🚩 Report
The Code doesn't works: from diffusers import DiffusionPipeline
pipe = DiffusionPipeline.from_pretrained("stepfun-ai/stepvideo-t2v")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]
It gives error: ValueError: scheduler/stepvideo.py as defined in model_index.json does not exist in stepfun-ai/stepvideo-t2v and is not a module in 'diffusers/pipelines'.
Here's a polished version of your text with clearer technical communication:
To download the model checkpoint, execute the following command in your terminal:
huggingface-cli download stepfun-ai/stepvideo-t2v --local-dir [YOUR_DIRECTORY]
For multi-GPU inference configurations, please follow the instructions detailed in our model card.
We additionally provide a quantized model variant that enables single-GPU deployment with reduced VRAM requirements. Implementation specifics for this optimized version can be found in our GitHub repository documentation.😊