mirror of
https://github.com/invoke-ai/InvokeAI.git
synced 2026-01-15 09:18:00 -05:00
Compare commits
19 Commits
bria-UI
...
lstein/fea
| Author | SHA1 | Date | |
|---|---|---|---|
|
a81acacb2a | ||
|
|
f4f6296183 | ||
|
|
b9d8e196a4 | ||
|
|
2916d058d6 | ||
|
|
144673771c | ||
|
|
471dbf8668 | ||
|
|
9e097b6787 | ||
|
|
478154b930 | ||
|
|
03210bddcf | ||
|
|
32cdd42d2b | ||
|
|
63dbf38963 | ||
|
|
3487def2d8 | ||
|
|
4556343fa6 | ||
|
|
5daaaa3b70 | ||
|
|
7a9a1694a4 | ||
|
|
5b296d3c87 | ||
|
|
6af84434e0 | ||
|
|
5bde4eaa7a | ||
|
|
b5ec04f10c |
@@ -0,0 +1,42 @@
|
||||
{
|
||||
"_class_name": "ControlNetModel",
|
||||
"_diffusers_version": "0.16.0.dev0",
|
||||
"_name_or_path": "controlnet_v1_1/control_v11p_sd15_canny",
|
||||
"act_fn": "silu",
|
||||
"attention_head_dim": 8,
|
||||
"block_out_channels": [
|
||||
320,
|
||||
640,
|
||||
1280,
|
||||
1280
|
||||
],
|
||||
"class_embed_type": null,
|
||||
"conditioning_embedding_out_channels": [
|
||||
16,
|
||||
32,
|
||||
96,
|
||||
256
|
||||
],
|
||||
"controlnet_conditioning_channel_order": "rgb",
|
||||
"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,
|
||||
"num_class_embeds": null,
|
||||
"only_cross_attention": false,
|
||||
"projection_class_embeddings_input_dim": null,
|
||||
"resnet_time_scale_shift": "default",
|
||||
"upcast_attention": false,
|
||||
"use_linear_projection": false
|
||||
}
|
||||
@@ -0,0 +1,56 @@
|
||||
{
|
||||
"_class_name": "ControlNetModel",
|
||||
"_diffusers_version": "0.19.3",
|
||||
"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
|
||||
],
|
||||
"class_embed_type": null,
|
||||
"conditioning_channels": 3,
|
||||
"conditioning_embedding_out_channels": [
|
||||
16,
|
||||
32,
|
||||
96,
|
||||
256
|
||||
],
|
||||
"controlnet_conditioning_channel_order": "rgb",
|
||||
"cross_attention_dim": 2048,
|
||||
"down_block_types": [
|
||||
"DownBlock2D",
|
||||
"CrossAttnDownBlock2D",
|
||||
"CrossAttnDownBlock2D"
|
||||
],
|
||||
"downsample_padding": 1,
|
||||
"encoder_hid_dim": null,
|
||||
"encoder_hid_dim_type": null,
|
||||
"flip_sin_to_cos": true,
|
||||
"freq_shift": 0,
|
||||
"global_pool_conditions": false,
|
||||
"in_channels": 4,
|
||||
"layers_per_block": 2,
|
||||
"mid_block_scale_factor": 1,
|
||||
"norm_eps": 1e-05,
|
||||
"norm_num_groups": 32,
|
||||
"num_attention_heads": null,
|
||||
"num_class_embeds": null,
|
||||
"only_cross_attention": false,
|
||||
"projection_class_embeddings_input_dim": 2816,
|
||||
"resnet_time_scale_shift": "default",
|
||||
"transformer_layers_per_block": [
|
||||
1,
|
||||
2,
|
||||
10
|
||||
],
|
||||
"upcast_attention": null,
|
||||
"use_linear_projection": true
|
||||
}
|
||||
@@ -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
|
||||
}
|
||||
@@ -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"
|
||||
]
|
||||
}
|
||||
@@ -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
|
||||
}
|
||||
}
|
||||
@@ -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
|
||||
}
|
||||
@@ -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
|
||||
}
|
||||
File diff suppressed because it is too large
Load Diff
@@ -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
|
||||
}
|
||||
}
|
||||
@@ -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
|
||||
}
|
||||
}
|
||||
File diff suppressed because it is too large
Load Diff
@@ -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"
|
||||
]
|
||||
}
|
||||
@@ -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"
|
||||
]
|
||||
}
|
||||
@@ -0,0 +1,28 @@
|
||||
{
|
||||
"crop_size": {
|
||||
"height": 224,
|
||||
"width": 224
|
||||
},
|
||||
"do_center_crop": true,
|
||||
"do_convert_rgb": true,
|
||||
"do_normalize": true,
|
||||
"do_rescale": true,
|
||||
"do_resize": true,
|
||||
"feature_extractor_type": "CLIPFeatureExtractor",
|
||||
"image_mean": [
|
||||
0.48145466,
|
||||
0.4578275,
|
||||
0.40821073
|
||||
],
|
||||
"image_processor_type": "CLIPFeatureExtractor",
|
||||
"image_std": [
|
||||
0.26862954,
|
||||
0.26130258,
|
||||
0.27577711
|
||||
],
|
||||
"resample": 3,
|
||||
"rescale_factor": 0.00392156862745098,
|
||||
"size": {
|
||||
"shortest_edge": 224
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,33 @@
|
||||
{
|
||||
"_class_name": "StableDiffusionPipeline",
|
||||
"_diffusers_version": "0.18.0.dev0",
|
||||
"feature_extractor": [
|
||||
"transformers",
|
||||
"CLIPFeatureExtractor"
|
||||
],
|
||||
"requires_safety_checker": true,
|
||||
"safety_checker": [
|
||||
"stable_diffusion",
|
||||
"StableDiffusionSafetyChecker"
|
||||
],
|
||||
"scheduler": [
|
||||
"diffusers",
|
||||
"DPMSolverMultistepScheduler"
|
||||
],
|
||||
"text_encoder": [
|
||||
"transformers",
|
||||
"CLIPTextModel"
|
||||
],
|
||||
"tokenizer": [
|
||||
"transformers",
|
||||
"CLIPTokenizer"
|
||||
],
|
||||
"unet": [
|
||||
"diffusers",
|
||||
"UNet2DConditionModel"
|
||||
],
|
||||
"vae": [
|
||||
"diffusers",
|
||||
"AutoencoderKL"
|
||||
]
|
||||
}
|
||||
@@ -0,0 +1,168 @@
|
||||
{
|
||||
"_commit_hash": "cb41f3a270d63d454d385fc2e4f571c487c253c5",
|
||||
"_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,
|
||||
"begin_suppress_tokens": 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,
|
||||
"projection_dim": 512,
|
||||
"pruned_heads": {},
|
||||
"remove_invalid_values": false,
|
||||
"repetition_penalty": 1.0,
|
||||
"return_dict": true,
|
||||
"return_dict_in_generate": false,
|
||||
"sep_token_id": null,
|
||||
"suppress_tokens": 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": "4.30.2",
|
||||
"typical_p": 1.0,
|
||||
"use_bfloat16": false,
|
||||
"vocab_size": 49408
|
||||
},
|
||||
"torch_dtype": "float16",
|
||||
"transformers_version": null,
|
||||
"vision_config": {
|
||||
"_name_or_path": "",
|
||||
"add_cross_attention": false,
|
||||
"architectures": null,
|
||||
"attention_dropout": 0.0,
|
||||
"bad_words_ids": null,
|
||||
"begin_suppress_tokens": 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,
|
||||
"projection_dim": 512,
|
||||
"pruned_heads": {},
|
||||
"remove_invalid_values": false,
|
||||
"repetition_penalty": 1.0,
|
||||
"return_dict": true,
|
||||
"return_dict_in_generate": false,
|
||||
"sep_token_id": null,
|
||||
"suppress_tokens": 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": "4.30.2",
|
||||
"typical_p": 1.0,
|
||||
"use_bfloat16": false
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,26 @@
|
||||
{
|
||||
"_class_name": "DPMSolverMultistepScheduler",
|
||||
"_diffusers_version": "0.18.0.dev0",
|
||||
"algorithm_type": "dpmsolver++",
|
||||
"beta_end": 0.012,
|
||||
"beta_schedule": "scaled_linear",
|
||||
"beta_start": 0.00085,
|
||||
"clip_sample": false,
|
||||
"clip_sample_range": 1.0,
|
||||
"dynamic_thresholding_ratio": 0.995,
|
||||
"lambda_min_clipped": -Infinity,
|
||||
"lower_order_final": true,
|
||||
"num_train_timesteps": 1000,
|
||||
"prediction_type": "v_prediction",
|
||||
"rescale_betas_zero_snr": false,
|
||||
"sample_max_value": 1.0,
|
||||
"set_alpha_to_one": false,
|
||||
"solver_order": 2,
|
||||
"solver_type": "midpoint",
|
||||
"steps_offset": 1,
|
||||
"thresholding": false,
|
||||
"timestep_spacing": "leading",
|
||||
"trained_betas": null,
|
||||
"use_karras_sigmas": false,
|
||||
"variance_type": null
|
||||
}
|
||||
@@ -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": "float16",
|
||||
"transformers_version": "4.30.2",
|
||||
"vocab_size": 49408
|
||||
}
|
||||
File diff suppressed because it is too large
Load Diff
@@ -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
|
||||
}
|
||||
}
|
||||
@@ -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
|
||||
}
|
||||
}
|
||||
File diff suppressed because it is too large
Load Diff
@@ -0,0 +1,62 @@
|
||||
{
|
||||
"_class_name": "UNet2DConditionModel",
|
||||
"_diffusers_version": "0.18.0.dev0",
|
||||
"act_fn": "silu",
|
||||
"addition_embed_type": null,
|
||||
"addition_embed_type_num_heads": 64,
|
||||
"attention_head_dim": 8,
|
||||
"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,
|
||||
"down_block_types": [
|
||||
"CrossAttnDownBlock2D",
|
||||
"CrossAttnDownBlock2D",
|
||||
"CrossAttnDownBlock2D",
|
||||
"DownBlock2D"
|
||||
],
|
||||
"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": null,
|
||||
"resnet_out_scale_factor": 1.0,
|
||||
"resnet_skip_time_act": false,
|
||||
"resnet_time_scale_shift": "default",
|
||||
"sample_size": 96,
|
||||
"time_cond_proj_dim": null,
|
||||
"time_embedding_act_fn": null,
|
||||
"time_embedding_dim": null,
|
||||
"time_embedding_type": "positional",
|
||||
"timestep_post_act": null,
|
||||
"up_block_types": [
|
||||
"UpBlock2D",
|
||||
"CrossAttnUpBlock2D",
|
||||
"CrossAttnUpBlock2D",
|
||||
"CrossAttnUpBlock2D"
|
||||
],
|
||||
"upcast_attention": null,
|
||||
"use_linear_projection": false
|
||||
}
|
||||
@@ -0,0 +1,30 @@
|
||||
{
|
||||
"_class_name": "AutoencoderKL",
|
||||
"_diffusers_version": "0.18.0.dev0",
|
||||
"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": 768,
|
||||
"scaling_factor": 0.18215,
|
||||
"up_block_types": [
|
||||
"UpDecoderBlock2D",
|
||||
"UpDecoderBlock2D",
|
||||
"UpDecoderBlock2D",
|
||||
"UpDecoderBlock2D"
|
||||
]
|
||||
}
|
||||
@@ -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
|
||||
}
|
||||
@@ -0,0 +1,33 @@
|
||||
{
|
||||
"_class_name": "StableDiffusionPipeline",
|
||||
"_diffusers_version": "0.8.0",
|
||||
"feature_extractor": [
|
||||
"transformers",
|
||||
"CLIPImageProcessor"
|
||||
],
|
||||
"requires_safety_checker": false,
|
||||
"safety_checker": [
|
||||
null,
|
||||
null
|
||||
],
|
||||
"scheduler": [
|
||||
"diffusers",
|
||||
"DDIMScheduler"
|
||||
],
|
||||
"text_encoder": [
|
||||
"transformers",
|
||||
"CLIPTextModel"
|
||||
],
|
||||
"tokenizer": [
|
||||
"transformers",
|
||||
"CLIPTokenizer"
|
||||
],
|
||||
"unet": [
|
||||
"diffusers",
|
||||
"UNet2DConditionModel"
|
||||
],
|
||||
"vae": [
|
||||
"diffusers",
|
||||
"AutoencoderKL"
|
||||
]
|
||||
}
|
||||
@@ -0,0 +1,14 @@
|
||||
{
|
||||
"_class_name": "DDIMScheduler",
|
||||
"_diffusers_version": "0.8.0",
|
||||
"beta_end": 0.012,
|
||||
"beta_schedule": "scaled_linear",
|
||||
"beta_start": 0.00085,
|
||||
"clip_sample": false,
|
||||
"num_train_timesteps": 1000,
|
||||
"prediction_type": "v_prediction",
|
||||
"set_alpha_to_one": false,
|
||||
"skip_prk_steps": true,
|
||||
"steps_offset": 1,
|
||||
"trained_betas": null
|
||||
}
|
||||
@@ -0,0 +1,25 @@
|
||||
{
|
||||
"_name_or_path": "hf-models/stable-diffusion-v2-768x768/text_encoder",
|
||||
"architectures": [
|
||||
"CLIPTextModel"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 0,
|
||||
"dropout": 0.0,
|
||||
"eos_token_id": 2,
|
||||
"hidden_act": "gelu",
|
||||
"hidden_size": 1024,
|
||||
"initializer_factor": 1.0,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 4096,
|
||||
"layer_norm_eps": 1e-05,
|
||||
"max_position_embeddings": 77,
|
||||
"model_type": "clip_text_model",
|
||||
"num_attention_heads": 16,
|
||||
"num_hidden_layers": 23,
|
||||
"pad_token_id": 1,
|
||||
"projection_dim": 512,
|
||||
"torch_dtype": "float32",
|
||||
"transformers_version": "4.25.0.dev0",
|
||||
"vocab_size": 49408
|
||||
}
|
||||
File diff suppressed because it is too large
Load Diff
@@ -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
|
||||
}
|
||||
}
|
||||
@@ -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": "hf-models/stable-diffusion-v2-768x768/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
|
||||
}
|
||||
}
|
||||
File diff suppressed because it is too large
Load Diff
@@ -0,0 +1,46 @@
|
||||
{
|
||||
"_class_name": "UNet2DConditionModel",
|
||||
"_diffusers_version": "0.10.0.dev0",
|
||||
"act_fn": "silu",
|
||||
"attention_head_dim": [
|
||||
5,
|
||||
10,
|
||||
20,
|
||||
20
|
||||
],
|
||||
"block_out_channels": [
|
||||
320,
|
||||
640,
|
||||
1280,
|
||||
1280
|
||||
],
|
||||
"center_input_sample": false,
|
||||
"cross_attention_dim": 1024,
|
||||
"down_block_types": [
|
||||
"CrossAttnDownBlock2D",
|
||||
"CrossAttnDownBlock2D",
|
||||
"CrossAttnDownBlock2D",
|
||||
"DownBlock2D"
|
||||
],
|
||||
"downsample_padding": 1,
|
||||
"dual_cross_attention": false,
|
||||
"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,
|
||||
"num_class_embeds": null,
|
||||
"only_cross_attention": false,
|
||||
"out_channels": 4,
|
||||
"sample_size": 96,
|
||||
"up_block_types": [
|
||||
"UpBlock2D",
|
||||
"CrossAttnUpBlock2D",
|
||||
"CrossAttnUpBlock2D",
|
||||
"CrossAttnUpBlock2D"
|
||||
],
|
||||
"use_linear_projection": true,
|
||||
"upcast_attention": true
|
||||
}
|
||||
@@ -0,0 +1,30 @@
|
||||
{
|
||||
"_class_name": "AutoencoderKL",
|
||||
"_diffusers_version": "0.8.0",
|
||||
"_name_or_path": "hf-models/stable-diffusion-v2-768x768/vae",
|
||||
"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": 768,
|
||||
"up_block_types": [
|
||||
"UpDecoderBlock2D",
|
||||
"UpDecoderBlock2D",
|
||||
"UpDecoderBlock2D",
|
||||
"UpDecoderBlock2D"
|
||||
]
|
||||
}
|
||||
@@ -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"
|
||||
]
|
||||
}
|
||||
@@ -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
|
||||
}
|
||||
@@ -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
|
||||
}
|
||||
@@ -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
|
||||
}
|
||||
File diff suppressed because it is too large
Load Diff
@@ -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
|
||||
}
|
||||
}
|
||||
@@ -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
|
||||
}
|
||||
}
|
||||
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
@@ -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
|
||||
}
|
||||
}
|
||||
@@ -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
|
||||
}
|
||||
}
|
||||
File diff suppressed because it is too large
Load Diff
@@ -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
|
||||
}
|
||||
@@ -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"
|
||||
]
|
||||
}
|
||||
@@ -0,0 +1,31 @@
|
||||
{
|
||||
"_class_name": "AutoencoderKL",
|
||||
"_diffusers_version": "0.19.0.dev0",
|
||||
"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"
|
||||
]
|
||||
}
|
||||
@@ -0,0 +1,31 @@
|
||||
{
|
||||
"_class_name": "AutoencoderKL",
|
||||
"_diffusers_version": "0.19.0.dev0",
|
||||
"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"
|
||||
]
|
||||
}
|
||||
@@ -0,0 +1,31 @@
|
||||
{
|
||||
"_class_name": "AutoencoderKL",
|
||||
"_diffusers_version": "0.19.0.dev0",
|
||||
"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"
|
||||
]
|
||||
}
|
||||
@@ -0,0 +1,35 @@
|
||||
{
|
||||
"_class_name": "StableDiffusionXLImg2ImgPipeline",
|
||||
"_diffusers_version": "0.19.0.dev0",
|
||||
"force_zeros_for_empty_prompt": false,
|
||||
"add_watermarker": null,
|
||||
"requires_aesthetics_score": true,
|
||||
"scheduler": [
|
||||
"diffusers",
|
||||
"EulerDiscreteScheduler"
|
||||
],
|
||||
"text_encoder": [
|
||||
null,
|
||||
null
|
||||
],
|
||||
"text_encoder_2": [
|
||||
"transformers",
|
||||
"CLIPTextModelWithProjection"
|
||||
],
|
||||
"tokenizer": [
|
||||
null,
|
||||
null
|
||||
],
|
||||
"tokenizer_2": [
|
||||
"transformers",
|
||||
"CLIPTokenizer"
|
||||
],
|
||||
"unet": [
|
||||
"diffusers",
|
||||
"UNet2DConditionModel"
|
||||
],
|
||||
"vae": [
|
||||
"diffusers",
|
||||
"AutoencoderKL"
|
||||
]
|
||||
}
|
||||
@@ -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
|
||||
}
|
||||
@@ -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
|
||||
}
|
||||
File diff suppressed because it is too large
Load Diff
@@ -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
|
||||
}
|
||||
}
|
||||
@@ -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
|
||||
}
|
||||
}
|
||||
File diff suppressed because it is too large
Load Diff
@@ -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": [
|
||||
6,
|
||||
12,
|
||||
24,
|
||||
24
|
||||
],
|
||||
"block_out_channels": [
|
||||
384,
|
||||
768,
|
||||
1536,
|
||||
1536
|
||||
],
|
||||
"center_input_sample": false,
|
||||
"class_embed_type": null,
|
||||
"class_embeddings_concat": false,
|
||||
"conv_in_kernel": 3,
|
||||
"conv_out_kernel": 3,
|
||||
"cross_attention_dim": 1280,
|
||||
"cross_attention_norm": null,
|
||||
"down_block_types": [
|
||||
"DownBlock2D",
|
||||
"CrossAttnDownBlock2D",
|
||||
"CrossAttnDownBlock2D",
|
||||
"DownBlock2D"
|
||||
],
|
||||
"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": 2560,
|
||||
"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": 4,
|
||||
"up_block_types": [
|
||||
"UpBlock2D",
|
||||
"CrossAttnUpBlock2D",
|
||||
"CrossAttnUpBlock2D",
|
||||
"UpBlock2D"
|
||||
],
|
||||
"upcast_attention": null,
|
||||
"use_linear_projection": true
|
||||
}
|
||||
@@ -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"
|
||||
]
|
||||
}
|
||||
@@ -0,0 +1,31 @@
|
||||
{
|
||||
"_class_name": "AutoencoderKL",
|
||||
"_diffusers_version": "0.19.0.dev0",
|
||||
"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"
|
||||
]
|
||||
}
|
||||
@@ -1,10 +1,12 @@
|
||||
# Copyright (c) 2024, Lincoln D. Stein and the InvokeAI Development Team
|
||||
"""Class for ControlNet model loading in InvokeAI."""
|
||||
|
||||
from pathlib import Path
|
||||
from typing import Optional
|
||||
|
||||
from diffusers import ControlNetModel
|
||||
|
||||
import invokeai.backend.assets.model_base_conf_files as conf_file_cache
|
||||
from invokeai.backend.model_manager import (
|
||||
AnyModel,
|
||||
AnyModelConfig,
|
||||
@@ -46,9 +48,20 @@ class ControlNetLoader(GenericDiffusersLoader):
|
||||
config: AnyModelConfig,
|
||||
submodel_type: Optional[SubModelType] = None,
|
||||
) -> AnyModel:
|
||||
config_dirs = {
|
||||
BaseModelType.StableDiffusion1: "controlnet_sd15",
|
||||
BaseModelType.StableDiffusionXL: "controlnet_sdxl",
|
||||
}
|
||||
try:
|
||||
config_dir = config_dirs[config.base]
|
||||
except KeyError:
|
||||
raise Exception(f"No configuration template known for controlnet model with base={config.base}")
|
||||
|
||||
if isinstance(config, ControlNetCheckpointConfig):
|
||||
return ControlNetModel.from_single_file(
|
||||
config.path,
|
||||
config=Path(conf_file_cache.__path__[0], config_dir).as_posix(),
|
||||
local_files_only=True,
|
||||
torch_dtype=self._torch_dtype,
|
||||
)
|
||||
else:
|
||||
|
||||
@@ -11,6 +11,7 @@ from diffusers import (
|
||||
StableDiffusionXLPipeline,
|
||||
)
|
||||
|
||||
import invokeai.backend.assets.model_base_conf_files as conf_file_cache
|
||||
from invokeai.backend.model_manager import (
|
||||
AnyModel,
|
||||
AnyModelConfig,
|
||||
@@ -18,6 +19,7 @@ from invokeai.backend.model_manager import (
|
||||
ModelFormat,
|
||||
ModelType,
|
||||
ModelVariantType,
|
||||
SchedulerPredictionType,
|
||||
SubModelType,
|
||||
)
|
||||
from invokeai.backend.model_manager.config import (
|
||||
@@ -106,11 +108,33 @@ class StableDiffusionDiffusersModel(GenericDiffusersLoader):
|
||||
ModelVariantType.Normal: StableDiffusionXLPipeline,
|
||||
},
|
||||
}
|
||||
config_dirs = {
|
||||
BaseModelType.StableDiffusion1: {
|
||||
SchedulerPredictionType.Epsilon: "stable-diffusion-1.5-epsilon",
|
||||
SchedulerPredictionType.VPrediction: "stable-diffusion-1.5-v_prediction",
|
||||
},
|
||||
BaseModelType.StableDiffusion2: {
|
||||
SchedulerPredictionType.VPrediction: "stable-diffusion-2.0-v_prediction",
|
||||
},
|
||||
BaseModelType.StableDiffusionXL: {
|
||||
SchedulerPredictionType.Epsilon: "stable-diffusion-xl-base-1.0",
|
||||
},
|
||||
BaseModelType.StableDiffusionXLRefiner: {
|
||||
SchedulerPredictionType.Epsilon: "stable-diffusion-xl-refiner-1.0",
|
||||
},
|
||||
}
|
||||
|
||||
assert isinstance(config, MainCheckpointConfig)
|
||||
try:
|
||||
load_class = load_classes[config.base][config.variant]
|
||||
except KeyError as e:
|
||||
raise Exception(f"No diffusers pipeline known for base={config.base}, variant={config.variant}") from e
|
||||
try:
|
||||
config_dir = config_dirs[config.base][config.prediction_type]
|
||||
except KeyError as e:
|
||||
raise Exception(
|
||||
f"No configuration template known for base={config.base}, prediction_type={config.prediction_type}"
|
||||
) from e
|
||||
|
||||
# Without SilenceWarnings we get log messages like this:
|
||||
# site-packages/huggingface_hub/file_download.py:1132: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`.
|
||||
@@ -120,8 +144,17 @@ class StableDiffusionDiffusersModel(GenericDiffusersLoader):
|
||||
# Some weights of the model checkpoint were not used when initializing CLIPTextModelWithProjection:
|
||||
# ['text_model.embeddings.position_ids']
|
||||
|
||||
original_config_file = self._app_config.legacy_conf_path / config.config_path
|
||||
|
||||
with SilenceWarnings():
|
||||
pipeline = load_class.from_single_file(config.path, torch_dtype=self._torch_dtype)
|
||||
pipeline = load_class.from_single_file(
|
||||
config.path,
|
||||
config=Path(conf_file_cache.__path__[0], config_dir).as_posix(),
|
||||
original_config=original_config_file,
|
||||
torch_dtype=self._torch_dtype,
|
||||
local_files_only=True,
|
||||
kwargs={"load_safety_checker": False},
|
||||
)
|
||||
|
||||
if not submodel_type:
|
||||
return pipeline
|
||||
|
||||
@@ -684,6 +684,7 @@ class ControlNetCheckpointProbe(CheckpointProbeBase):
|
||||
"controlnet_mid_block.bias",
|
||||
"input_blocks.2.1.transformer_blocks.0.attn2.to_k.weight",
|
||||
"down_blocks.1.attentions.0.transformer_blocks.0.attn2.to_k.weight",
|
||||
"input_blocks.7.0.emb_layers.1.down",
|
||||
):
|
||||
if key_name not in checkpoint:
|
||||
continue
|
||||
|
||||
@@ -148,6 +148,7 @@ version = { attr = "invokeai.version.__version__" }
|
||||
"invokeai.version*",
|
||||
"invokeai.generator*",
|
||||
"invokeai.backend*",
|
||||
"invokeai.backend.assets.model_base_conf_files*",
|
||||
"invokeai.frontend*",
|
||||
"invokeai.frontend.web.dist*",
|
||||
"invokeai.frontend.web.static*",
|
||||
@@ -164,6 +165,7 @@ version = { attr = "invokeai.version.__version__" }
|
||||
"*.png",
|
||||
]
|
||||
"invokeai.assets.fonts" = ["**/*.ttf"]
|
||||
"invokeai.backend.assets.model_base_conf_files" = ["**/*.json", "**/*.txt"]
|
||||
"invokeai.backend" = ["**.png", "**/*.icc"]
|
||||
"invokeai.configs" = ["*.example", "**/*.yaml", "*.txt"]
|
||||
"invokeai.frontend.web.dist" = ["**"]
|
||||
|
||||
Reference in New Issue
Block a user