HanLiii/mochi-1-preview-diffusers

Diffusers formation for mochi-1-preview model.

Use following code to inference

import torch 
from diffusers import MochiPipeline
from diffusers.utils import export_to_video
pipe = MochiPipeline.from_pretrained('HanLiii/mochi-1-preview-diffusers', torch_dtype=torch.bfloat16)
pipe.to("cuda")
prompt = """
A hand with delicate fingers picks up a bright yellow lemon from a wooden bowl 
filled with lemons and sprigs of mint against a peach-colored background. 
The hand gently tosses the lemon up and catches it, showcasing its smooth texture. 
A beige string bag sits beside the bowl, adding a rustic touch to the scene. 
Additional lemons, one halved, are scattered around the base of the bowl. 
The even lighting enhances the vibrant colors and creates a fresh, 
inviting atmosphere.
"""
frames = pipe(prompt, 
    num_inference_steps=64, 
    guidance_scale=4.5,
    num_frames=61,
    generator=torch.Generator(device="cuda").manual_seed(42),
).frames[0]
export_to_video(frames, "mochi_test.mp4")

bf16 diffusers version result(num_frames=61):

github version result(num_frames=163):

---

license: apache-2.0