Spark-Wan
Collection
1 item • Updated
import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("chestnutlzj/Spark-Wan-4Steps", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]📰 News
[2025.9.26] 🔥🔥🔥 Release 4-steps model in huggingface.
[2025.9.26] 🔥🔥🔥 We open-source the distillation weights for 8-steps and 4-steps based on Wan2.1 14B, as well as the training code.
https://github.com/PKU-YuanGroup/Spark-Wan
🚀 Main Results
| Step4 | ||
|---|---|---|
- Downloads last month
- 18
Model tree for chestnutlzj/Spark-Wan-4Steps
Base model
Wan-AI/Wan2.1-T2V-14B