1580158
/
automatic
mirror of https://github.com/vladmandic/automatic
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

cache diffusers model config

pull/3136/head
Vladimir Mandic 2024-05-14 12:54:34 -04:00
parent 4b4783db11
commit 76cbf11559
27 changed files with 295644 additions and 15 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

20
configs/sd15/feature_extractor/preprocessor_config.json Normal file
View File

@ -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
}

32
configs/sd15/model_index.json Normal file
View File

@ -0,0 +1,32 @@
{
"_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"
]
}

175
configs/sd15/safety_checker/config.json Normal file
View File

@ -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
}
}

13
configs/sd15/scheduler/scheduler_config.json Normal file
View File

@ -0,0 +1,13 @@
{
"_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
}

25
configs/sd15/text_encoder/config.json Normal file
View File

@ -0,0 +1,25 @@
{
"_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
}

48895
configs/sd15/tokenizer/merges.txt Normal file
View File

File diff suppressed because it is too large Load Diff

24
configs/sd15/tokenizer/special_tokens_map.json Normal file
View File

@ -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
}
}

34
configs/sd15/tokenizer/tokenizer_config.json Normal file
View File

@ -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": "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
}
}

49410
configs/sd15/tokenizer/vocab.json Normal file
View File

File diff suppressed because it is too large Load Diff

36
configs/sd15/unet/config.json Normal file
View File

@ -0,0 +1,36 @@
{
"_class_name": "UNet2DConditionModel",
"_diffusers_version": "0.6.0",
"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"
]
}

29
configs/sd15/vae/config.json Normal file
View File

@ -0,0 +1,29 @@
{
"_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"
]
}

34
configs/sdxl/model_index.json Normal file
View File

@ -0,0 +1,34 @@
{
"_class_name": "StableDiffusionXLPipeline",
"_diffusers_version": "0.19.0.dev0",
"force_zeros_for_empty_prompt": true,
"add_watermarker": null,
"scheduler": [
"diffusers",
"EulerDiscreteScheduler"
],
"text_encoder": [
"transformers",
"CLIPTextModel"
],
"text_encoder_2": [
"transformers",
"CLIPTextModelWithProjection"
],
"tokenizer": [
"transformers",
"CLIPTokenizer"
],
"tokenizer_2": [
"transformers",
"CLIPTokenizer"
],
"unet": [
"diffusers",
"UNet2DConditionModel"
],
"vae": [
"diffusers",
"AutoencoderKL"
]
}

18
configs/sdxl/scheduler/scheduler_config.json Normal file
View File

@ -0,0 +1,18 @@
{
"_class_name": "EulerDiscreteScheduler",
"_diffusers_version": "0.19.0.dev0",
"beta_end": 0.012,
"beta_schedule": "scaled_linear",
"beta_start": 0.00085,
"clip_sample": false,
"interpolation_type": "linear",
"num_train_timesteps": 1000,
"prediction_type": "epsilon",
"sample_max_value": 1.0,
"set_alpha_to_one": false,
"skip_prk_steps": true,
"steps_offset": 1,
"timestep_spacing": "leading",
"trained_betas": null,
"use_karras_sigmas": false
}

24
configs/sdxl/text_encoder/config.json Normal file
View File

@ -0,0 +1,24 @@
{
"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": "float16",
"transformers_version": "4.32.0.dev0",
"vocab_size": 49408
}

24
configs/sdxl/text_encoder_2/config.json Normal file
View File

@ -0,0 +1,24 @@
{
"architectures": [
"CLIPTextModelWithProjection"
],
"attention_dropout": 0.0,
"bos_token_id": 0,
"dropout": 0.0,
"eos_token_id": 2,
"hidden_act": "gelu",
"hidden_size": 1280,
"initializer_factor": 1.0,
"initializer_range": 0.02,
"intermediate_size": 5120,
"layer_norm_eps": 1e-05,
"max_position_embeddings": 77,
"model_type": "clip_text_model",
"num_attention_heads": 20,
"num_hidden_layers": 32,
"pad_token_id": 1,
"projection_dim": 1280,
"torch_dtype": "float16",
"transformers_version": "4.32.0.dev0",
"vocab_size": 49408
}

48895
configs/sdxl/tokenizer/merges.txt Normal file
View File

File diff suppressed because it is too large Load Diff

24
configs/sdxl/tokenizer/special_tokens_map.json Normal file
View File

@ -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
}
}

33
configs/sdxl/tokenizer/tokenizer_config.json Normal file
View File

@ -0,0 +1,33 @@
{
"add_prefix_space": false,
"bos_token": {
"__type": "AddedToken",
"content": "<|startoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"clean_up_tokenization_spaces": true,
"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,
"pad_token": "<|endoftext|>",
"tokenizer_class": "CLIPTokenizer",
"unk_token": {
"__type": "AddedToken",
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
}
}

49410
configs/sdxl/tokenizer/vocab.json Normal file
View File

File diff suppressed because it is too large Load Diff

48895
configs/sdxl/tokenizer_2/merges.txt Normal file
View File

File diff suppressed because it is too large Load Diff

24
configs/sdxl/tokenizer_2/special_tokens_map.json Normal file
View File

@ -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": "!",
"unk_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
}
}

33
configs/sdxl/tokenizer_2/tokenizer_config.json Normal file
View File

@ -0,0 +1,33 @@
{
"add_prefix_space": false,
"bos_token": {
"__type": "AddedToken",
"content": "<|startoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"clean_up_tokenization_spaces": true,
"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,
"pad_token": "!",
"tokenizer_class": "CLIPTokenizer",
"unk_token": {
"__type": "AddedToken",
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
}
}

49410
configs/sdxl/tokenizer_2/vocab.json Normal file
View File

File diff suppressed because it is too large Load Diff

69
configs/sdxl/unet/config.json Normal file
View File

@ -0,0 +1,69 @@
{
"_class_name": "UNet2DConditionModel",
"_diffusers_version": "0.19.0.dev0",
"act_fn": "silu",
"addition_embed_type": "text_time",
"addition_embed_type_num_heads": 64,
"addition_time_embed_dim": 256,
"attention_head_dim": [
5,
10,
20
],
"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": 2048,
"cross_attention_norm": null,
"down_block_types": [
"DownBlock2D",
"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,
"layers_per_block": 2,
"mid_block_only_cross_attention": null,
"mid_block_scale_factor": 1,
"mid_block_type": "UNetMidBlock2DCrossAttn",
"norm_eps": 1e-05,
"norm_num_groups": 32,
"num_attention_heads": null,
"num_class_embeds": null,
"only_cross_attention": false,
"out_channels": 4,
"projection_class_embeddings_input_dim": 2816,
"resnet_out_scale_factor": 1.0,
"resnet_skip_time_act": false,
"resnet_time_scale_shift": "default",
"sample_size": 128,
"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,
2,
10
],
"up_block_types": [
"CrossAttnUpBlock2D",
"CrossAttnUpBlock2D",
"UpBlock2D"
],
"upcast_attention": null,
"use_linear_projection": true
}

32
configs/sdxl/vae/config.json Normal file
View File

@ -0,0 +1,32 @@
{
"_class_name": "AutoencoderKL",
"_diffusers_version": "0.20.0.dev0",
"_name_or_path": "../sdxl-vae/",
"act_fn": "silu",
"block_out_channels": [
128,
256,
512,
512
],
"down_block_types": [
"DownEncoderBlock2D",
"DownEncoderBlock2D",
"DownEncoderBlock2D",
"DownEncoderBlock2D"
],
"force_upcast": true,
"in_channels": 3,
"latent_channels": 4,
"layers_per_block": 2,
"norm_num_groups": 32,
"out_channels": 3,
"sample_size": 1024,
"scaling_factor": 0.13025,
"up_block_types": [
"UpDecoderBlock2D",
"UpDecoderBlock2D",
"UpDecoderBlock2D",
"UpDecoderBlock2D"
]
}

40
modules/sd_models.py
View File

@ -800,20 +800,28 @@ def move_model(model, device=None, force=False):
devices.torch_gc()
def get_load_config(model_file, model_type):
yaml = os.path.splitext(model_file)[0] + '.yaml'
if os.path.exists(yaml):
return yaml
elif model_type == 'Stable Diffusion':
return 'configs/v1-inference.yaml'
elif model_type == 'Stable Diffusion XL':
return 'configs/sd_xl_base.yaml'
elif model_type == 'Stable Diffusion XL Refiner':
return 'configs/sd_xl_refiner.yaml'
elif model_type == 'Stable Diffusion 2':
return None # dont know if its eps or v so let diffusers sort it out
# return 'configs/v2-inference-512-base.yaml'
# return 'configs/v2-inference-768-v.yaml'
def get_load_config(model_file, model_type, config_type='yaml'):
if config_type == 'yaml':
yaml = os.path.splitext(model_file)[0] + '.yaml'
if os.path.exists(yaml):
return yaml
if model_type == 'Stable Diffusion':
return 'configs/v1-inference.yaml'
if model_type == 'Stable Diffusion XL':
return 'configs/sd_xl_base.yaml'
if model_type == 'Stable Diffusion XL Refiner':
return 'configs/sd_xl_refiner.yaml'
if model_type == 'Stable Diffusion 2':
return None # dont know if its eps or v so let diffusers sort it out
# return 'configs/v2-inference-512-base.yaml'
# return 'configs/v2-inference-768-v.yaml'
elif config_type == 'json':
if not shared.opts.diffuser_cache_config:
return None
if model_type == 'Stable Diffusion':
return 'configs/sd15'
if model_type == 'Stable Diffusion XL':
return 'configs/sdxl'
return None
@ -1063,7 +1071,9 @@ def load_diffuser(checkpoint_info=None, already_loaded_state_dict=None, timer=No
if shared.opts.diffusers_force_zeros:
diffusers_load_config['force_zeros_for_empty_prompt '] = shared.opts.diffusers_force_zeros
if diffusers_version < 28:
diffusers_load_config['original_config_file'] = get_load_config(checkpoint_info.path, model_type) # disabled as not used in diffusers 0.28
diffusers_load_config['original_config_file'] = get_load_config(checkpoint_info.path, model_type, config_type='yaml')
else:
diffusers_load_config['config'] = get_load_config(checkpoint_info.path, model_type, config_type='json')
if hasattr(pipeline, 'from_single_file'):
diffusers_load_config['use_safetensors'] = True
diffusers_load_config['cache_dir'] = shared.opts.hfcache_dir # use hfcache instead of diffusers dir as this is for config only in case of single-file

1
modules/shared.py
View File

@ -512,6 +512,7 @@ options_templates.update(options_section(('advanced', "Inference Settings"), {
options_templates.update(options_section(('diffusers', "Diffusers Settings"), {
"diffusers_pipeline": OptionInfo('Autodetect', 'Diffusers pipeline', gr.Dropdown, lambda: {"choices": list(shared_items.get_pipelines()) }),
"diffuser_cache_config": OptionInfo(True, "Use cached model config when available"),
"diffusers_move_base": OptionInfo(False, "Move base model to CPU when using refiner"),
"diffusers_move_unet": OptionInfo(False, "Move base model to CPU when using VAE"),
"diffusers_move_refiner": OptionInfo(False, "Move refiner model to CPU when not in use"),