How to use stepfun-ai/stepvideo-t2v with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("stepfun-ai/stepvideo-t2v", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0]
When I use SGLANG diffusion, I get this error:
File "/home/roywan/sglang/python/sglang/multimodal_gen/runtime/pipelines/stepvideo_pipeline.py", line 147, in load_modules raise ValueError( ValueError: model_index.json must contain a vae module
· Sign up or log in to comment
