mirror of
https://github.com/modelscope/DiffSynth-Studio.git
synced 2026-03-18 22:08:13 +00:00
39 KiB
39 KiB
Model Directory
Qwen-Image
Documentation: ./Qwen-Image.md
Effect Preview
Quick Start
from diffsynth.pipelines.qwen_image import QwenImagePipeline, ModelConfig
from PIL import Image
import torch
pipe = QwenImagePipeline.from_pretrained(
torch_dtype=torch.bfloat16,
device="cuda",
model_configs=[
ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="transformer/diffusion_pytorch_model*.safetensors"),
ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="text_encoder/model*.safetensors"),
ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="vae/diffusion_pytorch_model.safetensors"),
],
tokenizer_config=ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="tokenizer/"),
)
prompt = "精致肖像，水下少女，蓝裙飘逸，发丝轻扬，光影透澈，气泡环绕，面容恬静，细节精致，梦幻唯美。"
image = pipe(
prompt, seed=0, num_inference_steps=40,
# edit_image=Image.open("xxx.jpg").resize((1328, 1328)) # For Qwen-Image-Edit
)
image.save("image.jpg")
Model Lineage
graph LR;
Qwen/Qwen-Image-->Qwen/Qwen-Image-Edit;
Qwen/Qwen-Image-Edit-->Qwen/Qwen-Image-Edit-2509;
Qwen/Qwen-Image-->EliGen-Series;
EliGen-Series-->DiffSynth-Studio/Qwen-Image-EliGen;
DiffSynth-Studio/Qwen-Image-EliGen-->DiffSynth-Studio/Qwen-Image-EliGen-V2;
EliGen-Series-->DiffSynth-Studio/Qwen-Image-EliGen-Poster;
Qwen/Qwen-Image-->Distill-Series;
Distill-Series-->DiffSynth-Studio/Qwen-Image-Distill-Full;
Distill-Series-->DiffSynth-Studio/Qwen-Image-Distill-LoRA;
Qwen/Qwen-Image-->ControlNet-Series;
ControlNet-Series-->Blockwise-ControlNet-Series;
Blockwise-ControlNet-Series-->DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Canny;
Blockwise-ControlNet-Series-->DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Depth;
Blockwise-ControlNet-Series-->DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Inpaint;
ControlNet-Series-->DiffSynth-Studio/Qwen-Image-In-Context-Control-Union;
Qwen/Qwen-Image-->DiffSynth-Studio/Qwen-Image-Edit-Lowres-Fix;
| Model ID | Inference | Low VRAM Inference | Full Training | Validation After Full Training | LoRA Training | Validation After LoRA Training |
|---|---|---|---|---|---|---|
| Qwen/Qwen-Image | code | code | code | code | code | code |
| Qwen/Qwen-Image-Edit | code | code | code | code | code | code |
| Qwen/Qwen-Image-Edit-2509 | code | code | code | code | code | code |
| DiffSynth-Studio/Qwen-Image-EliGen | code | code | - | - | code | code |
| DiffSynth-Studio/Qwen-Image-EliGen-V2 | code | code | - | - | code | code |
| DiffSynth-Studio/Qwen-Image-EliGen-Poster | code | code | - | - | code | code |
| DiffSynth-Studio/Qwen-Image-Distill-Full | code | code | code | code | code | code |
| DiffSynth-Studio/Qwen-Image-Distill-LoRA | code | code | - | - | code | code |
| DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Canny | code | code | code | code | code | code |
| DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Depth | code | code | code | code | code | code |
| DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Inpaint | code | code | code | code | code | code |
| DiffSynth-Studio/Qwen-Image-In-Context-Control-Union | code | code | - | - | code | code |
| DiffSynth-Studio/Qwen-Image-Edit-Lowres-Fix | code | code | - | - | - | - |
FLUX Series
Documentation: ./FLUX.md
Effect Preview
Quick Start
import torch
from diffsynth.pipelines.flux_image import FluxImagePipeline, ModelConfig
pipe = FluxImagePipeline.from_pretrained(
torch_dtype=torch.bfloat16,
device="cuda",
model_configs=[
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="flux1-dev.safetensors"),
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder/model.safetensors"),
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder_2/*.safetensors"),
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="ae.safetensors"),
],
)
image = pipe(prompt="a cat", seed=0)
image.save("image.jpg")
Model Lineage
graph LR;
FLUX.1-Series-->black-forest-labs/FLUX.1-dev;
FLUX.1-Series-->black-forest-labs/FLUX.1-Krea-dev;
FLUX.1-Series-->black-forest-labs/FLUX.1-Kontext-dev;
black-forest-labs/FLUX.1-dev-->FLUX.1-dev-ControlNet-Series;
FLUX.1-dev-ControlNet-Series-->alimama-creative/FLUX.1-dev-Controlnet-Inpainting-Beta;
FLUX.1-dev-ControlNet-Series-->InstantX/FLUX.1-dev-Controlnet-Union-alpha;
FLUX.1-dev-ControlNet-Series-->jasperai/Flux.1-dev-Controlnet-Upscaler;
black-forest-labs/FLUX.1-dev-->InstantX/FLUX.1-dev-IP-Adapter;
black-forest-labs/FLUX.1-dev-->ByteDance/InfiniteYou;
black-forest-labs/FLUX.1-dev-->DiffSynth-Studio/Eligen;
black-forest-labs/FLUX.1-dev-->DiffSynth-Studio/LoRA-Encoder-FLUX.1-Dev;
black-forest-labs/FLUX.1-dev-->DiffSynth-Studio/LoRAFusion-preview-FLUX.1-dev;
black-forest-labs/FLUX.1-dev-->ostris/Flex.2-preview;
black-forest-labs/FLUX.1-dev-->stepfun-ai/Step1X-Edit;
Qwen/Qwen2.5-VL-7B-Instruct-->stepfun-ai/Step1X-Edit;
black-forest-labs/FLUX.1-dev-->DiffSynth-Studio/Nexus-GenV2;
Qwen/Qwen2.5-VL-7B-Instruct-->DiffSynth-Studio/Nexus-GenV2;
Wan Series
Documentation: ./Wan.md
Quick Start
import torch
from diffsynth.utils.data import save_video
from diffsynth.pipelines.wan_video import WanVideoPipeline, ModelConfig
pipe = WanVideoPipeline.from_pretrained(
torch_dtype=torch.bfloat16,
device="cuda",
model_configs=[
ModelConfig(model_id="Wan-AI/Wan2.1-T2V-1.3B", origin_file_pattern="diffusion_pytorch_model*.safetensors"),
ModelConfig(model_id="Wan-AI/Wan2.1-T2V-1.3B", origin_file_pattern="models_t5_umt5-xxl-enc-bf16.pth"),
ModelConfig(model_id="Wan-AI/Wan2.1-T2V-1.3B", origin_file_pattern="Wan2.1_VAE.pth"),
],
)
video = pipe(
prompt="纪实摄影风格画面，一只活泼的小狗在绿茵茵的草地上迅速奔跑。小狗毛色棕黄，两只耳朵立起，神情专注而欢快。阳光洒在它身上，使得毛发看上去格外柔软而闪亮。背景是一片开阔的草地，偶尔点缀着几朵野花，远处隐约可见蓝天和几片白云。透视感鲜明，捕捉小狗奔跑时的动感和四周草地的生机。中景侧面移动视角。",
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",
seed=0, tiled=True,
)
save_video(video, "video.mp4", fps=15, quality=5)
Model Lineage
graph LR;
Wan-Series-->Wan2.1-Series;
Wan-Series-->Wan2.2-Series;
Wan2.1-Series-->Wan-AI/Wan2.1-T2V-1.3B;
Wan2.1-Series-->Wan-AI/Wan2.1-T2V-14B;
Wan-AI/Wan2.1-T2V-14B-->Wan-AI/Wan2.1-I2V-14B-480P;
Wan-AI/Wan2.1-I2V-14B-480P-->Wan-AI/Wan2.1-I2V-14B-720P;
Wan-AI/Wan2.1-T2V-14B-->Wan-AI/Wan2.1-FLF2V-14B-720P;
Wan-AI/Wan2.1-T2V-1.3B-->iic/VACE-Wan2.1-1.3B-Preview;
iic/VACE-Wan2.1-1.3B-Preview-->Wan-AI/Wan2.1-VACE-1.3B;
Wan-AI/Wan2.1-T2V-14B-->Wan-AI/Wan2.1-VACE-14B;
Wan-AI/Wan2.1-T2V-1.3B-->Wan2.1-Fun-1.3B-Series;
Wan2.1-Fun-1.3B-Series-->PAI/Wan2.1-Fun-1.3B-InP;
Wan2.1-Fun-1.3B-Series-->PAI/Wan2.1-Fun-1.3B-Control;
Wan-AI/Wan2.1-T2V-14B-->Wan2.1-Fun-14B-Series;
Wan2.1-Fun-14B-Series-->PAI/Wan2.1-Fun-14B-InP;
Wan2.1-Fun-14B-Series-->PAI/Wan2.1-Fun-14B-Control;
Wan-AI/Wan2.1-T2V-1.3B-->Wan2.1-Fun-V1.1-1.3B-Series;
Wan2.1-Fun-V1.1-1.3B-Series-->PAI/Wan2.1-Fun-V1.1-1.3B-Control;
Wan2.1-Fun-V1.1-1.3B-Series-->PAI/Wan2.1-Fun-V1.1-1.3B-InP;
Wan2.1-Fun-V1.1-1.3B-Series-->PAI/Wan2.1-Fun-V1.1-1.3B-Control-Camera;
Wan-AI/Wan2.1-T2V-14B-->Wan2.1-Fun-V1.1-14B-Series;
Wan2.1-Fun-V1.1-14B-Series-->PAI/Wan2.1-Fun-V1.1-14B-Control;
Wan2.1-Fun-V1.1-14B-Series-->PAI/Wan2.1-Fun-V1.1-14B-InP;
Wan2.1-Fun-V1.1-14B-Series-->PAI/Wan2.1-Fun-V1.1-14B-Control-Camera;
Wan-AI/Wan2.1-T2V-1.3B-->DiffSynth-Studio/Wan2.1-1.3b-speedcontrol-v1;
Wan-AI/Wan2.1-T2V-14B-->krea/krea-realtime-video;
Wan-AI/Wan2.1-I2V-14B-720P-->ByteDance/Video-As-Prompt-Wan2.1-14B;
Wan-AI/Wan2.1-T2V-14B-->Wan-AI/Wan2.2-Animate-14B;
Wan-AI/Wan2.1-T2V-14B-->Wan-AI/Wan2.2-S2V-14B;
Wan2.2-Series-->Wan-AI/Wan2.2-T2V-A14B;
Wan2.2-Series-->Wan-AI/Wan2.2-I2V-A14B;
Wan2.2-Series-->Wan-AI/Wan2.2-TI2V-5B;
Wan-AI/Wan2.2-T2V-A14B-->Wan2.2-Fun-Series;
Wan2.2-Fun-Series-->PAI/Wan2.2-VACE-Fun-A14B;
Wan2.2-Fun-Series-->PAI/Wan2.2-Fun-A14B-InP;
Wan2.2-Fun-Series-->PAI/Wan2.2-Fun-A14B-Control;
Wan2.2-Fun-Series-->PAI/Wan2.2-Fun-A14B-Control-Camera;