upload textdiffuser2 ckpt

random_states_0.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0827f1abef6217b1c6f988db067c391b0513d5b206649da5fb195e84fcea3a29
+size 21795

scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52c6c7e844087fcad1116ded8427150e776621aeb561c4274a2bb9d0e3c70bc8
+size 557

scheduler.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad234661410f5ffbb6e05544a6e9bbd54ffc03c17eefad50670e2529e02f7d8f
+size 627

text_encoder/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "runwayml/stable-diffusion-v1-5",
+  "architectures": [
+    "CLIPTextModel"
+  ],
+  "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": "float32",
+  "transformers_version": "4.28.0",
+  "vocab_size": 51583
+}

text_encoder/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac2be640c85bdfc4b75c41386539d819128f071e1e6bb3be15c109bd0eab96b3
+size 498991393

unet/config.json

@@ -0,0 +1,64 @@
+{
+    "_class_name": "UNet2DConditionModel",
+    "_diffusers_version": "0.18.0.dev0",
+    "_name_or_path": "default",
+    "act_fn": "silu",
+    "addition_embed_type": null,
+    "addition_embed_type_num_heads": 64,
+    "attention_head_dim": 8,
+    "block_out_channels": [
+      320,
+      640,
+      1280,
+      1280
+    ],
+    "center_input_sample": false,
+    "class_embed_type": null,
+    "class_embeddings_concat": false,
+    "conv_in_kernel": 3,
+    "conv_out_kernel": 3,
+    "cross_attention_dim": 768,
+    "cross_attention_norm": null,
+    "down_block_types": [
+      "CrossAttnDownBlock2D",
+      "CrossAttnDownBlock2D",
+      "CrossAttnDownBlock2D",
+      "DownBlock2D"
+    ],
+    "downsample_padding": 1,
+    "dual_cross_attention": false,
+    "encoder_hid_dim": null,
+    "encoder_hid_dim_type": null,
+    "flip_sin_to_cos": true,
+    "freq_shift": 0,
+    "in_channels": 4,
+    "layers_per_block": 2,
+    "mid_block_only_cross_attention": null,
+    "mid_block_scale_factor": 1,
+    "mid_block_type": "UNetMidBlock2DCrossAttn",
+    "norm_eps": 1e-05,
+    "norm_num_groups": 32,
+    "num_attention_heads": null,
+    "num_class_embeds": null,
+    "only_cross_attention": false,
+    "out_channels": 4,
+    "projection_class_embeddings_input_dim": null,
+    "resnet_out_scale_factor": 1.0,
+    "resnet_skip_time_act": false,
+    "resnet_time_scale_shift": "default",
+    "sample_size": 64,
+    "time_cond_proj_dim": null,
+    "time_embedding_act_fn": null,
+    "time_embedding_dim": null,
+    "time_embedding_type": "positional",
+    "timestep_post_act": null,
+    "up_block_types": [
+      "UpBlock2D",
+      "CrossAttnUpBlock2D",
+      "CrossAttnUpBlock2D",
+      "CrossAttnUpBlock2D"
+    ],
+    "upcast_attention": false,
+    "use_linear_projection": false
+  }
+  

unet/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04cdf880f4aed7572f1ff639f1506e0ed4b2f76aa52d2cbbd1f44b29ae61077c
+size 3438167536