Remove old-layout metadata orphaned by MODEL_SPEC.md restructure

config.json

@@ -1,33 +0,0 @@
-{
-  "_class_name": "StableDiffusionPipeline",
-  "_diffusers_version": "0.20.2",
-  "feature_extractor": [
-    "transformers",
-    "CLIPImageProcessor"
-  ],
-  "safety_checker": [
-    "stable_diffusion",
-    "StableDiffusionSafetyChecker"
-  ],
-  "scheduler": [
-    "diffusers",
-    "PNDMScheduler"
-  ],
-  "text_encoder": [
-    "transformers",
-    "CLIPTextModel"
-  ],
-  "tokenizer": [
-    "transformers",
-    "CLIPTokenizer"
-  ],
-  "unet": [
-    "diffusers",
-    "UNet2DConditionModel"
-  ],
-  "vae": [
-    "diffusers",
-    "AutoencoderKL"
-  ]
-}
-

text_encoder/config.json

@@ -1,24 +0,0 @@
-{
-  "_name_or_path": "openai/clip-vit-large-patch14",
-  "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,
-  "torch_dtype": "float32",
-  "transformers_version": "4.21.0.dev0",
-  "vocab_size": 49408
-}

unet/config.json

@@ -1,70 +0,0 @@
-{
-  "_class_name": "UNet2DConditionModel",
-  "_diffusers_version": "0.20.2",
-  "_name_or_path": "nota-ai/bk-sdm-tiny",
-  "act_fn": "silu",
-  "addition_embed_type": null,
-  "addition_embed_type_num_heads": 64,
-  "addition_time_embed_dim": null,
-  "attention_head_dim": 8,
-  "attention_type": "default",
-  "block_out_channels": [
-    320,
-    640,
-    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,
-  "decay": 0.9999,
-  "down_block_types": [
-    "CrossAttnDownBlock2D",
-    "CrossAttnDownBlock2D",
-    "CrossAttnDownBlock2D"
-  ],
-  "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,
-  "inv_gamma": 1.0,
-  "layers_per_block": 1,
-  "mid_block_only_cross_attention": null,
-  "mid_block_scale_factor": 1,
-  "mid_block_type": null,
-  "min_decay": 0.0,
-  "norm_eps": 1e-05,
-  "norm_num_groups": 32,
-  "num_attention_heads": null,
-  "num_class_embeds": null,
-  "only_cross_attention": false,
-  "optimization_step": 8000,
-  "out_channels": 4,
-  "power": 0.6666666666666666,
-  "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,
-  "transformer_layers_per_block": 1,
-  "up_block_types": [
-    "CrossAttnUpBlock2D",
-    "CrossAttnUpBlock2D",
-    "CrossAttnUpBlock2D"
-  ],
-  "upcast_attention": false,
-  "update_after_step": 0,
-  "use_ema_warmup": false,
-  "use_linear_projection": false
-}

vae/config.json

@@ -1,29 +0,0 @@
-{
-  "_class_name": "AutoencoderKL",
-  "_diffusers_version": "0.20.2",
-  "act_fn": "silu",
-  "block_out_channels": [
-    128,
-    256,
-    512,
-    512
-  ],
-  "down_block_types": [
-    "DownEncoderBlock2D",
-    "DownEncoderBlock2D",
-    "DownEncoderBlock2D",
-    "DownEncoderBlock2D"
-  ],
-  "in_channels": 3,
-  "latent_channels": 4,
-  "layers_per_block": 2,
-  "out_channels": 3,
-  "sample_size": 512,
-  "scaling_factor": 0.18215,
-  "up_block_types": [
-    "UpDecoderBlock2D",
-    "UpDecoderBlock2D",
-    "UpDecoderBlock2D",
-    "UpDecoderBlock2D"
-  ]
-}