Upload README.md

README.md

@@ -1,3 +1,56 @@
 ---
 license: mit
+base_model: Bingsu/my-korean-stable-diffusion-v1-5
+training_prompt: A rabbit is eating a watermelon on the table
+tags:
+- tune-a-video
+- text-to-video
+- diffusers
+- korean
+inference: false
 ---
+
+# Tune-A-VideKO - Korean Stable Diffusion v1-5
+
+## Model Description
+- Base model: [Bingsu/my-korean-stable-diffusion-v1-5](https://huggingface.co/Bingsu/my-korean-stable-diffusion-v1-5)
+- Training prompt: A rabbit is eating a watermelon on the table
+![sample-train](samples/rabbit.gif)
+
+## Samples
+
+![sample-500](samples/video4.gif)
+Test prompt: 고양이가 해변에서 수박을 먹고 있습니다
+
+![sample-500](samples/video5.gif)
+Test prompt: 강아지가 오렌지를 먹고 있습니다
+
+## Usage
+Clone the github repo
+```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 = "Bingsu/my-korean-stable-diffusion-v1-5"
+unet_model_path = "kyujinpy/Tune-A-VideoKO-v1-5"
+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 = "강아지가 만화 스타일로 상자를 먹고 있습니다"
+video = pipe(prompt, video_length=8, height=512, width=512, num_inference_steps=50, guidance_scale=12.5).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