---
base_model: genmo/mochi-1-preview
library_name: diffusers
license: apache-2.0
instance_prompt: A pristine snowglobe featuring a winter scene sits peacefully. The
  globe violently explodes, sending glass, water, and glittering fake snow in all
  directions. The scene is captured with high-speed photography.
widget:
- text: A pristine snowglobe featuring a winter scene sits peacefully. The globe violently
    explodes, sending glass, water, and glittering fake snow in all directions. The
    scene is captured with high-speed photography.
  output:
    url: final_video_0.mp4
tags:
- text-to-video
- diffusers-training
- diffusers
- lora
- mochi-1-preview
- mochi-1-preview-diffusers
- template:sd-lora
---

<!-- This model card has been generated automatically according to the information the training script had access to. You
should probably proofread and complete it, then remove this comment. -->


# Mochi-1 Preview LoRA Finetune

<Gallery />

## Model description

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

The model was trained using [CogVideoX Factory](https://github.com/a-r-r-o-w/cogvideox-factory) - a repository containing memory-optimized training scripts for the CogVideoX and Mochi family of models using [TorchAO](https://github.com/pytorch/ao) and [DeepSpeed](https://github.com/microsoft/DeepSpeed). The scripts were adopted from [CogVideoX Diffusers trainer](https://github.com/huggingface/diffusers/blob/main/examples/cogvideo/train_cogvideox_lora.py).

## Download model

[Download LoRA](sayakpaul/mochi-lora-dissolve/tree/main) in the Files & Versions tab.

## Usage

Requires the [🧨 Diffusers library](https://github.com/huggingface/diffusers) installed.

```py
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](https://huggingface.co/docs/diffusers/main/en/using-diffusers/loading_adapters) on loading LoRAs in diffusers.



## Intended uses & limitations

#### How to use

```python
# 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]