theluyuan/DiffSynth-Studio
1
0
Fork 0
mirror of https://github.com/modelscope/DiffSynth-Studio.git synced 2026-03-19 06:48:12 +00:00
Code Issues Packages Projects Releases Wiki Activity

wan-fun-inp-1.1

Browse Source
This commit is contained in:
Artiprocher
2025-06-12 14:42:28 +08:00
parent b25c66b303
commit 7dc273c020
11 changed files with 256 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
examples/wanvideo/README_zh.md
View File

@@ -13,8 +13,8 @@
|[PAI/Wan2.1-Fun-14B-Control](https://modelscope.cn/models/PAI/Wan2.1-Fun-14B-Control)|基础模型|`control_video`|[code](./model_inference/Wan2.1-Fun-14B-Control.py)|[code](./model_training/full/Wan2.1-Fun-14B-Control.sh)|[code](./model_training/validate_full/Wan2.1-Fun-14B-Control.py)|[code](./model_training/lora/Wan2.1-Fun-14B-Control.sh)|[code](./model_training/validate_lora/Wan2.1-Fun-14B-Control.py)|
|[PAI/Wan2.1-Fun-V1.1-1.3B-Control](https://modelscope.cn/models/PAI/Wan2.1-Fun-V1.1-1.3B-Control)|基础模型|`control_video`, `reference_image`|[code](./model_inference/Wan2.1-Fun-V1.1-1.3B-Control.py)|[code](./model_training/full/Wan2.1-Fun-V1.1-1.3B-Control.sh)|[code](./model_training/validate_full/Wan2.1-Fun-V1.1-1.3B-Control.py)|[code](./model_training/lora/Wan2.1-Fun-V1.1-1.3B-Control.sh)|[code](./model_training/validate_lora/Wan2.1-Fun-V1.1-1.3B-Control.py)|
|[PAI/Wan2.1-Fun-V1.1-14B-Control](https://modelscope.cn/models/PAI/Wan2.1-Fun-V1.1-14B-Control)|基础模型|`control_video`, `reference_image`|[code](./model_inference/Wan2.1-Fun-V1.1-14B-Control.py)|[code](./model_training/full/Wan2.1-Fun-V1.1-14B-Control.sh)|[code](./model_training/validate_full/Wan2.1-Fun-V1.1-14B-Control.py)|[code](./model_training/lora/Wan2.1-Fun-V1.1-14B-Control.sh)|[code](./model_training/validate_lora/Wan2.1-Fun-V1.1-14B-Control.py)|
|[PAI/Wan2.1-Fun-V1.1-1.3B-InP](https://modelscope.cn/models/PAI/Wan2.1-Fun-V1.1-1.3B-InP)|基础模型|`input_image`, `end_image`||||||
|[PAI/Wan2.1-Fun-V1.1-14B-InP](https://modelscope.cn/models/PAI/Wan2.1-Fun-V1.1-14B-InP)|基础模型|`input_image`, `end_image`||||||
|[PAI/Wan2.1-Fun-V1.1-1.3B-InP](https://modelscope.cn/models/PAI/Wan2.1-Fun-V1.1-1.3B-InP)|基础模型|`input_image`, `end_image`|[code](./model_inference/Wan2.1-Fun-V1.1-1.3B-InP.py)|[code](./model_training/full/Wan2.1-Fun-V1.1-1.3B-InP.sh)|[code](./model_training/validate_full/Wan2.1-Fun-V1.1-1.3B-InP.py)|[code](./model_training/lora/Wan2.1-Fun-V1.1-1.3B-InP.sh)|[code](./model_training/validate_lora/Wan2.1-Fun-V1.1-1.3B-InP.py)|
|[PAI/Wan2.1-Fun-V1.1-14B-InP](https://modelscope.cn/models/PAI/Wan2.1-Fun-V1.1-14B-InP)|基础模型|`input_image`, `end_image`|[code](./model_inference/Wan2.1-Fun-V1.1-14B-InP.py)|[code](./model_training/full/Wan2.1-Fun-V1.1-14B-InP.sh)|[code](./model_training/validate_full/Wan2.1-Fun-V1.1-14B-InP.py)|[code](./model_training/lora/Wan2.1-Fun-V1.1-14B-InP.sh)|[code](./model_training/validate_lora/Wan2.1-Fun-V1.1-14B-InP.py)|
|[PAI/Wan2.1-Fun-V1.1-1.3B-Control-Camera](https://modelscope.cn/models/PAI/Wan2.1-Fun-V1.1-1.3B-Control-Camera)|基础模型|||||||
|[PAI/Wan2.1-Fun-V1.1-14B-Control-Camera](https://modelscope.cn/models/PAI/Wan2.1-Fun-V1.1-14B-Control-Camera)|基础模型|||||||
|[iic/VACE-Wan2.1-1.3B-Preview](https://modelscope.cn/models/iic/VACE-Wan2.1-1.3B-Preview)|适配器|`vace_control_video`, `vace_reference_image`|[code](./model_inference/Wan2.1-VACE-1.3B-Preview.py)|[code](./model_training/full/Wan2.1-VACE-1.3B-Preview.sh)|[code](./model_training/validate_full/Wan2.1-VACE-1.3B-Preview.py)|[code](./model_training/lora/Wan2.1-VACE-1.3B-Preview.sh)|[code](./model_training/validate_lora/Wan2.1-VACE-1.3B-Preview.py)|

36
examples/wanvideo/model_inference/Wan2.1-Fun-V1.1-1.3B-InP.py Normal file
View File

@@ -0,0 +1,36 @@
import torch
from PIL import Image
from diffsynth import save_video, VideoData
from diffsynth.pipelines.wan_video_new import WanVideoPipeline, ModelConfig
from modelscope import dataset_snapshot_download
pipe = WanVideoPipeline.from_pretrained(
torch_dtype=torch.bfloat16,
device="cuda",
model_configs=[
ModelConfig(model_id="PAI/Wan2.1-Fun-V1.1-1.3B-InP", origin_file_pattern="diffusion_pytorch_model*.safetensors", offload_device="cpu"),
ModelConfig(model_id="PAI/Wan2.1-Fun-V1.1-1.3B-InP", origin_file_pattern="models_t5_umt5-xxl-enc-bf16.pth", offload_device="cpu"),
ModelConfig(model_id="PAI/Wan2.1-Fun-V1.1-1.3B-InP", origin_file_pattern="Wan2.1_VAE.pth", offload_device="cpu"),
ModelConfig(model_id="PAI/Wan2.1-Fun-V1.1-1.3B-InP", origin_file_pattern="models_clip_open-clip-xlm-roberta-large-vit-huge-14.pth", offload_device="cpu"),
],
)
pipe.enable_vram_management()
dataset_snapshot_download(
dataset_id="DiffSynth-Studio/examples_in_diffsynth",
local_dir="./",
allow_file_pattern=f"data/examples/wan/input_image.jpg"
)
image = Image.open("data/examples/wan/input_image.jpg")
# First and last frame to video
video = pipe(
prompt="一艘小船正勇敢地乘风破浪前行。蔚蓝的大海波涛汹涌，白色的浪花拍打着船身，但小船毫不畏惧，坚定地驶向远方。阳光洒在水面上，闪烁着金色的光芒，为这壮丽的场景增添了一抹温暖。镜头拉近，可以看到船上的旗帜迎风飘扬，象征着不屈的精神与冒险的勇气。这段画面充满力量，激励人心，展现了面对挑战时的无畏与执着。",
negative_prompt="色调艳丽，过曝，静态，细节模糊不清，字幕，风格，作品，画作，画面，静止，整体发灰，最差质量，低质量，JPEG压缩残留，丑陋的，残缺的，多余的手指，画得不好的手部，画得不好的脸部，畸形的，毁容的，形态畸形的肢体，手指融合，静止不动的画面，杂乱的背景，三条腿，背景人很多，倒着走",
input_image=image,
seed=0, tiled=True
# You can input `end_image=xxx` to control the last frame of the video.
# The model will automatically generate the dynamic content between `input_image` and `end_image`.
)
save_video(video, "video.mp4", fps=15, quality=5)

36
examples/wanvideo/model_inference/Wan2.1-Fun-V1.1-14B-InP.py Normal file
View File

@@ -0,0 +1,36 @@
import torch
from PIL import Image
from diffsynth import save_video, VideoData
from diffsynth.pipelines.wan_video_new import WanVideoPipeline, ModelConfig
from modelscope import dataset_snapshot_download
pipe = WanVideoPipeline.from_pretrained(
torch_dtype=torch.bfloat16,
device="cuda",
model_configs=[
ModelConfig(model_id="PAI/Wan2.1-Fun-V1.1-14B-InP", origin_file_pattern="diffusion_pytorch_model*.safetensors", offload_device="cpu"),
ModelConfig(model_id="PAI/Wan2.1-Fun-V1.1-14B-InP", origin_file_pattern="models_t5_umt5-xxl-enc-bf16.pth", offload_device="cpu"),
ModelConfig(model_id="PAI/Wan2.1-Fun-V1.1-14B-InP", origin_file_pattern="Wan2.1_VAE.pth", offload_device="cpu"),
ModelConfig(model_id="PAI/Wan2.1-Fun-V1.1-14B-InP", origin_file_pattern="models_clip_open-clip-xlm-roberta-large-vit-huge-14.pth", offload_device="cpu"),
],
)
pipe.enable_vram_management()
dataset_snapshot_download(
dataset_id="DiffSynth-Studio/examples_in_diffsynth",
local_dir="./",
allow_file_pattern=f"data/examples/wan/input_image.jpg"
)
image = Image.open("data/examples/wan/input_image.jpg")
# First and last frame to video
video = pipe(
prompt="一艘小船正勇敢地乘风破浪前行。蔚蓝的大海波涛汹涌，白色的浪花拍打着船身，但小船毫不畏惧，坚定地驶向远方。阳光洒在水面上，闪烁着金色的光芒，为这壮丽的场景增添了一抹温暖。镜头拉近，可以看到船上的旗帜迎风飘扬，象征着不屈的精神与冒险的勇气。这段画面充满力量，激励人心，展现了面对挑战时的无畏与执着。",
negative_prompt="色调艳丽，过曝，静态，细节模糊不清，字幕，风格，作品，画作，画面，静止，整体发灰，最差质量，低质量，JPEG压缩残留，丑陋的，残缺的，多余的手指，画得不好的手部，画得不好的脸部，畸形的，毁容的，形态畸形的肢体，手指融合，静止不动的画面，杂乱的背景，三条腿，背景人很多，倒着走",
input_image=image,
seed=0, tiled=True
# You can input `end_image=xxx` to control the last frame of the video.
# The model will automatically generate the dynamic content between `input_image` and `end_image`.
)
save_video(video, "video.mp4", fps=15, quality=5)

14
examples/wanvideo/model_training/full/Wan2.1-Fun-V1.1-1.3B-InP.sh Normal file
View File

@@ -0,0 +1,14 @@
accelerate launch examples/wanvideo/model_training/train.py \
--dataset_base_path data/example_video_dataset \
--dataset_metadata_path data/example_video_dataset/metadata.csv \
--height 480 \
--width 832 \
--dataset_repeat 100 \
--model_id_with_origin_paths "PAI/Wan2.1-Fun-V1.1-1.3B-InP:diffusion_pytorch_model*.safetensors,PAI/Wan2.1-Fun-V1.1-1.3B-InP:models_t5_umt5-xxl-enc-bf16.pth,PAI/Wan2.1-Fun-V1.1-1.3B-InP:Wan2.1_VAE.pth,PAI/Wan2.1-Fun-V1.1-1.3B-InP:models_clip_open-clip-xlm-roberta-large-vit-huge-14.pth" \
--learning_rate 1e-5 \
--num_epochs 2 \
--remove_prefix_in_ckpt "pipe.dit." \
--output_path "./models/train/Wan2.1-Fun-V1.1-1.3B-InP_full" \
--trainable_models "dit" \
--input_contains_input_image \
--input_contains_end_image

14
examples/wanvideo/model_training/full/Wan2.1-Fun-V1.1-14B-InP.sh Normal file
View File

@@ -0,0 +1,14 @@
accelerate launch --config_file examples/wanvideo/model_training/full/accelerate_config_14B.yaml examples/wanvideo/model_training/train.py \
--dataset_base_path data/example_video_dataset \
--dataset_metadata_path data/example_video_dataset/metadata.csv \
--height 480 \
--width 832 \
--dataset_repeat 100 \
--model_id_with_origin_paths "PAI/Wan2.1-Fun-V1.1-14B-InP:diffusion_pytorch_model*.safetensors,PAI/Wan2.1-Fun-V1.1-14B-InP:models_t5_umt5-xxl-enc-bf16.pth,PAI/Wan2.1-Fun-V1.1-14B-InP:Wan2.1_VAE.pth,PAI/Wan2.1-Fun-V1.1-14B-InP:models_clip_open-clip-xlm-roberta-large-vit-huge-14.pth" \
--learning_rate 1e-5 \
--num_epochs 2 \
--remove_prefix_in_ckpt "pipe.dit." \
--output_path "./models/train/Wan2.1-Fun-V1.1-14B-InP_full" \
--trainable_models "dit" \
--input_contains_input_image \
--input_contains_end_image

16
examples/wanvideo/model_training/lora/Wan2.1-Fun-V1.1-1.3B-InP.sh Normal file
View File

@@ -0,0 +1,16 @@
accelerate launch examples/wanvideo/model_training/train.py \
--dataset_base_path data/example_video_dataset \
--dataset_metadata_path data/example_video_dataset/metadata.csv \
--height 480 \
--width 832 \
--dataset_repeat 100 \
--model_id_with_origin_paths "PAI/Wan2.1-Fun-V1.1-1.3B-InP:diffusion_pytorch_model*.safetensors,PAI/Wan2.1-Fun-V1.1-1.3B-InP:models_t5_umt5-xxl-enc-bf16.pth,PAI/Wan2.1-Fun-V1.1-1.3B-InP:Wan2.1_VAE.pth,PAI/Wan2.1-Fun-V1.1-1.3B-InP:models_clip_open-clip-xlm-roberta-large-vit-huge-14.pth" \
--learning_rate 1e-4 \
--num_epochs 5 \
--remove_prefix_in_ckpt "pipe.dit." \
--output_path "./models/train/Wan2.1-Fun-V1.1-1.3B-InP_lora" \
--lora_base_model "dit" \
--lora_target_modules "q,k,v,o,ffn.0,ffn.2" \
--lora_rank 32 \
--input_contains_input_image \
--input_contains_end_image

16
examples/wanvideo/model_training/lora/Wan2.1-Fun-V1.1-14B-InP.sh Normal file
View File

@@ -0,0 +1,16 @@
accelerate launch examples/wanvideo/model_training/train.py \
--dataset_base_path data/example_video_dataset \
--dataset_metadata_path data/example_video_dataset/metadata.csv \
--height 480 \
--width 832 \
--dataset_repeat 100 \
--model_id_with_origin_paths "PAI/Wan2.1-Fun-V1.1-14B-InP:diffusion_pytorch_model*.safetensors,PAI/Wan2.1-Fun-V1.1-14B-InP:models_t5_umt5-xxl-enc-bf16.pth,PAI/Wan2.1-Fun-V1.1-14B-InP:Wan2.1_VAE.pth,PAI/Wan2.1-Fun-V1.1-14B-InP:models_clip_open-clip-xlm-roberta-large-vit-huge-14.pth" \
--learning_rate 1e-4 \
--num_epochs 5 \
--remove_prefix_in_ckpt "pipe.dit." \
--output_path "./models/train/Wan2.1-Fun-V1.1-14B-InP_lora" \
--lora_base_model "dit" \
--lora_target_modules "q,k,v,o,ffn.0,ffn.2" \
--lora_rank 32 \
--input_contains_input_image \
--input_contains_end_image

31
examples/wanvideo/model_training/validate_full/Wan2.1-Fun-V1.1-1.3B-InP.py Normal file
View File

@@ -0,0 +1,31 @@
import torch
from PIL import Image
from diffsynth import save_video, VideoData, load_state_dict
from diffsynth.pipelines.wan_video_new import WanVideoPipeline, ModelConfig
from modelscope import dataset_snapshot_download
pipe = WanVideoPipeline.from_pretrained(
torch_dtype=torch.bfloat16,
device="cuda",
model_configs=[
ModelConfig(model_id="PAI/Wan2.1-Fun-V1.1-1.3B-InP", origin_file_pattern="diffusion_pytorch_model*.safetensors", offload_device="cpu"),
ModelConfig(model_id="PAI/Wan2.1-Fun-V1.1-1.3B-InP", origin_file_pattern="models_t5_umt5-xxl-enc-bf16.pth", offload_device="cpu"),
ModelConfig(model_id="PAI/Wan2.1-Fun-V1.1-1.3B-InP", origin_file_pattern="Wan2.1_VAE.pth", offload_device="cpu"),
ModelConfig(model_id="PAI/Wan2.1-Fun-V1.1-1.3B-InP", origin_file_pattern="models_clip_open-clip-xlm-roberta-large-vit-huge-14.pth", offload_device="cpu"),
],
)
state_dict = load_state_dict("models/train/Wan2.1-Fun-V1.1-1.3B-InP_full/epoch-1.safetensors")
pipe.dit.load_state_dict(state_dict)
pipe.enable_vram_management()
video = VideoData("data/example_video_dataset/video1.mp4", height=480, width=832)
# First and last frame to video
video = pipe(
prompt="from sunset to night, a small town, light, house, river",
negative_prompt="色调艳丽，过曝，静态，细节模糊不清，字幕，风格，作品，画作，画面，静止，整体发灰，最差质量，低质量，JPEG压缩残留，丑陋的，残缺的，多余的手指，画得不好的手部，画得不好的脸部，畸形的，毁容的，形态畸形的肢体，手指融合，静止不动的画面，杂乱的背景，三条腿，背景人很多，倒着走",
input_image=video[0], end_image=video[80],
seed=0, tiled=True
)
save_video(video, "video_Wan2.1-Fun-V1.1-1.3B-InP.mp4", fps=15, quality=5)

31
examples/wanvideo/model_training/validate_full/Wan2.1-Fun-V1.1-14B-InP.py Normal file
View File

@@ -0,0 +1,31 @@
import torch
from PIL import Image
from diffsynth import save_video, VideoData, load_state_dict
from diffsynth.pipelines.wan_video_new import WanVideoPipeline, ModelConfig
from modelscope import dataset_snapshot_download
pipe = WanVideoPipeline.from_pretrained(
torch_dtype=torch.bfloat16,
device="cuda",
model_configs=[
ModelConfig(model_id="PAI/Wan2.1-Fun-V1.1-14B-InP", origin_file_pattern="diffusion_pytorch_model*.safetensors", offload_device="cpu"),
ModelConfig(model_id="PAI/Wan2.1-Fun-V1.1-14B-InP", origin_file_pattern="models_t5_umt5-xxl-enc-bf16.pth", offload_device="cpu"),
ModelConfig(model_id="PAI/Wan2.1-Fun-V1.1-14B-InP", origin_file_pattern="Wan2.1_VAE.pth", offload_device="cpu"),
ModelConfig(model_id="PAI/Wan2.1-Fun-V1.1-14B-InP", origin_file_pattern="models_clip_open-clip-xlm-roberta-large-vit-huge-14.pth", offload_device="cpu"),
],
)
state_dict = load_state_dict("models/train/Wan2.1-Fun-V1.1-14B-InP_full/epoch-1.safetensors")
pipe.dit.load_state_dict(state_dict)
pipe.enable_vram_management()
video = VideoData("data/example_video_dataset/video1.mp4", height=480, width=832)
# First and last frame to video
video = pipe(
prompt="from sunset to night, a small town, light, house, river",
negative_prompt="色调艳丽，过曝，静态，细节模糊不清，字幕，风格，作品，画作，画面，静止，整体发灰，最差质量，低质量，JPEG压缩残留，丑陋的，残缺的，多余的手指，画得不好的手部，画得不好的脸部，畸形的，毁容的，形态畸形的肢体，手指融合，静止不动的画面，杂乱的背景，三条腿，背景人很多，倒着走",
input_image=video[0], end_image=video[80],
seed=0, tiled=True
)
save_video(video, "video_Wan2.1-Fun-V1.1-14B-InP.mp4", fps=15, quality=5)

30
examples/wanvideo/model_training/validate_lora/Wan2.1-Fun-V1.1-1.3B-InP.py Normal file
View File

@@ -0,0 +1,30 @@
import torch
from PIL import Image
from diffsynth import save_video, VideoData
from diffsynth.pipelines.wan_video_new import WanVideoPipeline, ModelConfig
from modelscope import dataset_snapshot_download
pipe = WanVideoPipeline.from_pretrained(
torch_dtype=torch.bfloat16,
device="cuda",
model_configs=[
ModelConfig(model_id="PAI/Wan2.1-Fun-V1.1-1.3B-InP", origin_file_pattern="diffusion_pytorch_model*.safetensors", offload_device="cpu"),
ModelConfig(model_id="PAI/Wan2.1-Fun-V1.1-1.3B-InP", origin_file_pattern="models_t5_umt5-xxl-enc-bf16.pth", offload_device="cpu"),
ModelConfig(model_id="PAI/Wan2.1-Fun-V1.1-1.3B-InP", origin_file_pattern="Wan2.1_VAE.pth", offload_device="cpu"),
ModelConfig(model_id="PAI/Wan2.1-Fun-V1.1-1.3B-InP", origin_file_pattern="models_clip_open-clip-xlm-roberta-large-vit-huge-14.pth", offload_device="cpu"),
],
)
pipe.load_lora(pipe.dit, "models/train/Wan2.1-Fun-V1.1-1.3B-InP_lora/epoch-4.safetensors", alpha=1)
pipe.enable_vram_management()
video = VideoData("data/example_video_dataset/video1.mp4", height=480, width=832)
# First and last frame to video
video = pipe(
prompt="from sunset to night, a small town, light, house, river",
negative_prompt="色调艳丽，过曝，静态，细节模糊不清，字幕，风格，作品，画作，画面，静止，整体发灰，最差质量，低质量，JPEG压缩残留，丑陋的，残缺的，多余的手指，画得不好的手部，画得不好的脸部，畸形的，毁容的，形态畸形的肢体，手指融合，静止不动的画面，杂乱的背景，三条腿，背景人很多，倒着走",
input_image=video[0], end_image=video[80],
seed=0, tiled=True
)
save_video(video, "video_Wan2.1-Fun-V1.1-1.3B-InP.mp4", fps=15, quality=5)

30
examples/wanvideo/model_training/validate_lora/Wan2.1-Fun-V1.1-14B-InP.py Normal file
View File

@@ -0,0 +1,30 @@
import torch
from PIL import Image
from diffsynth import save_video, VideoData
from diffsynth.pipelines.wan_video_new import WanVideoPipeline, ModelConfig
from modelscope import dataset_snapshot_download
pipe = WanVideoPipeline.from_pretrained(
torch_dtype=torch.bfloat16,
device="cuda",
model_configs=[
ModelConfig(model_id="PAI/Wan2.1-Fun-V1.1-14B-InP", origin_file_pattern="diffusion_pytorch_model*.safetensors", offload_device="cpu"),
ModelConfig(model_id="PAI/Wan2.1-Fun-V1.1-14B-InP", origin_file_pattern="models_t5_umt5-xxl-enc-bf16.pth", offload_device="cpu"),
ModelConfig(model_id="PAI/Wan2.1-Fun-V1.1-14B-InP", origin_file_pattern="Wan2.1_VAE.pth", offload_device="cpu"),
ModelConfig(model_id="PAI/Wan2.1-Fun-V1.1-14B-InP", origin_file_pattern="models_clip_open-clip-xlm-roberta-large-vit-huge-14.pth", offload_device="cpu"),
],
)
pipe.load_lora(pipe.dit, "models/train/Wan2.1-Fun-V1.1-14B-InP_lora/epoch-4.safetensors", alpha=1)
pipe.enable_vram_management()
video = VideoData("data/example_video_dataset/video1.mp4", height=480, width=832)
# First and last frame to video
video = pipe(
prompt="from sunset to night, a small town, light, house, river",
negative_prompt="色调艳丽，过曝，静态，细节模糊不清，字幕，风格，作品，画作，画面，静止，整体发灰，最差质量，低质量，JPEG压缩残留，丑陋的，残缺的，多余的手指，画得不好的手部，画得不好的脸部，畸形的，毁容的，形态畸形的肢体，手指融合，静止不动的画面，杂乱的背景，三条腿，背景人很多，倒着走",
input_image=video[0], end_image=video[80],
seed=0, tiled=True
)
save_video(video, "video_Wan2.1-Fun-V1.1-14B-InP.mp4", fps=15, quality=5)