from diffusers import MochiPipeline
from diffusers.utils import export_to_video
pipe = MochiPipeline.from_pretrained(VikramSingh178/mochi-diffuser-bf16, torch_dtype=torch.bfloat16)
pipe.to("cuda")
prompt = "A beautiful sunset over the mountains"
frames = pipe(prompt, num_inference_steps=50, guidance_scale=4.5,num_frames=61,generator=torch.Generator(device="cuda").manual_seed(42),).frames[0]
export_to_video(frames, "sunset.mp4")
- Downloads last month
- 105
Inference API (serverless) does not yet support diffusers models for this pipeline type.
Model tree for VikramSingh178/mochi-diffuser-bf16
Base model
genmo/mochi-1-preview