Upload configs from Drive bundle

configs/text_encoder_config.json

@@ -0,0 +1,39 @@
+{
+  "return_dict": true,
+  "output_hidden_states": false,
+  "dtype": "float32",
+  "chunk_size_feed_forward": 0,
+  "is_encoder_decoder": false,
+  "architectures": [
+    "CLIPTextModel"
+  ],
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1"
+  },
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1
+  },
+  "problem_type": null,
+  "_name_or_path": "/root/.cache/huggingface/hub/models--stable-diffusion-v1-5--stable-diffusion-v1-5/snapshots/451f4fe16113bff5a5d2269ed5ad43b0592e9a14/text_encoder",
+  "transformers_version": "5.0.0",
+  "dropout": 0.0,
+  "model_type": "clip_text_model",
+  "pad_token_id": 1,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "vocab_size": 49408,
+  "hidden_size": 768,
+  "intermediate_size": 3072,
+  "projection_dim": 768,
+  "num_hidden_layers": 12,
+  "num_attention_heads": 12,
+  "max_position_embeddings": 77,
+  "layer_norm_eps": 1e-05,
+  "hidden_act": "quick_gelu",
+  "initializer_range": 0.02,
+  "initializer_factor": 1.0,
+  "attention_dropout": 0.0,
+  "output_attentions": false
+}

configs/unet_config.json

@@ -0,0 +1,101 @@
+{
+  "sample_size": 64,
+  "in_channels": 4,
+  "out_channels": 4,
+  "center_input_sample": false,
+  "flip_sin_to_cos": true,
+  "freq_shift": 0,
+  "down_block_types": [
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "DownBlock2D"
+  ],
+  "mid_block_type": "UNetMidBlock2DCrossAttn",
+  "up_block_types": [
+    "UpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D"
+  ],
+  "only_cross_attention": false,
+  "block_out_channels": [
+    320,
+    640,
+    1280,
+    1280
+  ],
+  "layers_per_block": 2,
+  "downsample_padding": 1,
+  "mid_block_scale_factor": 1,
+  "dropout": 0.0,
+  "act_fn": "silu",
+  "norm_num_groups": 32,
+  "norm_eps": 1e-05,
+  "cross_attention_dim": 768,
+  "transformer_layers_per_block": 1,
+  "reverse_transformer_layers_per_block": null,
+  "encoder_hid_dim": null,
+  "encoder_hid_dim_type": null,
+  "attention_head_dim": 8,
+  "num_attention_heads": null,
+  "dual_cross_attention": false,
+  "use_linear_projection": false,
+  "class_embed_type": null,
+  "addition_embed_type": null,
+  "addition_time_embed_dim": null,
+  "num_class_embeds": null,
+  "upcast_attention": false,
+  "resnet_time_scale_shift": "default",
+  "resnet_skip_time_act": false,
+  "resnet_out_scale_factor": 1.0,
+  "time_embedding_type": "positional",
+  "time_embedding_dim": null,
+  "time_embedding_act_fn": null,
+  "timestep_post_act": null,
+  "time_cond_proj_dim": null,
+  "conv_in_kernel": 3,
+  "conv_out_kernel": 3,
+  "projection_class_embeddings_input_dim": null,
+  "attention_type": "default",
+  "class_embeddings_concat": false,
+  "mid_block_only_cross_attention": null,
+  "cross_attention_norm": null,
+  "addition_embed_type_num_heads": 64,
+  "_use_default_values": [
+    "num_attention_heads",
+    "cross_attention_norm",
+    "class_embeddings_concat",
+    "resnet_out_scale_factor",
+    "resnet_time_scale_shift",
+    "conv_in_kernel",
+    "dual_cross_attention",
+    "num_class_embeds",
+    "mid_block_only_cross_attention",
+    "reverse_transformer_layers_per_block",
+    "time_embedding_act_fn",
+    "upcast_attention",
+    "addition_embed_type_num_heads",
+    "projection_class_embeddings_input_dim",
+    "only_cross_attention",
+    "conv_out_kernel",
+    "mid_block_type",
+    "dropout",
+    "encoder_hid_dim_type",
+    "addition_embed_type",
+    "addition_time_embed_dim",
+    "time_embedding_dim",
+    "resnet_skip_time_act",
+    "encoder_hid_dim",
+    "use_linear_projection",
+    "attention_type",
+    "transformer_layers_per_block",
+    "timestep_post_act",
+    "time_embedding_type",
+    "class_embed_type",
+    "time_cond_proj_dim"
+  ],
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.6.0",
+  "_name_or_path": "/root/.cache/huggingface/hub/models--stable-diffusion-v1-5--stable-diffusion-v1-5/snapshots/451f4fe16113bff5a5d2269ed5ad43b0592e9a14/unet"
+}

configs/vae_config.json

@@ -0,0 +1,48 @@
+{
+  "in_channels": 3,
+  "out_channels": 3,
+  "down_block_types": [
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D"
+  ],
+  "up_block_types": [
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D"
+  ],
+  "block_out_channels": [
+    128,
+    256,
+    512,
+    512
+  ],
+  "layers_per_block": 2,
+  "act_fn": "silu",
+  "latent_channels": 4,
+  "norm_num_groups": 32,
+  "sample_size": 512,
+  "scaling_factor": 0.18215,
+  "shift_factor": null,
+  "latents_mean": null,
+  "latents_std": null,
+  "force_upcast": true,
+  "use_quant_conv": true,
+  "use_post_quant_conv": true,
+  "mid_block_add_attention": true,
+  "_use_default_values": [
+    "mid_block_add_attention",
+    "latents_mean",
+    "use_quant_conv",
+    "force_upcast",
+    "scaling_factor",
+    "shift_factor",
+    "use_post_quant_conv",
+    "latents_std"
+  ],
+  "_class_name": "AutoencoderKL",
+  "_diffusers_version": "0.6.0",
+  "_name_or_path": "/root/.cache/huggingface/hub/models--stable-diffusion-v1-5--stable-diffusion-v1-5/snapshots/451f4fe16113bff5a5d2269ed5ad43b0592e9a14/vae"
+}