theluyuan/DiffSynth-Studio
1
0
Fork 0
mirror of https://github.com/modelscope/DiffSynth-Studio.git synced 2026-03-20 23:58:12 +00:00
Code Issues Packages Projects Releases Wiki Activity

load hunyuani2v model

Browse Source
This commit is contained in:
mi804
2025-03-07 17:43:30 +08:00
parent 6e316fd825
commit 945b43492e
6 changed files with 327 additions and 18 deletions
Download Patch File Download Diff File Expand all files Collapse all files

22
diffsynth/configs/model_config.py
View File

@@ -112,6 +112,7 @@ model_loader_configs = [
(None, "aeb82dce778a03dcb4d726cb03f3c43f", ["hunyuan_video_vae_decoder", "hunyuan_video_vae_encoder"], [HunyuanVideoVAEDecoder, HunyuanVideoVAEEncoder], "diffusers"),
(None, "b9588f02e78f5ccafc9d7c0294e46308", ["hunyuan_video_dit"], [HunyuanVideoDiT], "civitai"),
(None, "84ef4bd4757f60e906b54aa6a7815dc6", ["hunyuan_video_dit"], [HunyuanVideoDiT], "civitai"),
(None, "ae3c22aaa28bfae6f3688f796c9814ae", ["hunyuan_video_dit"], [HunyuanVideoDiT], "civitai"),
(None, "68beaf8429b7c11aa8ca05b1bd0058bd", ["stepvideo_vae"], [StepVideoVAE], "civitai"),
(None, "5c0216a2132b082c10cb7a0e0377e681", ["stepvideo_dit"], [StepVideoModel], "civitai"),
(None, "9269f8db9040a9d860eaca435be61814", ["wan_video_dit"], [WanModel], "civitai"),
@@ -135,6 +136,7 @@ huggingface_model_loader_configs = [
("CogVideoXTransformer3DModel", "diffsynth.models.cog_dit", "cog_dit", "CogDiT"),
("SiglipModel", "transformers.models.siglip.modeling_siglip", "siglip_vision_model", "SiglipVisionModel"),
("LlamaForCausalLM", "diffsynth.models.hunyuan_video_text_encoder", "hunyuan_video_text_encoder_2", "HunyuanVideoLLMEncoder"),
("LlavaForConditionalGeneration", "diffsynth.models.hunyuan_video_text_encoder", "hunyuan_video_text_encoder_2", "HunyuanVideoMLLMEncoder"),
("Step1Model", "diffsynth.models.stepvideo_text_encoder", "stepvideo_text_encoder_2", "STEP1TextEncoder"),
]
patch_model_loader_configs = [
@@ -677,6 +679,25 @@ preset_models_on_modelscope = {
"models/HunyuanVideo/transformers/mp_rank_00_model_states.pt"
],
},
"HunyuanVideoI2V":{
"file_list": [
("AI-ModelScope/clip-vit-large-patch14", "model.safetensors", "models/HunyuanVideoI2V/text_encoder"),
("AI-ModelScope/llava-llama-3-8b-v1_1-transformers", "model-00001-of-00004.safetensors", "models/HunyuanVideoI2V/text_encoder_2"),
("AI-ModelScope/llava-llama-3-8b-v1_1-transformers", "model-00002-of-00004.safetensors", "models/HunyuanVideoI2V/text_encoder_2"),
("AI-ModelScope/llava-llama-3-8b-v1_1-transformers", "model-00003-of-00004.safetensors", "models/HunyuanVideoI2V/text_encoder_2"),
("AI-ModelScope/llava-llama-3-8b-v1_1-transformers", "model-00004-of-00004.safetensors", "models/HunyuanVideoI2V/text_encoder_2"),
("AI-ModelScope/llava-llama-3-8b-v1_1-transformers", "config.json", "models/HunyuanVideoI2V/text_encoder_2"),
("AI-ModelScope/llava-llama-3-8b-v1_1-transformers", "model.safetensors.index.json", "models/HunyuanVideoI2V/text_encoder_2"),
("AI-ModelScope/HunyuanVideo-I2V", "hunyuan-video-i2v-720p/vae/pytorch_model.pt", "models/HunyuanVideoI2V/vae"),
("AI-ModelScope/HunyuanVideo-I2V", "hunyuan-video-i2v-720p/transformers/mp_rank_00_model_states.pt", "models/HunyuanVideoI2V/transformers")
],
"load_path": [
"models/HunyuanVideoI2V/text_encoder/model.safetensors",
"models/HunyuanVideoI2V/text_encoder_2",
"models/HunyuanVideoI2V/vae/pytorch_model.pt",
"models/HunyuanVideoI2V/transformers/mp_rank_00_model_states.pt"
],
},
"HunyuanVideo-fp8":{
"file_list": [
("AI-ModelScope/clip-vit-large-patch14", "model.safetensors", "models/HunyuanVideo/text_encoder"),
@@ -753,4 +774,5 @@ Preset_model_id: TypeAlias = Literal[
"StableDiffusion3.5-medium",
"HunyuanVideo",
"HunyuanVideo-fp8",
"HunyuanVideoI2V",
]