README.md

metadata

base_model: genmo/mochi-1-preview
library_name: diffusers
license: apache-2.0
instance_prompt: >-
  There is a *crab* blending into a +rocky ocean floor+ where the crab's mottled
  brown shell, rough texture, and uneven shape closely match the scattered rocks
  and coarse sand, all in muted brown and grey tones. The crab moves slowly and
  subtly, making it difficult to distinguish as its rough brown pattern looks
  just like a piece of rock among the uneven, similarly colored stones and
  patches of sand.
widget:
  - text: >-
      There is a *crab* blending into a +rocky ocean floor+ where the crab's
      mottled brown shell, rough texture, and uneven shape closely match the
      scattered rocks and coarse sand, all in muted brown and grey tones. The
      crab moves slowly and subtly, making it difficult to distinguish as its
      rough brown pattern looks just like a piece of rock among the uneven,
      similarly colored stones and patches of sand.
    output:
      url: final_video_0.mp4
tags:
  - text-to-video
  - diffusers-training
  - diffusers
  - lora
  - mochi-1-preview
  - mochi-1-preview-diffusers
  - template:sd-lora
  - text-to-video
  - diffusers-training
  - diffusers
  - lora
  - mochi-1-preview
  - mochi-1-preview-diffusers
  - template:sd-lora

Mochi-1 Preview LoRA Finetune

Prompt

There is a *crab* blending into a +rocky ocean floor+ where the crab's mottled brown shell, rough texture, and uneven shape closely match the scattered rocks and coarse sand, all in muted brown and grey tones. The crab moves slowly and subtly, making it difficult to distinguish as its rough brown pattern looks just like a piece of rock among the uneven, similarly colored stones and patches of sand.

Model description

This is a lora finetune of the Mochi-1 preview model genmo/mochi-1-preview.

The model was trained using CogVideoX Factory - a repository containing memory-optimized training scripts for the CogVideoX and Mochi family of models using TorchAO and DeepSpeed. The scripts were adopted from CogVideoX Diffusers trainer.

Download model

Download LoRA in the Files & Versions tab.

Usage

Requires the 🧨 Diffusers library installed.

from diffusers import MochiPipeline
from diffusers.utils import export_to_video
import torch 

pipe = MochiPipeline.from_pretrained("genmo/mochi-1-preview")
pipe.load_lora_weights("CHANGE_ME")
pipe.enable_model_cpu_offload()

with torch.autocast("cuda", torch.bfloat16):
    video = pipe(
        prompt="CHANGE_ME",
        guidance_scale=6.0,
        num_inference_steps=64,
        height=480,
        width=848,
        max_sequence_length=256,
        output_type="np"
    ).frames[0]
export_to_video(video)

For more details, including weighting, merging and fusing LoRAs, check the documentation on loading LoRAs in diffusers.

Intended uses & limitations

How to use

# TODO: add an example code snippet for running this diffusion pipeline

Limitations and bias

[TODO: provide examples of latent issues and potential remediations]

Training details

[TODO: describe the data used to train the model]