---
datasets:
- Wild-Heart/Disney-VideoGeneration-Dataset
language:
- en
base_model:
- THUDM/CogVideoX-5b
pipeline_tag: text-to-video
library_name: diffusers
tags:
- text-to-video
- diffusers-training
- diffusers
- lora
- cogvideox
- cogvideox-diffusers
---
# CogVideoX LoRA Finetune

<Gallery />

## Model description

This is a lora finetune of the CogVideoX model `THUDM/CogVideoX-5b`.

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 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](https://huggingface.co/a-r-r-o-w/cogvideox-disney-adamw-4000-0.0003-constant/tree/main) in the Files & Versions tab.

## Usage

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

```py
import torch
from diffusers import CogVideoXPipeline
from diffusers.utils import export_to_video

pipe = CogVideoXPipeline.from_pretrained("THUDM/CogVideoX-5b", torch_dtype=torch.bfloat16).to("cuda")
pipe.load_lora_weights("a-r-r-o-w/cogvideox-disney-adamw-4000-0.0003-constant", weight_name="pytorch_lora_weights.safetensors", adapter_name="cogvideox-lora")

# The LoRA adapter weights are determined by what was used for training.
# In this case, we assume `--lora_alpha` is 32 and `--rank` is 64.
# It can be made lower or higher from what was used in training to decrease or amplify the effect
# of the LoRA upto a tolerance, beyond which one might notice no effect at all or overflows.
pipe.set_adapters(["cogvideox-lora"], [32 / 64])

video = pipe("BW_STYLE A black and white animated scene unfolds with an anthropomorphic goat surrounded by musical notes and symbols, suggesting a playful environment. Mickey Mouse appears, leaning forward in curiosity as the goat remains still. The goat then engages with Mickey, who bends down to converse or react. The dynamics shift as Mickey grabs the goat, potentially in surprise or playfulness, amidst a minimalistic background. The scene captures the evolving relationship between the two characters in a whimsical, animated setting, emphasizing their interactions and emotions", guidance_scale=6, use_dynamic_cfg=True).frames[0]
export_to_video(video, "output.mp4", fps=8)
```

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.

## License

Please adhere to the licensing terms as described [here](https://huggingface.co/THUDM/CogVideoX-5b/blob/main/LICENSE) and [here](https://huggingface.co/THUDM/CogVideoX-2b/blob/main/LICENSE).