Text-to-Video
Diffusers
TuneAVideoPipeline
tune-a-video
redshift-man-skiing / README.md
hysts's picture
hysts HF staff
Update README.md
9cf1a15
---
license: creativeml-openrail-m
base_model: nitrosocke/redshift-diffusion
training_prompt: A man is skiing.
tags:
- tune-a-video
- text-to-video
- diffusers
inference: false
---
# Tune-A-Video - Redshift
## Model Description
- Base model: [nitrosocke/redshift-diffusion](https://huggingface.co./nitrosocke/redshift-diffusion)
- Training prompt: a man is skiing.
![sample-train](samples/train.gif)
## Samples
![sample-500](samples/sample-500.gif)
Test prompt: (redshift style) [spider man/black widow/batman/hulk] is skiing.
## Usage
Clone the [github repo](https://github.com/showlab/Tune-A-Video)
```bash
git clone https://github.com/showlab/Tune-A-Video.git
```
Run inference code
```python
from tuneavideo.pipelines.pipeline_tuneavideo import TuneAVideoPipeline
from tuneavideo.models.unet import UNet3DConditionModel
from tuneavideo.util import save_videos_grid
import torch
pretrained_model_path = "nitrosocke/redshift-diffusion"
unet_model_path = "Tune-A-Video-library/redshift-man-skiing"
unet = UNet3DConditionModel.from_pretrained(unet_model_path, subfolder='unet', torch_dtype=torch.float16).to('cuda')
pipe = TuneAVideoPipeline.from_pretrained(pretrained_model_path, unet=unet, torch_dtype=torch.float16).to("cuda")
pipe.enable_xformers_memory_efficient_attention()
prompt = "(redshift style) spider man is skiing"
video = pipe(prompt, video_length=8, height=512, width=512, num_inference_steps=50, guidance_scale=7.5).videos
save_videos_grid(video, f"./{prompt}.gif")
```
## Related Papers:
- [Tune-A-Video](https://arxiv.org/abs/2212.11565): One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation
- [Stable Diffusion](https://arxiv.org/abs/2112.10752): High-Resolution Image Synthesis with Latent Diffusion Models