Add model files

.gitignore

@@ -0,0 +1,8 @@
+/.idea
+.DS_Store
+__pycache__
+*/**/__pycache__
+logs
+/tmp
+/train
+/data

clone-wars-diffusion-v1.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e7f6f95a061a62caa9c3bc0715cd77ae668ba4b0e33ec8cc9c581a5e0a1a2c2
+size 2132856622

convert_diffusers_to_sd.py

@@ -0,0 +1,235 @@
+# Script for converting a HF Diffusers saved pipeline to a Stable Diffusion checkpoint.
+# *Only* converts the UNet, VAE, and Text Encoder.
+# Does not convert optimizer state or any other thing.
+# Written by jachiam
+
+import argparse
+import os.path as osp
+
+import torch
+
+
+# =================#
+# UNet Conversion #
+# =================#
+
+unet_conversion_map = [
+    # (stable-diffusion, HF Diffusers)
+    ("time_embed.0.weight", "time_embedding.linear_1.weight"),
+    ("time_embed.0.bias", "time_embedding.linear_1.bias"),
+    ("time_embed.2.weight", "time_embedding.linear_2.weight"),
+    ("time_embed.2.bias", "time_embedding.linear_2.bias"),
+    ("input_blocks.0.0.weight", "conv_in.weight"),
+    ("input_blocks.0.0.bias", "conv_in.bias"),
+    ("out.0.weight", "conv_norm_out.weight"),
+    ("out.0.bias", "conv_norm_out.bias"),
+    ("out.2.weight", "conv_out.weight"),
+    ("out.2.bias", "conv_out.bias"),
+]
+
+unet_conversion_map_resnet = [
+    # (stable-diffusion, HF Diffusers)
+    ("in_layers.0", "norm1"),
+    ("in_layers.2", "conv1"),
+    ("out_layers.0", "norm2"),
+    ("out_layers.3", "conv2"),
+    ("emb_layers.1", "time_emb_proj"),
+    ("skip_connection", "conv_shortcut"),
+]
+
+unet_conversion_map_layer = []
+# hardcoded number of downblocks and resnets/attentions...
+# would need smarter logic for other networks.
+for i in range(4):
+    # loop over downblocks/upblocks
+
+    for j in range(2):
+        # loop over resnets/attentions for downblocks
+        hf_down_res_prefix = f"down_blocks.{i}.resnets.{j}."
+        sd_down_res_prefix = f"input_blocks.{3*i + j + 1}.0."
+        unet_conversion_map_layer.append((sd_down_res_prefix, hf_down_res_prefix))
+
+        if i < 3:
+            # no attention layers in down_blocks.3
+            hf_down_atn_prefix = f"down_blocks.{i}.attentions.{j}."
+            sd_down_atn_prefix = f"input_blocks.{3*i + j + 1}.1."
+            unet_conversion_map_layer.append((sd_down_atn_prefix, hf_down_atn_prefix))
+
+    for j in range(3):
+        # loop over resnets/attentions for upblocks
+        hf_up_res_prefix = f"up_blocks.{i}.resnets.{j}."
+        sd_up_res_prefix = f"output_blocks.{3*i + j}.0."
+        unet_conversion_map_layer.append((sd_up_res_prefix, hf_up_res_prefix))
+
+        if i > 0:
+            # no attention layers in up_blocks.0
+            hf_up_atn_prefix = f"up_blocks.{i}.attentions.{j}."
+            sd_up_atn_prefix = f"output_blocks.{3*i + j}.1."
+            unet_conversion_map_layer.append((sd_up_atn_prefix, hf_up_atn_prefix))
+
+    if i < 3:
+        # no downsample in down_blocks.3
+        hf_downsample_prefix = f"down_blocks.{i}.downsamplers.0.conv."
+        sd_downsample_prefix = f"input_blocks.{3*(i+1)}.0.op."
+        unet_conversion_map_layer.append((sd_downsample_prefix, hf_downsample_prefix))
+
+        # no upsample in up_blocks.3
+        hf_upsample_prefix = f"up_blocks.{i}.upsamplers.0."
+        sd_upsample_prefix = f"output_blocks.{3*i + 2}.{1 if i == 0 else 2}."
+        unet_conversion_map_layer.append((sd_upsample_prefix, hf_upsample_prefix))
+
+hf_mid_atn_prefix = "mid_block.attentions.0."
+sd_mid_atn_prefix = "middle_block.1."
+unet_conversion_map_layer.append((sd_mid_atn_prefix, hf_mid_atn_prefix))
+
+for j in range(2):
+    hf_mid_res_prefix = f"mid_block.resnets.{j}."
+    sd_mid_res_prefix = f"middle_block.{2*j}."
+    unet_conversion_map_layer.append((sd_mid_res_prefix, hf_mid_res_prefix))
+
+
+def convert_unet_state_dict(unet_state_dict):
+    # buyer beware: this is a *brittle* function,
+    # and correct output requires that all of these pieces interact in
+    # the exact order in which I have arranged them.
+    mapping = {k: k for k in unet_state_dict.keys()}
+    for sd_name, hf_name in unet_conversion_map:
+        mapping[hf_name] = sd_name
+    for k, v in mapping.items():
+        if "resnets" in k:
+            for sd_part, hf_part in unet_conversion_map_resnet:
+                v = v.replace(hf_part, sd_part)
+            mapping[k] = v
+    for k, v in mapping.items():
+        for sd_part, hf_part in unet_conversion_map_layer:
+            v = v.replace(hf_part, sd_part)
+        mapping[k] = v
+    new_state_dict = {v: unet_state_dict[k] for k, v in mapping.items()}
+    return new_state_dict
+
+
+# ================#
+# VAE Conversion #
+# ================#
+
+vae_conversion_map = [
+    # (stable-diffusion, HF Diffusers)
+    ("nin_shortcut", "conv_shortcut"),
+    ("norm_out", "conv_norm_out"),
+    ("mid.attn_1.", "mid_block.attentions.0."),
+]
+
+for i in range(4):
+    # down_blocks have two resnets
+    for j in range(2):
+        hf_down_prefix = f"encoder.down_blocks.{i}.resnets.{j}."
+        sd_down_prefix = f"encoder.down.{i}.block.{j}."
+        vae_conversion_map.append((sd_down_prefix, hf_down_prefix))
+
+    if i < 3:
+        hf_downsample_prefix = f"down_blocks.{i}.downsamplers.0."
+        sd_downsample_prefix = f"down.{i}.downsample."
+        vae_conversion_map.append((sd_downsample_prefix, hf_downsample_prefix))
+
+        hf_upsample_prefix = f"up_blocks.{i}.upsamplers.0."
+        sd_upsample_prefix = f"up.{3-i}.upsample."
+        vae_conversion_map.append((sd_upsample_prefix, hf_upsample_prefix))
+
+    # up_blocks have three resnets
+    # also, up blocks in hf are numbered in reverse from sd
+    for j in range(3):
+        hf_up_prefix = f"decoder.up_blocks.{i}.resnets.{j}."
+        sd_up_prefix = f"decoder.up.{3-i}.block.{j}."
+        vae_conversion_map.append((sd_up_prefix, hf_up_prefix))
+
+# this part accounts for mid blocks in both the encoder and the decoder
+for i in range(2):
+    hf_mid_res_prefix = f"mid_block.resnets.{i}."
+    sd_mid_res_prefix = f"mid.block_{i+1}."
+    vae_conversion_map.append((sd_mid_res_prefix, hf_mid_res_prefix))
+
+
+vae_conversion_map_attn = [
+    # (stable-diffusion, HF Diffusers)
+    ("norm.", "group_norm."),
+    ("q.", "query."),
+    ("k.", "key."),
+    ("v.", "value."),
+    ("proj_out.", "proj_attn."),
+]
+
+
+def reshape_weight_for_sd(w):
+    # convert HF linear weights to SD conv2d weights
+    return w.reshape(*w.shape, 1, 1)
+
+
+def convert_vae_state_dict(vae_state_dict):
+    mapping = {k: k for k in vae_state_dict.keys()}
+    for k, v in mapping.items():
+        for sd_part, hf_part in vae_conversion_map:
+            v = v.replace(hf_part, sd_part)
+        mapping[k] = v
+    for k, v in mapping.items():
+        if "attentions" in k:
+            for sd_part, hf_part in vae_conversion_map_attn:
+                v = v.replace(hf_part, sd_part)
+            mapping[k] = v
+    new_state_dict = {v: vae_state_dict[k] for k, v in mapping.items()}
+    weights_to_convert = ["q", "k", "v", "proj_out"]
+    for k, v in new_state_dict.items():
+        for weight_name in weights_to_convert:
+            if f"mid.attn_1.{weight_name}.weight" in k:
+                print(f"Reshaping {k} for SD format")
+                new_state_dict[k] = reshape_weight_for_sd(v)
+    return new_state_dict
+
+
+# =========================#
+# Text Encoder Conversion #
+# =========================#
+# pretty much a no-op
+
+
+def convert_text_enc_state_dict(text_enc_dict):
+    return text_enc_dict
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser()
+
+    parser.add_argument("--model_path", default=None, type=str, required=True, help="Path to the model to convert.")
+    parser.add_argument("--checkpoint_path", default=None, type=str, required=True, help="Path to the output model.")
+    parser.add_argument("--half", action="store_true", help="Save weights in half precision.")
+
+    args = parser.parse_args()
+
+    assert args.model_path is not None, "Must provide a model path!"
+
+    assert args.checkpoint_path is not None, "Must provide a checkpoint path!"
+
+    unet_path = osp.join(args.model_path, "unet", "diffusion_pytorch_model.bin")
+    vae_path = osp.join(args.model_path, "vae", "diffusion_pytorch_model.bin")
+    text_enc_path = osp.join(args.model_path, "text_encoder", "pytorch_model.bin")
+
+    # Convert the UNet model
+    unet_state_dict = torch.load(unet_path, map_location='cpu')
+    unet_state_dict = convert_unet_state_dict(unet_state_dict)
+    unet_state_dict = {"model.diffusion_model." + k: v for k, v in unet_state_dict.items()}
+
+    # Convert the VAE model
+    vae_state_dict = torch.load(vae_path, map_location='cpu')
+    vae_state_dict = convert_vae_state_dict(vae_state_dict)
+    vae_state_dict = {"first_stage_model." + k: v for k, v in vae_state_dict.items()}
+
+    # Convert the text encoder model
+    text_enc_dict = torch.load(text_enc_path, map_location='cpu')
+    text_enc_dict = convert_text_enc_state_dict(text_enc_dict)
+    text_enc_dict = {"cond_stage_model.transformer." + k: v for k, v in text_enc_dict.items()}
+
+    # Put together new checkpoint
+    state_dict = {**unet_state_dict, **vae_state_dict, **text_enc_dict}
+    if args.half:
+        state_dict = {k:v.half() for k,v in state_dict.items()}
+    state_dict = {"state_dict": state_dict}
+    torch.save(state_dict, args.checkpoint_path)

feature_extractor/preprocessor_config.json

@@ -0,0 +1,20 @@
+{
+  "crop_size": 224,
+  "do_center_crop": true,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_resize": true,
+  "feature_extractor_type": "CLIPFeatureExtractor",
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "resample": 3,
+  "size": 224
+}

model_index.json

@@ -0,0 +1,32 @@
+{
+  "_class_name": "StableDiffusionPipeline",
+  "_diffusers_version": "0.6.0",
+  "feature_extractor": [
+    "transformers",
+    "CLIPFeatureExtractor"
+  ],
+  "safety_checker": [
+    "stable_diffusion",
+    "StableDiffusionSafetyChecker"
+  ],
+  "scheduler": [
+    "diffusers",
+    "PNDMScheduler"
+  ],
+  "text_encoder": [
+    "transformers",
+    "CLIPTextModel"
+  ],
+  "tokenizer": [
+    "transformers",
+    "CLIPTokenizer"
+  ],
+  "unet": [
+    "diffusers",
+    "UNet2DConditionModel"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKL"
+  ]
+}

safety_checker/config.json

@@ -0,0 +1,175 @@
+{
+  "_commit_hash": "4bb648a606ef040e7685bde262611766a5fdd67b",
+  "_name_or_path": "CompVis/stable-diffusion-safety-checker",
+  "architectures": [
+    "StableDiffusionSafetyChecker"
+  ],
+  "initializer_factor": 1.0,
+  "logit_scale_init_value": 2.6592,
+  "model_type": "clip",
+  "projection_dim": 768,
+  "text_config": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "bos_token_id": 0,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "dropout": 0.0,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 2,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "quick_gelu",
+    "hidden_size": 768,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-05,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 77,
+    "min_length": 0,
+    "model_type": "clip_text_model",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 12,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 12,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 1,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "transformers_version": "4.22.0.dev0",
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "vocab_size": 49408
+  },
+  "text_config_dict": {
+    "hidden_size": 768,
+    "intermediate_size": 3072,
+    "num_attention_heads": 12,
+    "num_hidden_layers": 12
+  },
+  "torch_dtype": "float32",
+  "transformers_version": null,
+  "vision_config": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "dropout": 0.0,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "quick_gelu",
+    "hidden_size": 1024,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "image_size": 224,
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 4096,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-05,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "model_type": "clip_vision_model",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 16,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_channels": 3,
+    "num_hidden_layers": 24,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "patch_size": 14,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "transformers_version": "4.22.0.dev0",
+    "typical_p": 1.0,
+    "use_bfloat16": false
+  },
+  "vision_config_dict": {
+    "hidden_size": 1024,
+    "intermediate_size": 4096,
+    "num_attention_heads": 16,
+    "num_hidden_layers": 24,
+    "patch_size": 14
+  }
+}

safety_checker/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:193490b58ef62739077262e833bf091c66c29488058681ac25cf7df3d8190974
+size 1216061799

scheduler/scheduler_config.json

@@ -0,0 +1,12 @@
+{
+  "_class_name": "DDIMScheduler",
+  "_diffusers_version": "0.7.0.dev0",
+  "beta_end": 0.012,
+  "beta_schedule": "scaled_linear",
+  "beta_start": 0.00085,
+  "clip_sample": false,
+  "num_train_timesteps": 1000,
+  "set_alpha_to_one": false,
+  "steps_offset": 1,
+  "trained_betas": null
+}

text_encoder/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "models/b_step1/20000",
+  "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": "4.24.0",
+  "vocab_size": 49408
+}

text_encoder/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9763dce458c00c60d8c3a8206310410fac434b8c7094d6b9993542991cb048f
+size 492309793

tokenizer/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer/tokenizer_config.json

@@ -0,0 +1,34 @@
+{
+  "add_prefix_space": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "do_lower_case": true,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "model_max_length": 77,
+  "name_or_path": "models/b_step1/20000\\tokenizer",
+  "pad_token": "<|endoftext|>",
+  "special_tokens_map_file": "./special_tokens_map.json",
+  "tokenizer_class": "CLIPTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

unet/config.json

@@ -0,0 +1,37 @@
+{
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.7.0.dev0",
+  "_name_or_path": "models/b_step1/20000",
+  "act_fn": "silu",
+  "attention_head_dim": 8,
+  "block_out_channels": [
+    320,
+    640,
+    1280,
+    1280
+  ],
+  "center_input_sample": false,
+  "cross_attention_dim": 768,
+  "down_block_types": [
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "DownBlock2D"
+  ],
+  "downsample_padding": 1,
+  "flip_sin_to_cos": true,
+  "freq_shift": 0,
+  "in_channels": 4,
+  "layers_per_block": 2,
+  "mid_block_scale_factor": 1,
+  "norm_eps": 1e-05,
+  "norm_num_groups": 32,
+  "out_channels": 4,
+  "sample_size": 64,
+  "up_block_types": [
+    "UpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D"
+  ]
+}

unet/diffusion_pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea0b39120d0adb2d9736d2ffada4e4b7d56487562456927e55b71cd27f180570
+size 3438375973

vae/README.md

@@ -0,0 +1,84 @@
+---
+license: mit
+tags:
+- stable-diffusion
+- stable-diffusion-diffusers
+- text-to-image
+inference: false
+---
+# Improved Autoencoders
+
+## Utilizing
+These weights are intended to be used with the [🧨 diffusers library](https://github.com/huggingface/diffusers). If you are looking for the model to use with the original [CompVis Stable Diffusion codebase](https://github.com/CompVis/stable-diffusion), [come here](https://huggingface.co/CompVis/stabilityai/sd-vae-ft-ema-original).
+
+#### How to use with 🧨 diffusers
+You can integrate this fine-tuned VAE decoder to your existing `diffusers` workflows, by including a `vae` argument to the `StableDiffusionPipeline`
+```py
+from diffusers.models import AutoencoderKL
+from diffusers import StableDiffusionPipeline
+
+model = "CompVis/stable-diffusion-v1-4"
+vae = AutoencoderKL.from_pretrained("stabilityai/sd-vae-ft-mse")
+pipe = StableDiffusionPipeline.from_pretrained(model, vae=vae)
+```
+
+## Decoder Finetuning
+We publish two kl-f8 autoencoder versions, finetuned from the original [kl-f8 autoencoder](https://github.com/CompVis/latent-diffusion#pretrained-autoencoding-models).
+The first, _ft-EMA_, was resumed from the original checkpoint, trained for 313198 steps and uses EMA weights.
+The second, _ft-MSE_, was resumed from _ft-EMA_ and uses EMA weights and was trained for another 280k steps using a re-weighted loss, with more emphasis 
+on MSE reconstruction (producing somewhat ``smoother'' outputs).
+To keep compatibility with existing models, only the decoder part was finetuned; the checkpoints can be used as a drop-in replacement for the existing autoencoder.
+
+_Original kl-f8 VAE vs f8-ft-EMA vs f8-ft-MSE_
+
+## Evaluation 
+### COCO 2017 (256x256, val, 5000 images)
+| Model    | train steps | rFID | PSNR         | SSIM          | PSIM          | Link                                                                              | Comments                                                                                        
+|----------|---------|------|--------------|---------------|---------------|-----------------------------------------------------------------------------------|-------------------------------------------------------------------------------------------------|
+|          |         |      |              |               |               |                                                                                   |                                                                                                 |
+| original | 246803        | 4.99 | 23.4 +/- 3.8 | 0.69 +/- 0.14 | 1.01 +/- 0.28 | https://ommer-lab.com/files/latent-diffusion/kl-f8.zip                            | as used in SD                                                                                   |
+| ft-EMA   | 560001        | 4.42 | 23.8 +/- 3.9 | 0.69 +/- 0.13 | 0.96 +/- 0.27 | https://huggingface.co/stabilityai/sd-vae-ft-ema-original/resolve/main/vae-ft-ema-560000-ema-pruned.ckpt | slightly better overall, with EMA                                                               |
+| ft-MSE   | 840001        | 4.70 | 24.5 +/- 3.7 | 0.71 +/- 0.13 | 0.92 +/- 0.27 | https://huggingface.co/stabilityai/sd-vae-ft-mse-original/resolve/main/vae-ft-mse-840000-ema-pruned.ckpt | resumed with EMA from ft-EMA, emphasis on MSE (rec. loss = MSE + 0.1 * LPIPS), smoother outputs |
+
+
+### LAION-Aesthetics 5+ (256x256, subset, 10000 images)
+| Model    | train steps | rFID | PSNR         | SSIM          | PSIM          | Link                                                                              | Comments                                                                                        
+|----------|-----------|------|--------------|---------------|---------------|-----------------------------------------------------------------------------------|-------------------------------------------------------------------------------------------------|
+|          |           |      |              |               |               |                                                                                   |                                                                                                 |
+| original | 246803         | 2.61 | 26.0 +/- 4.4 | 0.81 +/- 0.12 | 0.75 +/- 0.36 | https://ommer-lab.com/files/latent-diffusion/kl-f8.zip                            | as used in SD                                                                                   |
+| ft-EMA   | 560001          | 1.77 | 26.7 +/- 4.8 | 0.82 +/- 0.12 | 0.67 +/- 0.34 | https://huggingface.co/stabilityai/sd-vae-ft-ema-original/resolve/main/vae-ft-ema-560000-ema-pruned.ckpt | slightly better overall, with EMA                                                               |
+| ft-MSE   | 840001          | 1.88 | 27.3 +/- 4.7 | 0.83 +/- 0.11 | 0.65 +/- 0.34 | https://huggingface.co/stabilityai/sd-vae-ft-mse-original/resolve/main/vae-ft-mse-840000-ema-pruned.ckpt | resumed with EMA from ft-EMA, emphasis on MSE (rec. loss = MSE + 0.1 * LPIPS), smoother outputs |
+
+
+### Visual
+_Visualization of reconstructions on  256x256 images from the COCO2017 validation dataset._ 
+
+<p align="center">
+  <br>
+  <b>
+256x256: ft-EMA (left), ft-MSE (middle), original (right)</b>
+</p>
+
+<p align="center">
+<img src=https://huggingface.co/stabilityai/stable-diffusion-decoder-finetune/resolve/main/eval/ae-decoder-tuning-reconstructions/merged/00025_merged.png />
+</p>
+
+<p align="center">
+<img src=https://huggingface.co/stabilityai/stable-diffusion-decoder-finetune/resolve/main/eval/ae-decoder-tuning-reconstructions/merged/00011_merged.png />
+</p>
+
+<p align="center">
+<img src=https://huggingface.co/stabilityai/stable-diffusion-decoder-finetune/resolve/main/eval/ae-decoder-tuning-reconstructions/merged/00037_merged.png />
+</p>
+
+<p align="center">
+<img src=https://huggingface.co/stabilityai/stable-diffusion-decoder-finetune/resolve/main/eval/ae-decoder-tuning-reconstructions/merged/00043_merged.png />
+</p>
+
+<p align="center">
+<img src=https://huggingface.co/stabilityai/stable-diffusion-decoder-finetune/resolve/main/eval/ae-decoder-tuning-reconstructions/merged/00053_merged.png />
+</p>
+
+<p align="center">
+<img src=https://huggingface.co/stabilityai/stable-diffusion-decoder-finetune/resolve/main/eval/ae-decoder-tuning-reconstructions/merged/00029_merged.png />
+</p>

vae/config.json

@@ -0,0 +1,30 @@
+{
+  "_class_name": "AutoencoderKL",
+  "_diffusers_version": "0.7.0.dev0",
+  "_name_or_path": "stabilityai/sd-vae-ft-mse",
+  "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,
+  "norm_num_groups": 32,
+  "out_channels": 3,
+  "sample_size": 256,
+  "up_block_types": [
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D"
+  ]
+}

vae/diffusion_pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36bb8e1b54aba3a0914eb35fba13dcb107e9f18d379d1df2158732cd4bf56a94
+size 334711857