theluyuan/DiffSynth-Studio
1
0
Fork 0
mirror of https://github.com/modelscope/DiffSynth-Studio.git synced 2026-03-22 08:40:47 +00:00
Code Issues Packages Projects Releases Wiki Activity

support stepvideo

Browse Source
This commit is contained in:
Artiprocher
2025-02-17 17:32:25 +08:00
parent 7434ec8fcd
commit 3681adc5ac
12 changed files with 2866 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
diffsynth/configs/model_config.py
View File

@@ -51,6 +51,9 @@ from ..extensions.ESRGAN import RRDBNet
from ..models.hunyuan_video_dit import HunyuanVideoDiT
from ..models.stepvideo_vae import StepVideoVAE
from ..models.stepvideo_dit import StepVideoModel
model_loader_configs = [
# These configs are provided for detecting model type automatically.
@@ -103,6 +106,8 @@ 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, "68beaf8429b7c11aa8ca05b1bd0058bd", ["stepvideo_vae"], [StepVideoVAE], "civitai"),
(None, "5c0216a2132b082c10cb7a0e0377e681", ["stepvideo_dit"], [StepVideoModel], "civitai"),
]
huggingface_model_loader_configs = [
# These configs are provided for detecting model type automatically.
@@ -115,7 +120,8 @@ huggingface_model_loader_configs = [
("T5EncoderModel", "diffsynth.models.flux_text_encoder", "flux_text_encoder_2", "FluxTextEncoder2"),
("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")
("LlamaForCausalLM", "diffsynth.models.hunyuan_video_text_encoder", "hunyuan_video_text_encoder_2", "HunyuanVideoLLMEncoder"),
("Step1Model", "diffsynth.models.stepvideo_text_encoder", "stepvideo_text_encoder_2", "STEP1TextEncoder"),
]
patch_model_loader_configs = [
# These configs are provided for detecting model type automatically.