theluyuan/DiffSynth-Studio
1
0
Fork 0
mirror of https://github.com/modelscope/DiffSynth-Studio.git synced 2026-03-21 16:18:13 +00:00
Code Issues Packages Projects Releases Wiki Activity

update model loader

Browse Source
This commit is contained in:
Artiprocher
2024-10-08 16:46:44 +08:00
parent 892f80c265
commit ec352cfce2
4 changed files with 189 additions and 90 deletions
Download Patch File Download Diff File Expand all files Collapse all files

202
diffsynth/configs/model_config.py
View File

@@ -353,47 +353,67 @@ preset_models_on_modelscope = {
("Damo_XR_Lab/cv_rife_video-frame-interpolation", "flownet.pkl", "models/RIFE"),
],
# Qwen Prompt
"QwenPrompt": [
("qwen/Qwen2-1.5B-Instruct", "config.json", "models/QwenPrompt/qwen2-1.5b-instruct"),
("qwen/Qwen2-1.5B-Instruct", "generation_config.json", "models/QwenPrompt/qwen2-1.5b-instruct"),
("qwen/Qwen2-1.5B-Instruct", "model.safetensors", "models/QwenPrompt/qwen2-1.5b-instruct"),
("qwen/Qwen2-1.5B-Instruct", "special_tokens_map.json", "models/QwenPrompt/qwen2-1.5b-instruct"),
("qwen/Qwen2-1.5B-Instruct", "tokenizer.json", "models/QwenPrompt/qwen2-1.5b-instruct"),
("qwen/Qwen2-1.5B-Instruct", "tokenizer_config.json", "models/QwenPrompt/qwen2-1.5b-instruct"),
("qwen/Qwen2-1.5B-Instruct", "merges.txt", "models/QwenPrompt/qwen2-1.5b-instruct"),
("qwen/Qwen2-1.5B-Instruct", "vocab.json", "models/QwenPrompt/qwen2-1.5b-instruct"),
],
"QwenPrompt": {
"file_list": [
("qwen/Qwen2-1.5B-Instruct", "config.json", "models/QwenPrompt/qwen2-1.5b-instruct"),
("qwen/Qwen2-1.5B-Instruct", "generation_config.json", "models/QwenPrompt/qwen2-1.5b-instruct"),
("qwen/Qwen2-1.5B-Instruct", "model.safetensors", "models/QwenPrompt/qwen2-1.5b-instruct"),
("qwen/Qwen2-1.5B-Instruct", "special_tokens_map.json", "models/QwenPrompt/qwen2-1.5b-instruct"),
("qwen/Qwen2-1.5B-Instruct", "tokenizer.json", "models/QwenPrompt/qwen2-1.5b-instruct"),
("qwen/Qwen2-1.5B-Instruct", "tokenizer_config.json", "models/QwenPrompt/qwen2-1.5b-instruct"),
("qwen/Qwen2-1.5B-Instruct", "merges.txt", "models/QwenPrompt/qwen2-1.5b-instruct"),
("qwen/Qwen2-1.5B-Instruct", "vocab.json", "models/QwenPrompt/qwen2-1.5b-instruct"),
],
"load_path": [
"models/QwenPrompt/qwen2-1.5b-instruct",
],
},
# Beautiful Prompt
"BeautifulPrompt": [
("AI-ModelScope/pai-bloom-1b1-text2prompt-sd", "config.json", "models/BeautifulPrompt/pai-bloom-1b1-text2prompt-sd"),
("AI-ModelScope/pai-bloom-1b1-text2prompt-sd", "generation_config.json", "models/BeautifulPrompt/pai-bloom-1b1-text2prompt-sd"),
("AI-ModelScope/pai-bloom-1b1-text2prompt-sd", "model.safetensors", "models/BeautifulPrompt/pai-bloom-1b1-text2prompt-sd"),
("AI-ModelScope/pai-bloom-1b1-text2prompt-sd", "special_tokens_map.json", "models/BeautifulPrompt/pai-bloom-1b1-text2prompt-sd"),
("AI-ModelScope/pai-bloom-1b1-text2prompt-sd", "tokenizer.json", "models/BeautifulPrompt/pai-bloom-1b1-text2prompt-sd"),
("AI-ModelScope/pai-bloom-1b1-text2prompt-sd", "tokenizer_config.json", "models/BeautifulPrompt/pai-bloom-1b1-text2prompt-sd"),
],
"BeautifulPrompt": {
"file_list": [
("AI-ModelScope/pai-bloom-1b1-text2prompt-sd", "config.json", "models/BeautifulPrompt/pai-bloom-1b1-text2prompt-sd"),
("AI-ModelScope/pai-bloom-1b1-text2prompt-sd", "generation_config.json", "models/BeautifulPrompt/pai-bloom-1b1-text2prompt-sd"),
("AI-ModelScope/pai-bloom-1b1-text2prompt-sd", "model.safetensors", "models/BeautifulPrompt/pai-bloom-1b1-text2prompt-sd"),
("AI-ModelScope/pai-bloom-1b1-text2prompt-sd", "special_tokens_map.json", "models/BeautifulPrompt/pai-bloom-1b1-text2prompt-sd"),
("AI-ModelScope/pai-bloom-1b1-text2prompt-sd", "tokenizer.json", "models/BeautifulPrompt/pai-bloom-1b1-text2prompt-sd"),
("AI-ModelScope/pai-bloom-1b1-text2prompt-sd", "tokenizer_config.json", "models/BeautifulPrompt/pai-bloom-1b1-text2prompt-sd"),
],
"load_path": [
"models/BeautifulPrompt/pai-bloom-1b1-text2prompt-sd",
],
},
# Omost prompt
"OmostPrompt":[
("Omost/omost-llama-3-8b-4bits", "model-00001-of-00002.safetensors", "models/OmostPrompt/omost-llama-3-8b-4bits"),
("Omost/omost-llama-3-8b-4bits", "model-00002-of-00002.safetensors", "models/OmostPrompt/omost-llama-3-8b-4bits"),
("Omost/omost-llama-3-8b-4bits", "tokenizer.json", "models/OmostPrompt/omost-llama-3-8b-4bits"),
("Omost/omost-llama-3-8b-4bits", "tokenizer_config.json", "models/OmostPrompt/omost-llama-3-8b-4bits"),
("Omost/omost-llama-3-8b-4bits", "config.json", "models/OmostPrompt/omost-llama-3-8b-4bits"),
("Omost/omost-llama-3-8b-4bits", "generation_config.json", "models/OmostPrompt/omost-llama-3-8b-4bits"),
("Omost/omost-llama-3-8b-4bits", "model.safetensors.index.json", "models/OmostPrompt/omost-llama-3-8b-4bits"),
("Omost/omost-llama-3-8b-4bits", "special_tokens_map.json", "models/OmostPrompt/omost-llama-3-8b-4bits"),
],
"OmostPrompt": {
"file_list": [
("Omost/omost-llama-3-8b-4bits", "model-00001-of-00002.safetensors", "models/OmostPrompt/omost-llama-3-8b-4bits"),
("Omost/omost-llama-3-8b-4bits", "model-00002-of-00002.safetensors", "models/OmostPrompt/omost-llama-3-8b-4bits"),
("Omost/omost-llama-3-8b-4bits", "tokenizer.json", "models/OmostPrompt/omost-llama-3-8b-4bits"),
("Omost/omost-llama-3-8b-4bits", "tokenizer_config.json", "models/OmostPrompt/omost-llama-3-8b-4bits"),
("Omost/omost-llama-3-8b-4bits", "config.json", "models/OmostPrompt/omost-llama-3-8b-4bits"),
("Omost/omost-llama-3-8b-4bits", "generation_config.json", "models/OmostPrompt/omost-llama-3-8b-4bits"),
("Omost/omost-llama-3-8b-4bits", "model.safetensors.index.json", "models/OmostPrompt/omost-llama-3-8b-4bits"),
("Omost/omost-llama-3-8b-4bits", "special_tokens_map.json", "models/OmostPrompt/omost-llama-3-8b-4bits"),
],
"load_path": [
"models/OmostPrompt/omost-llama-3-8b-4bits",
],
},
# Translator
"opus-mt-zh-en": [
("moxying/opus-mt-zh-en", "config.json", "models/translator/opus-mt-zh-en"),
("moxying/opus-mt-zh-en", "generation_config.json", "models/translator/opus-mt-zh-en"),
("moxying/opus-mt-zh-en", "metadata.json", "models/translator/opus-mt-zh-en"),
("moxying/opus-mt-zh-en", "pytorch_model.bin", "models/translator/opus-mt-zh-en"),
("moxying/opus-mt-zh-en", "source.spm", "models/translator/opus-mt-zh-en"),
("moxying/opus-mt-zh-en", "target.spm", "models/translator/opus-mt-zh-en"),
("moxying/opus-mt-zh-en", "tokenizer_config.json", "models/translator/opus-mt-zh-en"),
("moxying/opus-mt-zh-en", "vocab.json", "models/translator/opus-mt-zh-en"),
],
"opus-mt-zh-en": {
"file_list": [
("moxying/opus-mt-zh-en", "config.json", "models/translator/opus-mt-zh-en"),
("moxying/opus-mt-zh-en", "generation_config.json", "models/translator/opus-mt-zh-en"),
("moxying/opus-mt-zh-en", "metadata.json", "models/translator/opus-mt-zh-en"),
("moxying/opus-mt-zh-en", "pytorch_model.bin", "models/translator/opus-mt-zh-en"),
("moxying/opus-mt-zh-en", "source.spm", "models/translator/opus-mt-zh-en"),
("moxying/opus-mt-zh-en", "target.spm", "models/translator/opus-mt-zh-en"),
("moxying/opus-mt-zh-en", "tokenizer_config.json", "models/translator/opus-mt-zh-en"),
("moxying/opus-mt-zh-en", "vocab.json", "models/translator/opus-mt-zh-en"),
],
"load_path": [
"models/translator/opus-mt-zh-en",
],
},
# IP-Adapter
"IP-Adapter-SD": [
("AI-ModelScope/IP-Adapter", "models/image_encoder/model.safetensors", "models/IpAdapter/stable_diffusion/image_encoder"),
@@ -404,32 +424,64 @@ preset_models_on_modelscope = {
("AI-ModelScope/IP-Adapter", "sdxl_models/ip-adapter_sdxl.bin", "models/IpAdapter/stable_diffusion_xl"),
],
# Kolors
"Kolors": [
("Kwai-Kolors/Kolors", "text_encoder/config.json", "models/kolors/Kolors/text_encoder"),
("Kwai-Kolors/Kolors", "text_encoder/pytorch_model.bin.index.json", "models/kolors/Kolors/text_encoder"),
("Kwai-Kolors/Kolors", "text_encoder/pytorch_model-00001-of-00007.bin", "models/kolors/Kolors/text_encoder"),
("Kwai-Kolors/Kolors", "text_encoder/pytorch_model-00002-of-00007.bin", "models/kolors/Kolors/text_encoder"),
("Kwai-Kolors/Kolors", "text_encoder/pytorch_model-00003-of-00007.bin", "models/kolors/Kolors/text_encoder"),
("Kwai-Kolors/Kolors", "text_encoder/pytorch_model-00004-of-00007.bin", "models/kolors/Kolors/text_encoder"),
("Kwai-Kolors/Kolors", "text_encoder/pytorch_model-00005-of-00007.bin", "models/kolors/Kolors/text_encoder"),
("Kwai-Kolors/Kolors", "text_encoder/pytorch_model-00006-of-00007.bin", "models/kolors/Kolors/text_encoder"),
("Kwai-Kolors/Kolors", "text_encoder/pytorch_model-00007-of-00007.bin", "models/kolors/Kolors/text_encoder"),
("Kwai-Kolors/Kolors", "unet/diffusion_pytorch_model.safetensors", "models/kolors/Kolors/unet"),
("Kwai-Kolors/Kolors", "vae/diffusion_pytorch_model.safetensors", "models/kolors/Kolors/vae"),
],
"Kolors": {
"file_list": [
("Kwai-Kolors/Kolors", "text_encoder/config.json", "models/kolors/Kolors/text_encoder"),
("Kwai-Kolors/Kolors", "text_encoder/pytorch_model.bin.index.json", "models/kolors/Kolors/text_encoder"),
("Kwai-Kolors/Kolors", "text_encoder/pytorch_model-00001-of-00007.bin", "models/kolors/Kolors/text_encoder"),
("Kwai-Kolors/Kolors", "text_encoder/pytorch_model-00002-of-00007.bin", "models/kolors/Kolors/text_encoder"),
("Kwai-Kolors/Kolors", "text_encoder/pytorch_model-00003-of-00007.bin", "models/kolors/Kolors/text_encoder"),
("Kwai-Kolors/Kolors", "text_encoder/pytorch_model-00004-of-00007.bin", "models/kolors/Kolors/text_encoder"),
("Kwai-Kolors/Kolors", "text_encoder/pytorch_model-00005-of-00007.bin", "models/kolors/Kolors/text_encoder"),
("Kwai-Kolors/Kolors", "text_encoder/pytorch_model-00006-of-00007.bin", "models/kolors/Kolors/text_encoder"),
("Kwai-Kolors/Kolors", "text_encoder/pytorch_model-00007-of-00007.bin", "models/kolors/Kolors/text_encoder"),
("Kwai-Kolors/Kolors", "unet/diffusion_pytorch_model.safetensors", "models/kolors/Kolors/unet"),
("Kwai-Kolors/Kolors", "vae/diffusion_pytorch_model.safetensors", "models/kolors/Kolors/vae"),
],
"load_path": [
"models/kolors/Kolors/text_encoder",
"models/kolors/Kolors/unet/diffusion_pytorch_model.safetensors",
"models/kolors/Kolors/vae/diffusion_pytorch_model.safetensors",
],
},
"SDXL-vae-fp16-fix": [
("AI-ModelScope/sdxl-vae-fp16-fix", "diffusion_pytorch_model.safetensors", "models/sdxl-vae-fp16-fix")
],
# FLUX
"FLUX.1-dev": [
("AI-ModelScope/FLUX.1-dev", "text_encoder/model.safetensors", "models/FLUX/FLUX.1-dev/text_encoder"),
("AI-ModelScope/FLUX.1-dev", "text_encoder_2/config.json", "models/FLUX/FLUX.1-dev/text_encoder_2"),
("AI-ModelScope/FLUX.1-dev", "text_encoder_2/model-00001-of-00002.safetensors", "models/FLUX/FLUX.1-dev/text_encoder_2"),
("AI-ModelScope/FLUX.1-dev", "text_encoder_2/model-00002-of-00002.safetensors", "models/FLUX/FLUX.1-dev/text_encoder_2"),
("AI-ModelScope/FLUX.1-dev", "text_encoder_2/model.safetensors.index.json", "models/FLUX/FLUX.1-dev/text_encoder_2"),
("AI-ModelScope/FLUX.1-dev", "ae.safetensors", "models/FLUX/FLUX.1-dev"),
("AI-ModelScope/FLUX.1-dev", "flux1-dev.safetensors", "models/FLUX/FLUX.1-dev"),
],
"FLUX.1-dev": {
"file_list": [
("AI-ModelScope/FLUX.1-dev", "text_encoder/model.safetensors", "models/FLUX/FLUX.1-dev/text_encoder"),
("AI-ModelScope/FLUX.1-dev", "text_encoder_2/config.json", "models/FLUX/FLUX.1-dev/text_encoder_2"),
("AI-ModelScope/FLUX.1-dev", "text_encoder_2/model-00001-of-00002.safetensors", "models/FLUX/FLUX.1-dev/text_encoder_2"),
("AI-ModelScope/FLUX.1-dev", "text_encoder_2/model-00002-of-00002.safetensors", "models/FLUX/FLUX.1-dev/text_encoder_2"),
("AI-ModelScope/FLUX.1-dev", "text_encoder_2/model.safetensors.index.json", "models/FLUX/FLUX.1-dev/text_encoder_2"),
("AI-ModelScope/FLUX.1-dev", "ae.safetensors", "models/FLUX/FLUX.1-dev"),
("AI-ModelScope/FLUX.1-dev", "flux1-dev.safetensors", "models/FLUX/FLUX.1-dev"),
],
"load_path": [
"models/FLUX/FLUX.1-dev/text_encoder/model.safetensors",
"models/FLUX/FLUX.1-dev/text_encoder_2",
"models/FLUX/FLUX.1-dev/ae.safetensors",
"models/FLUX/FLUX.1-dev/flux1-dev.safetensors"
],
},
"FLUX.1-schnell": {
"file_list": [
("AI-ModelScope/FLUX.1-dev", "text_encoder/model.safetensors", "models/FLUX/FLUX.1-dev/text_encoder"),
("AI-ModelScope/FLUX.1-dev", "text_encoder_2/config.json", "models/FLUX/FLUX.1-dev/text_encoder_2"),
("AI-ModelScope/FLUX.1-dev", "text_encoder_2/model-00001-of-00002.safetensors", "models/FLUX/FLUX.1-dev/text_encoder_2"),
("AI-ModelScope/FLUX.1-dev", "text_encoder_2/model-00002-of-00002.safetensors", "models/FLUX/FLUX.1-dev/text_encoder_2"),
("AI-ModelScope/FLUX.1-dev", "text_encoder_2/model.safetensors.index.json", "models/FLUX/FLUX.1-dev/text_encoder_2"),
("AI-ModelScope/FLUX.1-dev", "ae.safetensors", "models/FLUX/FLUX.1-dev"),
("AI-ModelScope/FLUX.1-schnell", "flux1-schnell.safetensors", "models/FLUX/FLUX.1-schnell"),
],
"load_path": [
"models/FLUX/FLUX.1-dev/text_encoder/model.safetensors",
"models/FLUX/FLUX.1-dev/text_encoder_2",
"models/FLUX/FLUX.1-dev/ae.safetensors",
"models/FLUX/FLUX.1-schnell/flux1-schnell.safetensors"
],
},
# ESRGAN
"ESRGAN_x4": [
("AI-ModelScope/Real-ESRGAN", "RealESRGAN_x4.pth", "models/ESRGAN"),
@@ -439,17 +491,24 @@ preset_models_on_modelscope = {
("AI-ModelScope/RIFE", "flownet.pkl", "models/RIFE"),
],
# CogVideo
"CogVideoX-5B": [
("ZhipuAI/CogVideoX-5b", "text_encoder/config.json", "models/CogVideo/CogVideoX-5b/text_encoder"),
("ZhipuAI/CogVideoX-5b", "text_encoder/model.safetensors.index.json", "models/CogVideo/CogVideoX-5b/text_encoder"),
("ZhipuAI/CogVideoX-5b", "text_encoder/model-00001-of-00002.safetensors", "models/CogVideo/CogVideoX-5b/text_encoder"),
("ZhipuAI/CogVideoX-5b", "text_encoder/model-00002-of-00002.safetensors", "models/CogVideo/CogVideoX-5b/text_encoder"),
("ZhipuAI/CogVideoX-5b", "transformer/config.json", "models/CogVideo/CogVideoX-5b/transformer"),
("ZhipuAI/CogVideoX-5b", "transformer/diffusion_pytorch_model.safetensors.index.json", "models/CogVideo/CogVideoX-5b/transformer"),
("ZhipuAI/CogVideoX-5b", "transformer/diffusion_pytorch_model-00001-of-00002.safetensors", "models/CogVideo/CogVideoX-5b/transformer"),
("ZhipuAI/CogVideoX-5b", "transformer/diffusion_pytorch_model-00002-of-00002.safetensors", "models/CogVideo/CogVideoX-5b/transformer"),
("ZhipuAI/CogVideoX-5b", "vae/diffusion_pytorch_model.safetensors", "models/CogVideo/CogVideoX-5b/vae"),
],
"CogVideoX-5B": {
"file_list": [
("ZhipuAI/CogVideoX-5b", "text_encoder/config.json", "models/CogVideo/CogVideoX-5b/text_encoder"),
("ZhipuAI/CogVideoX-5b", "text_encoder/model.safetensors.index.json", "models/CogVideo/CogVideoX-5b/text_encoder"),
("ZhipuAI/CogVideoX-5b", "text_encoder/model-00001-of-00002.safetensors", "models/CogVideo/CogVideoX-5b/text_encoder"),
("ZhipuAI/CogVideoX-5b", "text_encoder/model-00002-of-00002.safetensors", "models/CogVideo/CogVideoX-5b/text_encoder"),
("ZhipuAI/CogVideoX-5b", "transformer/config.json", "models/CogVideo/CogVideoX-5b/transformer"),
("ZhipuAI/CogVideoX-5b", "transformer/diffusion_pytorch_model.safetensors.index.json", "models/CogVideo/CogVideoX-5b/transformer"),
("ZhipuAI/CogVideoX-5b", "transformer/diffusion_pytorch_model-00001-of-00002.safetensors", "models/CogVideo/CogVideoX-5b/transformer"),
("ZhipuAI/CogVideoX-5b", "transformer/diffusion_pytorch_model-00002-of-00002.safetensors", "models/CogVideo/CogVideoX-5b/transformer"),
("ZhipuAI/CogVideoX-5b", "vae/diffusion_pytorch_model.safetensors", "models/CogVideo/CogVideoX-5b/vae"),
],
"load_path": [
"models/CogVideo/CogVideoX-5b/text_encoder",
"models/CogVideo/CogVideoX-5b/transformer",
"models/CogVideo/CogVideoX-5b/vae/diffusion_pytorch_model.safetensors",
],
},
}
Preset_model_id: TypeAlias = Literal[
"HunyuanDiT",
@@ -481,6 +540,7 @@ Preset_model_id: TypeAlias = Literal[
"SDXL-vae-fp16-fix",
"ControlNet_union_sdxl_promax",
"FLUX.1-dev",
"FLUX.1-schnell",
"SDXL_lora_zyd232_ChineseInkStyle_SDXL_v1_0",
"QwenPrompt",
"OmostPrompt",