Image-to-Video
Diffusers
Safetensors
Kandinsky6TI2VAPipeline
video
video-generation
text-to-video
audio-generation
kandinsky
Instructions to use kandinskylab/Kandinsky-6.0-Lite-5s-Diffusers with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use kandinskylab/Kandinsky-6.0-Lite-5s-Diffusers with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline from diffusers.utils import load_image, export_to_video # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("kandinskylab/Kandinsky-6.0-Lite-5s-Diffusers", dtype=torch.bfloat16, device_map="cuda") pipe.to("cuda") prompt = "A man with short gray hair plays a red electric guitar." image = load_image( "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/guitar-man.png" ) output = pipe(image=image, prompt=prompt).frames[0] export_to_video(output, "output.mp4") - Notebooks
- Google Colab
- Kaggle
Download text_encoder/generation_config.json from kandinskylab/Kandinsky-6.0-Lite-5s-Diffusers: direct link, hf CLI and curl.
- Browser
- Download file 216 Bytes
-
https://huggingface.co/kandinskylab/Kandinsky-6.0-Lite-5s-Diffusers/resolve/main/text_encoder/generation_config.json
- Command line
-
hf download hf://kandinskylab/Kandinsky-6.0-Lite-5s-Diffusers/text_encoder/generation_config.json
-
curl -L -o generation_config.json https://huggingface.co/kandinskylab/Kandinsky-6.0-Lite-5s-Diffusers/resolve/main/text_encoder/generation_config.json
216 Bytes
| { | |
| "bos_token_id": 151643, | |
| "pad_token_id": 151643, | |
| "do_sample": true, | |
| "eos_token_id": [ | |
| 151645, | |
| 151643 | |
| ], | |
| "repetition_penalty": 1.05, | |
| "temperature": 0.000001, | |
| "transformers_version": "4.37.0" | |
| } |