import os import imageio import numpy as np from tqdm import tqdm from typing import Union from einops import rearrange from safetensors import safe_open from transformers import CLIPTextModel import torch import torchvision import torch.distributed as dist def zero_rank_print(s): if (not dist.is_initialized()) and (dist.is_initialized() and dist.get_rank() == 0): print("### " + s) def save_videos_grid(videos: torch.Tensor, path: str, rescale=False, n_rows=6, fps=8): videos = rearrange(videos, "b c t h w -> t b c h w") outputs = [] for x in videos: x = torchvision.utils.make_grid(x, nrow=n_rows) x = x.transpose(0, 1).transpose(1, 2).squeeze(-1) if rescale: x = (x + 1.0) / 2.0 # -1,1 -> 0,1 x = (x * 255).numpy().astype(np.uint8) outputs.append(x) os.makedirs(os.path.dirname(path), exist_ok=True) imageio.mimsave(path, outputs, fps=fps) # DDIM Inversion @torch.no_grad() def init_prompt(prompt, pipeline): uncond_input = pipeline.tokenizer( [""], padding="max_length", max_length=pipeline.tokenizer.model_max_length, return_tensors="pt" ) uncond_embeddings = pipeline.text_encoder(uncond_input.input_ids.to(pipeline.device))[0] text_input = pipeline.tokenizer( [prompt], padding="max_length", max_length=pipeline.tokenizer.model_max_length, truncation=True, return_tensors="pt", ) text_embeddings = pipeline.text_encoder(text_input.input_ids.to(pipeline.device))[0] context = torch.cat([uncond_embeddings, text_embeddings]) return context def next_step(model_output: Union[torch.FloatTensor, np.ndarray], timestep: int, sample: Union[torch.FloatTensor, np.ndarray], ddim_scheduler): timestep, next_timestep = min( timestep - ddim_scheduler.config.num_train_timesteps // ddim_scheduler.num_inference_steps, 999), timestep alpha_prod_t = ddim_scheduler.alphas_cumprod[timestep] if timestep >= 0 else ddim_scheduler.final_alpha_cumprod alpha_prod_t_next = ddim_scheduler.alphas_cumprod[next_timestep] beta_prod_t = 1 - alpha_prod_t next_original_sample = (sample - beta_prod_t ** 0.5 * model_output) / alpha_prod_t ** 0.5 next_sample_direction = (1 - alpha_prod_t_next) ** 0.5 * model_output next_sample = alpha_prod_t_next ** 0.5 * next_original_sample + next_sample_direction return next_sample def get_noise_pred_single(latents, t, context, unet): noise_pred = unet(latents, t, encoder_hidden_states=context)["sample"] return noise_pred @torch.no_grad() def ddim_loop(pipeline, ddim_scheduler, latent, num_inv_steps, prompt): context = init_prompt(prompt, pipeline) uncond_embeddings, cond_embeddings = context.chunk(2) all_latent = [latent] latent = latent.clone().detach() for i in tqdm(range(num_inv_steps)): t = ddim_scheduler.timesteps[len(ddim_scheduler.timesteps) - i - 1] noise_pred = get_noise_pred_single(latent, t, cond_embeddings, pipeline.unet) latent = next_step(noise_pred, t, latent, ddim_scheduler) all_latent.append(latent) return all_latent @torch.no_grad() def ddim_inversion(pipeline, ddim_scheduler, video_latent, num_inv_steps, prompt=""): ddim_latents = ddim_loop(pipeline, ddim_scheduler, video_latent, num_inv_steps, prompt) return ddim_latents def load_weights( magictime_pipeline, motion_module_path = "", dreambooth_model_path = "", magic_adapter_s_path = "", magic_adapter_t_path = "", magic_text_encoder_path = "", ): # motion module unet_state_dict = {} if motion_module_path != "": print(f"load motion module from {motion_module_path}") try: motion_module_state_dict = torch.load(motion_module_path, map_location="cpu") if "state_dict" in motion_module_state_dict: motion_module_state_dict = motion_module_state_dict["state_dict"] for name, param in motion_module_state_dict.items(): if "motion_modules." in name: modified_name = name.removeprefix('module.') if name.startswith('module.') else name unet_state_dict[modified_name] = param except Exception as e: print(f"Error loading motion module: {e}") try: missing, unexpected = magictime_pipeline.unet.load_state_dict(unet_state_dict, strict=False) assert len(unexpected) == 0, f"Unexpected keys in state_dict: {unexpected}" del unet_state_dict except Exception as e: print(f"Error loading state dict into UNet: {e}") # base model if dreambooth_model_path != "": print(f"load dreambooth model from {dreambooth_model_path}") if dreambooth_model_path.endswith(".safetensors"): dreambooth_state_dict = {} with safe_open(dreambooth_model_path, framework="pt", device="cpu") as f: for key in f.keys(): dreambooth_state_dict[key] = f.get_tensor(key) elif dreambooth_model_path.endswith(".ckpt"): dreambooth_state_dict = torch.load(dreambooth_model_path, map_location="cpu") # 1. vae converted_vae_checkpoint = convert_ldm_vae_checkpoint(dreambooth_state_dict, magictime_pipeline.vae.config) magictime_pipeline.vae.load_state_dict(converted_vae_checkpoint) # 2. unet converted_unet_checkpoint = convert_ldm_unet_checkpoint(dreambooth_state_dict, magictime_pipeline.unet.config) magictime_pipeline.unet.load_state_dict(converted_unet_checkpoint, strict=False) # 3. text_model magictime_pipeline.text_encoder = convert_ldm_clip_checkpoint(dreambooth_state_dict) del dreambooth_state_dict # MagicAdapter and MagicTextEncoder if magic_adapter_s_path != "": print(f"load domain lora from {magic_adapter_s_path}") magic_adapter_s_state_dict = torch.load(magic_adapter_s_path, map_location="cpu") magictime_pipeline = load_diffusers_lora(magictime_pipeline, magic_adapter_s_state_dict, alpha=1.0) if magic_adapter_t_path != "" or magic_text_encoder_path != "": from swift import Swift if magic_adapter_t_path != "": print("load lora from swift for Unet") Swift.from_pretrained(magictime_pipeline.unet, magic_adapter_t_path) if magic_text_encoder_path != "": print("load lora from swift for text encoder") Swift.from_pretrained(magictime_pipeline.text_encoder, magic_text_encoder_path) return magictime_pipeline def load_diffusers_lora(pipeline, state_dict, alpha=1.0): # directly update weight in diffusers model for key in state_dict: # only process lora down key if "up." in key: continue up_key = key.replace(".down.", ".up.") model_key = key.replace("processor.", "").replace("_lora", "").replace("down.", "").replace("up.", "") model_key = model_key.replace("to_out.", "to_out.0.") layer_infos = model_key.split(".")[:-1] curr_layer = pipeline.unet while len(layer_infos) > 0: temp_name = layer_infos.pop(0) curr_layer = curr_layer.__getattr__(temp_name) weight_down = state_dict[key] * 2 weight_up = state_dict[up_key] * 2 curr_layer.weight.data += alpha * torch.mm(weight_up, weight_down).to(curr_layer.weight.data.device) return pipeline def load_diffusers_lora_unet(unet, state_dict, alpha=1.0): # directly update weight in diffusers model for key in state_dict: # only process lora down key if "up." in key: continue up_key = key.replace(".down.", ".up.") model_key = key.replace("processor.", "").replace("_lora", "").replace("down.", "").replace("up.", "") model_key = model_key.replace("to_out.", "to_out.0.") layer_infos = model_key.split(".")[:-1] curr_layer = unet while len(layer_infos) > 0: temp_name = layer_infos.pop(0) curr_layer = curr_layer.__getattr__(temp_name) weight_down = state_dict[key] * 2 weight_up = state_dict[up_key] * 2 curr_layer.weight.data += alpha * torch.mm(weight_up, weight_down).to(curr_layer.weight.data.device) return unet def convert_lora(pipeline, state_dict, LORA_PREFIX_UNET="lora_unet", LORA_PREFIX_TEXT_ENCODER="lora_te", alpha=0.6): visited = [] # directly update weight in diffusers model for key in state_dict: # it is suggested to print out the key, it usually will be something like below # "lora_te_text_model_encoder_layers_0_self_attn_k_proj.lora_down.weight" # as we have set the alpha beforehand, so just skip if ".alpha" in key or key in visited: continue if "text" in key: layer_infos = key.split(".")[0].split(LORA_PREFIX_TEXT_ENCODER + "_")[-1].split("_") curr_layer = pipeline.text_encoder else: layer_infos = key.split(".")[0].split(LORA_PREFIX_UNET + "_")[-1].split("_") curr_layer = pipeline.unet # find the target layer temp_name = layer_infos.pop(0) while len(layer_infos) > -1: try: curr_layer = curr_layer.__getattr__(temp_name) if len(layer_infos) > 0: temp_name = layer_infos.pop(0) elif len(layer_infos) == 0: break except Exception: if len(temp_name) > 0: temp_name += "_" + layer_infos.pop(0) else: temp_name = layer_infos.pop(0) pair_keys = [] if "lora_down" in key: pair_keys.append(key.replace("lora_down", "lora_up")) pair_keys.append(key) else: pair_keys.append(key) pair_keys.append(key.replace("lora_up", "lora_down")) # update weight if len(state_dict[pair_keys[0]].shape) == 4: weight_up = state_dict[pair_keys[0]].squeeze(3).squeeze(2).to(torch.float32) weight_down = state_dict[pair_keys[1]].squeeze(3).squeeze(2).to(torch.float32) curr_layer.weight.data += alpha * torch.mm(weight_up, weight_down).unsqueeze(2).unsqueeze(3).to(curr_layer.weight.data.device) else: weight_up = state_dict[pair_keys[0]].to(torch.float32) weight_down = state_dict[pair_keys[1]].to(torch.float32) curr_layer.weight.data += alpha * torch.mm(weight_up, weight_down).to(curr_layer.weight.data.device) # update visited list for item in pair_keys: visited.append(item) return pipeline def shave_segments(path, n_shave_prefix_segments=1): """ Removes segments. Positive values shave the first segments, negative shave the last segments. """ if n_shave_prefix_segments >= 0: return ".".join(path.split(".")[n_shave_prefix_segments:]) else: return ".".join(path.split(".")[:n_shave_prefix_segments]) def renew_resnet_paths(old_list, n_shave_prefix_segments=0): """ Updates paths inside resnets to the new naming scheme (local renaming) """ mapping = [] for old_item in old_list: new_item = old_item.replace("in_layers.0", "norm1") new_item = new_item.replace("in_layers.2", "conv1") new_item = new_item.replace("out_layers.0", "norm2") new_item = new_item.replace("out_layers.3", "conv2") new_item = new_item.replace("emb_layers.1", "time_emb_proj") new_item = new_item.replace("skip_connection", "conv_shortcut") new_item = shave_segments(new_item, n_shave_prefix_segments=n_shave_prefix_segments) mapping.append({"old": old_item, "new": new_item}) return mapping def renew_vae_resnet_paths(old_list, n_shave_prefix_segments=0): """ Updates paths inside resnets to the new naming scheme (local renaming) """ mapping = [] for old_item in old_list: new_item = old_item new_item = new_item.replace("nin_shortcut", "conv_shortcut") new_item = shave_segments(new_item, n_shave_prefix_segments=n_shave_prefix_segments) mapping.append({"old": old_item, "new": new_item}) return mapping def renew_attention_paths(old_list, n_shave_prefix_segments=0): """ Updates paths inside attentions to the new naming scheme (local renaming) """ mapping = [] for old_item in old_list: new_item = old_item mapping.append({"old": old_item, "new": new_item}) return mapping def renew_vae_attention_paths(old_list, n_shave_prefix_segments=0): """ Updates paths inside attentions to the new naming scheme (local renaming) """ mapping = [] for old_item in old_list: new_item = old_item new_item = new_item.replace("norm.weight", "group_norm.weight") new_item = new_item.replace("norm.bias", "group_norm.bias") new_item = new_item.replace("q.weight", "query.weight") new_item = new_item.replace("q.bias", "query.bias") new_item = new_item.replace("k.weight", "key.weight") new_item = new_item.replace("k.bias", "key.bias") new_item = new_item.replace("v.weight", "value.weight") new_item = new_item.replace("v.bias", "value.bias") new_item = new_item.replace("proj_out.weight", "proj_attn.weight") new_item = new_item.replace("proj_out.bias", "proj_attn.bias") new_item = shave_segments(new_item, n_shave_prefix_segments=n_shave_prefix_segments) mapping.append({"old": old_item, "new": new_item}) return mapping def assign_to_checkpoint( paths, checkpoint, old_checkpoint, attention_paths_to_split=None, additional_replacements=None, config=None ): """ This does the final conversion step: take locally converted weights and apply a global renaming to them. It splits attention layers, and takes into account additional replacements that may arise. Assigns the weights to the new checkpoint. """ assert isinstance(paths, list), "Paths should be a list of dicts containing 'old' and 'new' keys." # Splits the attention layers into three variables. if attention_paths_to_split is not None: for path, path_map in attention_paths_to_split.items(): old_tensor = old_checkpoint[path] channels = old_tensor.shape[0] // 3 target_shape = (-1, channels) if len(old_tensor.shape) == 3 else (-1) num_heads = old_tensor.shape[0] // config["num_head_channels"] // 3 old_tensor = old_tensor.reshape((num_heads, 3 * channels // num_heads) + old_tensor.shape[1:]) query, key, value = old_tensor.split(channels // num_heads, dim=1) checkpoint[path_map["query"]] = query.reshape(target_shape) checkpoint[path_map["key"]] = key.reshape(target_shape) checkpoint[path_map["value"]] = value.reshape(target_shape) for path in paths: new_path = path["new"] # These have already been assigned if attention_paths_to_split is not None and new_path in attention_paths_to_split: continue # Global renaming happens here new_path = new_path.replace("middle_block.0", "mid_block.resnets.0") new_path = new_path.replace("middle_block.1", "mid_block.attentions.0") new_path = new_path.replace("middle_block.2", "mid_block.resnets.1") if additional_replacements is not None: for replacement in additional_replacements: new_path = new_path.replace(replacement["old"], replacement["new"]) # proj_attn.weight has to be converted from conv 1D to linear if "proj_attn.weight" in new_path: checkpoint[new_path] = old_checkpoint[path["old"]][:, :, 0] else: checkpoint[new_path] = old_checkpoint[path["old"]] def convert_ldm_unet_checkpoint(checkpoint, config, path=None, extract_ema=False): """ Takes a state dict and a config, and returns a converted checkpoint. """ # extract state_dict for UNet unet_state_dict = {} keys = list(checkpoint.keys()) unet_key = "model.diffusion_model." # at least a 100 parameters have to start with `model_ema` in order for the checkpoint to be EMA if sum(k.startswith("model_ema") for k in keys) > 100 and extract_ema: print(f"Checkpoint {path} has both EMA and non-EMA weights.") print( "In this conversion only the EMA weights are extracted. If you want to instead extract the non-EMA" " weights (useful to continue fine-tuning), please make sure to remove the `--extract_ema` flag." ) for key in keys: if key.startswith("model.diffusion_model"): flat_ema_key = "model_ema." + "".join(key.split(".")[1:]) unet_state_dict[key.replace(unet_key, "")] = checkpoint.pop(flat_ema_key) else: if sum(k.startswith("model_ema") for k in keys) > 100: print( "In this conversion only the non-EMA weights are extracted. If you want to instead extract the EMA" " weights (usually better for inference), please make sure to add the `--extract_ema` flag." ) for key in keys: if key.startswith(unet_key): unet_state_dict[key.replace(unet_key, "")] = checkpoint.pop(key) new_checkpoint = {} new_checkpoint["time_embedding.linear_1.weight"] = unet_state_dict["time_embed.0.weight"] new_checkpoint["time_embedding.linear_1.bias"] = unet_state_dict["time_embed.0.bias"] new_checkpoint["time_embedding.linear_2.weight"] = unet_state_dict["time_embed.2.weight"] new_checkpoint["time_embedding.linear_2.bias"] = unet_state_dict["time_embed.2.bias"] if config["class_embed_type"] is None: # No parameters to port ... elif config["class_embed_type"] == "timestep" or config["class_embed_type"] == "projection": new_checkpoint["class_embedding.linear_1.weight"] = unet_state_dict["label_emb.0.0.weight"] new_checkpoint["class_embedding.linear_1.bias"] = unet_state_dict["label_emb.0.0.bias"] new_checkpoint["class_embedding.linear_2.weight"] = unet_state_dict["label_emb.0.2.weight"] new_checkpoint["class_embedding.linear_2.bias"] = unet_state_dict["label_emb.0.2.bias"] else: raise NotImplementedError(f"Not implemented `class_embed_type`: {config['class_embed_type']}") new_checkpoint["conv_in.weight"] = unet_state_dict["input_blocks.0.0.weight"] new_checkpoint["conv_in.bias"] = unet_state_dict["input_blocks.0.0.bias"] new_checkpoint["conv_norm_out.weight"] = unet_state_dict["out.0.weight"] new_checkpoint["conv_norm_out.bias"] = unet_state_dict["out.0.bias"] new_checkpoint["conv_out.weight"] = unet_state_dict["out.2.weight"] new_checkpoint["conv_out.bias"] = unet_state_dict["out.2.bias"] # Retrieves the keys for the input blocks only num_input_blocks = len({".".join(layer.split(".")[:2]) for layer in unet_state_dict if "input_blocks" in layer}) input_blocks = { layer_id: [key for key in unet_state_dict if f"input_blocks.{layer_id}" in key] for layer_id in range(num_input_blocks) } # Retrieves the keys for the middle blocks only num_middle_blocks = len({".".join(layer.split(".")[:2]) for layer in unet_state_dict if "middle_block" in layer}) middle_blocks = { layer_id: [key for key in unet_state_dict if f"middle_block.{layer_id}" in key] for layer_id in range(num_middle_blocks) } # Retrieves the keys for the output blocks only num_output_blocks = len({".".join(layer.split(".")[:2]) for layer in unet_state_dict if "output_blocks" in layer}) output_blocks = { layer_id: [key for key in unet_state_dict if f"output_blocks.{layer_id}" in key] for layer_id in range(num_output_blocks) } for i in range(1, num_input_blocks): block_id = (i - 1) // (config["layers_per_block"] + 1) layer_in_block_id = (i - 1) % (config["layers_per_block"] + 1) resnets = [ key for key in input_blocks[i] if f"input_blocks.{i}.0" in key and f"input_blocks.{i}.0.op" not in key ] attentions = [key for key in input_blocks[i] if f"input_blocks.{i}.1" in key] if f"input_blocks.{i}.0.op.weight" in unet_state_dict: new_checkpoint[f"down_blocks.{block_id}.downsamplers.0.conv.weight"] = unet_state_dict.pop( f"input_blocks.{i}.0.op.weight" ) new_checkpoint[f"down_blocks.{block_id}.downsamplers.0.conv.bias"] = unet_state_dict.pop( f"input_blocks.{i}.0.op.bias" ) paths = renew_resnet_paths(resnets) meta_path = {"old": f"input_blocks.{i}.0", "new": f"down_blocks.{block_id}.resnets.{layer_in_block_id}"} assign_to_checkpoint( paths, new_checkpoint, unet_state_dict, additional_replacements=[meta_path], config=config ) if len(attentions): paths = renew_attention_paths(attentions) meta_path = {"old": f"input_blocks.{i}.1", "new": f"down_blocks.{block_id}.attentions.{layer_in_block_id}"} assign_to_checkpoint( paths, new_checkpoint, unet_state_dict, additional_replacements=[meta_path], config=config ) resnet_0 = middle_blocks[0] attentions = middle_blocks[1] resnet_1 = middle_blocks[2] resnet_0_paths = renew_resnet_paths(resnet_0) assign_to_checkpoint(resnet_0_paths, new_checkpoint, unet_state_dict, config=config) resnet_1_paths = renew_resnet_paths(resnet_1) assign_to_checkpoint(resnet_1_paths, new_checkpoint, unet_state_dict, config=config) attentions_paths = renew_attention_paths(attentions) meta_path = {"old": "middle_block.1", "new": "mid_block.attentions.0"} assign_to_checkpoint( attentions_paths, new_checkpoint, unet_state_dict, additional_replacements=[meta_path], config=config ) for i in range(num_output_blocks): block_id = i // (config["layers_per_block"] + 1) layer_in_block_id = i % (config["layers_per_block"] + 1) output_block_layers = [shave_segments(name, 2) for name in output_blocks[i]] output_block_list = {} for layer in output_block_layers: layer_id, layer_name = layer.split(".")[0], shave_segments(layer, 1) if layer_id in output_block_list: output_block_list[layer_id].append(layer_name) else: output_block_list[layer_id] = [layer_name] if len(output_block_list) > 1: resnets = [key for key in output_blocks[i] if f"output_blocks.{i}.0" in key] attentions = [key for key in output_blocks[i] if f"output_blocks.{i}.1" in key] resnet_0_paths = renew_resnet_paths(resnets) paths = renew_resnet_paths(resnets) meta_path = {"old": f"output_blocks.{i}.0", "new": f"up_blocks.{block_id}.resnets.{layer_in_block_id}"} assign_to_checkpoint( paths, new_checkpoint, unet_state_dict, additional_replacements=[meta_path], config=config ) output_block_list = {k: sorted(v) for k, v in output_block_list.items()} if ["conv.bias", "conv.weight"] in output_block_list.values(): index = list(output_block_list.values()).index(["conv.bias", "conv.weight"]) new_checkpoint[f"up_blocks.{block_id}.upsamplers.0.conv.weight"] = unet_state_dict[ f"output_blocks.{i}.{index}.conv.weight" ] new_checkpoint[f"up_blocks.{block_id}.upsamplers.0.conv.bias"] = unet_state_dict[ f"output_blocks.{i}.{index}.conv.bias" ] # Clear attentions as they have been attributed above. if len(attentions) == 2: attentions = [] if len(attentions): paths = renew_attention_paths(attentions) meta_path = { "old": f"output_blocks.{i}.1", "new": f"up_blocks.{block_id}.attentions.{layer_in_block_id}", } assign_to_checkpoint( paths, new_checkpoint, unet_state_dict, additional_replacements=[meta_path], config=config ) else: resnet_0_paths = renew_resnet_paths(output_block_layers, n_shave_prefix_segments=1) for path in resnet_0_paths: old_path = ".".join(["output_blocks", str(i), path["old"]]) new_path = ".".join(["up_blocks", str(block_id), "resnets", str(layer_in_block_id), path["new"]]) new_checkpoint[new_path] = unet_state_dict[old_path] return new_checkpoint def convert_ldm_clip_checkpoint(checkpoint): from transformers import CLIPTextModel text_model = CLIPTextModel.from_pretrained("openai/clip-vit-large-patch14") keys = list(checkpoint.keys()) keys.remove("cond_stage_model.transformer.text_model.embeddings.position_ids") text_model_dict = {} for key in keys: if key.startswith("cond_stage_model.transformer"): text_model_dict[key[len("cond_stage_model.transformer.") :]] = checkpoint[key] text_model.load_state_dict(text_model_dict) return text_model def convert_ldm_clip_text_model(text_model, checkpoint): keys = list(checkpoint.keys()) keys.remove("cond_stage_model.transformer.text_model.embeddings.position_ids") text_model_dict = {} for key in keys: if key.startswith("cond_stage_model.transformer"): text_model_dict[key[len("cond_stage_model.transformer.") :]] = checkpoint[key] text_model.load_state_dict(text_model_dict) return text_model def conv_attn_to_linear(checkpoint): keys = list(checkpoint.keys()) attn_keys = ["query.weight", "key.weight", "value.weight"] for key in keys: if ".".join(key.split(".")[-2:]) in attn_keys: if checkpoint[key].ndim > 2: checkpoint[key] = checkpoint[key][:, :, 0, 0] elif "proj_attn.weight" in key: if checkpoint[key].ndim > 2: checkpoint[key] = checkpoint[key][:, :, 0] def convert_ldm_vae_checkpoint(checkpoint, config): # extract state dict for VAE vae_state_dict = {} vae_key = "first_stage_model." keys = list(checkpoint.keys()) for key in keys: if key.startswith(vae_key): vae_state_dict[key.replace(vae_key, "")] = checkpoint.get(key) new_checkpoint = {} new_checkpoint["encoder.conv_in.weight"] = vae_state_dict["encoder.conv_in.weight"] new_checkpoint["encoder.conv_in.bias"] = vae_state_dict["encoder.conv_in.bias"] new_checkpoint["encoder.conv_out.weight"] = vae_state_dict["encoder.conv_out.weight"] new_checkpoint["encoder.conv_out.bias"] = vae_state_dict["encoder.conv_out.bias"] new_checkpoint["encoder.conv_norm_out.weight"] = vae_state_dict["encoder.norm_out.weight"] new_checkpoint["encoder.conv_norm_out.bias"] = vae_state_dict["encoder.norm_out.bias"] new_checkpoint["decoder.conv_in.weight"] = vae_state_dict["decoder.conv_in.weight"] new_checkpoint["decoder.conv_in.bias"] = vae_state_dict["decoder.conv_in.bias"] new_checkpoint["decoder.conv_out.weight"] = vae_state_dict["decoder.conv_out.weight"] new_checkpoint["decoder.conv_out.bias"] = vae_state_dict["decoder.conv_out.bias"] new_checkpoint["decoder.conv_norm_out.weight"] = vae_state_dict["decoder.norm_out.weight"] new_checkpoint["decoder.conv_norm_out.bias"] = vae_state_dict["decoder.norm_out.bias"] new_checkpoint["quant_conv.weight"] = vae_state_dict["quant_conv.weight"] new_checkpoint["quant_conv.bias"] = vae_state_dict["quant_conv.bias"] new_checkpoint["post_quant_conv.weight"] = vae_state_dict["post_quant_conv.weight"] new_checkpoint["post_quant_conv.bias"] = vae_state_dict["post_quant_conv.bias"] # Retrieves the keys for the encoder down blocks only num_down_blocks = len({".".join(layer.split(".")[:3]) for layer in vae_state_dict if "encoder.down" in layer}) down_blocks = { layer_id: [key for key in vae_state_dict if f"down.{layer_id}" in key] for layer_id in range(num_down_blocks) } # Retrieves the keys for the decoder up blocks only num_up_blocks = len({".".join(layer.split(".")[:3]) for layer in vae_state_dict if "decoder.up" in layer}) up_blocks = { layer_id: [key for key in vae_state_dict if f"up.{layer_id}" in key] for layer_id in range(num_up_blocks) } for i in range(num_down_blocks): resnets = [key for key in down_blocks[i] if f"down.{i}" in key and f"down.{i}.downsample" not in key] if f"encoder.down.{i}.downsample.conv.weight" in vae_state_dict: new_checkpoint[f"encoder.down_blocks.{i}.downsamplers.0.conv.weight"] = vae_state_dict.pop( f"encoder.down.{i}.downsample.conv.weight" ) new_checkpoint[f"encoder.down_blocks.{i}.downsamplers.0.conv.bias"] = vae_state_dict.pop( f"encoder.down.{i}.downsample.conv.bias" ) paths = renew_vae_resnet_paths(resnets) meta_path = {"old": f"down.{i}.block", "new": f"down_blocks.{i}.resnets"} assign_to_checkpoint(paths, new_checkpoint, vae_state_dict, additional_replacements=[meta_path], config=config) mid_resnets = [key for key in vae_state_dict if "encoder.mid.block" in key] num_mid_res_blocks = 2 for i in range(1, num_mid_res_blocks + 1): resnets = [key for key in mid_resnets if f"encoder.mid.block_{i}" in key] paths = renew_vae_resnet_paths(resnets) meta_path = {"old": f"mid.block_{i}", "new": f"mid_block.resnets.{i - 1}"} assign_to_checkpoint(paths, new_checkpoint, vae_state_dict, additional_replacements=[meta_path], config=config) mid_attentions = [key for key in vae_state_dict if "encoder.mid.attn" in key] paths = renew_vae_attention_paths(mid_attentions) meta_path = {"old": "mid.attn_1", "new": "mid_block.attentions.0"} assign_to_checkpoint(paths, new_checkpoint, vae_state_dict, additional_replacements=[meta_path], config=config) conv_attn_to_linear(new_checkpoint) for i in range(num_up_blocks): block_id = num_up_blocks - 1 - i resnets = [ key for key in up_blocks[block_id] if f"up.{block_id}" in key and f"up.{block_id}.upsample" not in key ] if f"decoder.up.{block_id}.upsample.conv.weight" in vae_state_dict: new_checkpoint[f"decoder.up_blocks.{i}.upsamplers.0.conv.weight"] = vae_state_dict[ f"decoder.up.{block_id}.upsample.conv.weight" ] new_checkpoint[f"decoder.up_blocks.{i}.upsamplers.0.conv.bias"] = vae_state_dict[ f"decoder.up.{block_id}.upsample.conv.bias" ] paths = renew_vae_resnet_paths(resnets) meta_path = {"old": f"up.{block_id}.block", "new": f"up_blocks.{i}.resnets"} assign_to_checkpoint(paths, new_checkpoint, vae_state_dict, additional_replacements=[meta_path], config=config) mid_resnets = [key for key in vae_state_dict if "decoder.mid.block" in key] num_mid_res_blocks = 2 for i in range(1, num_mid_res_blocks + 1): resnets = [key for key in mid_resnets if f"decoder.mid.block_{i}" in key] paths = renew_vae_resnet_paths(resnets) meta_path = {"old": f"mid.block_{i}", "new": f"mid_block.resnets.{i - 1}"} assign_to_checkpoint(paths, new_checkpoint, vae_state_dict, additional_replacements=[meta_path], config=config) mid_attentions = [key for key in vae_state_dict if "decoder.mid.attn" in key] paths = renew_vae_attention_paths(mid_attentions) meta_path = {"old": "mid.attn_1", "new": "mid_block.attentions.0"} assign_to_checkpoint(paths, new_checkpoint, vae_state_dict, additional_replacements=[meta_path], config=config) conv_attn_to_linear(new_checkpoint) return new_checkpoint