processor_class": "Qwen3VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

scheduler/scheduler_config.json

@@ -0,0 +1,18 @@
+{
+  "_class_name": "FlowMatchEulerDiscreteScheduler",
+  "_diffusers_version": "0.41.0.dev0",
+  "base_image_seq_len": 256,
+  "base_shift": 0.5,
+  "invert_sigmas": false,
+  "max_image_seq_len": 8192,
+  "max_shift": 0.9,
+  "num_train_timesteps": 1000,
+  "shift": 1.0,
+  "shift_terminal": 0.02,
+  "stochastic_sampling": false,
+  "time_shift_type": "exponential",
+  "use_beta_sigmas": false,
+  "use_dynamic_shifting": true,
+  "use_exponential_sigmas": false,
+  "use_karras_sigmas": false
+}

text_encoder/config.json

@@ -0,0 +1,63 @@
+{
+  "architectures": [
+    "Qwen3VLForConditionalGeneration"
+  ],
+  "dtype": "float32",
+  "image_token_id": 151655,
+  "model_type": "qwen3_vl",
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bos_token_id": 151643,
+    "eos_token_id": 151645,
+    "head_dim": 8,
+    "hidden_act": "silu",
+    "hidden_size": 16,
+    "initializer_range": 0.02,
+    "intermediate_size": 32,
+    "max_position_embeddings": 262144,
+    "model_type": "qwen3_vl_text",
+    "num_attention_heads": 2,
+    "num_hidden_layers": 2,
+    "num_key_value_heads": 1,
+    "pad_token_id": null,
+    "rms_norm_eps": 1e-06,
+    "rope_parameters": {
+      "mrope_interleaved": true,
+      "mrope_section": [
+        2,
+        1,
+        1
+      ],
+      "rope_theta": 5000000,
+      "rope_type": "default"
+    },
+    "use_cache": true,
+    "vocab_size": 151936
+  },
+  "tie_word_embeddings": true,
+  "transformers_version": "5.10.4",
+  "video_token_id": 151656,
+  "vision_config": {
+    "deepstack_visual_indexes": [
+      0,
+      1,
+      2
+    ],
+    "depth": 3,
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 16,
+    "in_channels": 3,
+    "initializer_range": 0.02,
+    "intermediate_size": 32,
+    "model_type": "qwen3_vl_vision",
+    "num_heads": 2,
+    "num_position_embeddings": 2304,
+    "out_hidden_size": 16,
+    "patch_size": 16,
+    "spatial_merge_size": 2,
+    "temporal_patch_size": 2
+  },
+  "vision_end_token_id": 151653,
+  "vision_start_token_id": 151652
+}

text_encoder/generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "transformers_version": "5.10.4",
+  "use_cache": true
+}

text_encoder/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51e2948a80852a8985b37cd35939207cdb066df20fde5cad392fd0c6aa6c4150
+size 10109760

transformer/config.json

@@ -0,0 +1,19 @@
+{
+  "_class_name": "QwenImage21Transformer2DModel",
+  "_diffusers_version": "0.41.0.dev0",
+  "attention_head_dim": 16,
+  "axes_dims_rope": [
+    4,
+    6,
+    6
+  ],
+  "causal_condition": true,
+  "context_in_dim": 16,
+  "eps": 1e-06,
+  "in_channels": 64,
+  "mlp_ratio": 3,
+  "num_attention_heads": 2,
+  "num_layers": 2,
+  "out_channels": 64,
+  "patch_size": 1
+}

transformer/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c571d7b4489f1c3f78afc53f50f8f28e248d2ba0e63b29650413795739bf133
+size 189416

vae/config.json

@@ -0,0 +1,161 @@
+{
+  "_class_name": "AutoencoderKLQwenImage21",
+  "_diffusers_version": "0.41.0.dev0",
+  "attn_scales": [],
+  "base_dim": 8,
+  "decoder_base_dim": 8,
+  "dim_mult": [
+    1,
+    2,
+    4,
+    8,
+    8
+  ],
+  "dropout": 0.0,
+  "in_channels": 4,
+  "is_residual": true,
+  "latents_mean": [
+    0.5126,
+    0.7721,
+    -0.0631,
+    1.3506,
+    -0.7855,
+    -2.1025,
+    -0.3458,
+    1.3722,
+    1.8873,
+    -1.7177,
+    -0.651,
+    0.2732,
+    0.7562,
+    -0.6163,
+    -1.0277,
+    3.8363,
+    2.021,
+    0.0472,
+    0.932,
+    2.0087,
+    2.4954,
+    -0.1391,
+    -1.4249,
+    1.8464,
+    -0.5236,
+    1.2826,
+    3.7046,
+    -1.3035,
+    2.7286,
+    -1.4518,
+    -1.9036,
+    -1.9955,
+    -0.0342,
+    -1.0265,
+    -0.7636,
+    3.0555,
+    0.0746,
+    -3.0751,
+    -0.1076,
+    1.7376,
+    -1.0914,
+    -1.9435,
+    -0.2784,
+    -1.368,
+    0.4809,
+    -0.4433,
+    0.3764,
+    0.5729,
+    -2.0595,
+    1.096,
+    -1.326,
+    -2.0211,
+    -5.0179,
+    0.5275,
+    4.0162,
+    1.8505,
+    0.3026,
+    1.9373,
+    1.4937,
+    0.2632,
+    0.5547,
+    -1.7121,
+    -0.1562,
+    0.0304
+  ],
+  "latents_std": [
+    3.2001,
+    3.2936,
+    3.4321,
+    3.0091,
+    3.1061,
+    4.0379,
+    4.0705,
+    3.791,
+    3.0785,
+    3.65,
+    3.9308,
+    3.0904,
+    2.8778,
+    3.7675,
+    3.732,
+    5.0756,
+    3.2864,
+    4.0397,
+    3.1317,
+    4.0443,
+    2.9249,
+    3.9454,
+    3.0988,
+    4.2489,
+    3.4896,
+    3.8513,
+    3.9323,
+    3.4719,
+    3.7498,
+    4.283,
+    3.5694,
+    4.2467,
+    3.9037,
+    3.2947,
+    5.077,
+    3.5075,
+    3.27,
+    3.4767,
+    2.8063,
+    5.1125,
+    3.5327,
+    4.7833,
+    3.1286,
+    4.1819,
+    3.8527,
+    3.8312,
+    3.5605,
+    4.3875,
+    3.9624,
+    4.0168,
+    3.5643,
+    4.055,
+    5.5614,
+    4.2963,
+    4.408,
+    3.4959,
+    3.8747,
+    3.7608,
+    3.5735,
+    3.149,
+    3.7662,
+    3.6746,
+    3.4563,
+    3.8161
+  ],
+  "num_res_blocks": 1,
+  "out_channels": 4,
+  "patch_size": null,
+  "scale_factor_spatial": 8,
+  "scale_factor_temporal": 8,
+  "temperal_downsample": [
+    false,
+    true,
+    true,
+    true
+  ],
+  "z_dim": 64
+}

vae/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6d9c2a41b8fc23a724ed0871cff7b0f6a7128ff75c48ac5472b42ff4f682c14
+size 4542792