license: cc-by-nc-4.0
pipeline_tag: text-to-image
library_name: diffusers
File information
The repository contains the following file information:
Filename: model_index.json Content: { "_class_name": "StableDiffusionPipeline", "_diffusers_version": "0.6.0", "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" ] }
Filename: preprocessor_config.json Content: { "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 }
Filename: config.json Content: { "_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 } }
Filename: config.json Content: { "_class_name": "AutoencoderKL", "_diffusers_version": "0.6.0", "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": 512, "up_block_types": [ "UpDecoderBlock2D", "UpDecoderBlock2D", "UpDecoderBlock2D", "UpDecoderBlock2D" ] }
Filename: vocab.json Content: Content of the file is larger than 50 KB, too long to display.
Filename: special_tokens_map.json Content: { "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 } }
Filename: tokenizer_config.json Content: { "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": "openai/clip-vit-large-patch14", "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 } }
Filename: config.json Content: { "_class_name": "UNet2DConditionModel", "_diffusers_version": "0.28.2", "_name_or_path": "/home/share/Loopfree/pretrained/loopfree-step4-sd15", "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, 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", "DownBlock2D" ], "downsample_padding": 1, "dropout": 0.0, "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": 2, "mid_block_only_cross_attention": null, "mid_block_scale_factor": 1, "mid_block_type": "UNetMidBlock2DCrossAttn", "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": 10000, "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", "reverse_transformer_layers_per_block": null, "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": [ "UpBlock2D", "CrossAttnUpBlock2D", "CrossAttnUpBlock2D", "CrossAttnUpBlock2D" ], "upcast_attention": false, "update_after_step": 0, "use_ema_warmup": false, "use_linear_projection": false }
Filename: scheduler_config.json Content: { "_class_name": "PNDMScheduler", "_diffusers_version": "0.6.0", "beta_end": 0.012, "beta_schedule": "scaled_linear", "beta_start": 0.00085, "num_train_timesteps": 1000, "set_alpha_to_one": false, "skip_prk_steps": true, "steps_offset": 1, "trained_betas": null, "clip_sample": false }
Filename: config.json Content: { "_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, "projection_dim": 768, "torch_dtype": "float32", "transformers_version": "4.22.0.dev0", "vocab_size": 49408 }
This model implements the method described in the paper One-Way Ticket:Time-Independent Unified Encoder for Distilling Text-to-Image Diffusion Models. Github repository: https://github.com/sen-mao/Loopfree