Image-to-Video
Diffusers
Safetensors
Kandinsky6TI2VAPipeline
video
video-generation
text-to-video
audio-generation
kandinsky
Instructions to use kandinskylab/Kandinsky-6.0-Pro-distill-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-Pro-distill-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-Pro-distill-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 vocoder/config.json from kandinskylab/Kandinsky-6.0-Pro-distill-5s-Diffusers: direct link, hf CLI and curl.
- Browser
- Download file 483 Bytes
-
https://huggingface.co/kandinskylab/Kandinsky-6.0-Pro-distill-5s-Diffusers/resolve/main/vocoder/config.json
- Command line
-
hf download hf://kandinskylab/Kandinsky-6.0-Pro-distill-5s-Diffusers/vocoder/config.json
-
curl -L -o config.json https://huggingface.co/kandinskylab/Kandinsky-6.0-Pro-distill-5s-Diffusers/resolve/main/vocoder/config.json
483 Bytes
| { | |
| "_class_name": "MMAudioVocoder", | |
| "_diffusers_version": "0.40.0.dev0", | |
| "num_mels": 128, | |
| "resblock_dilation_sizes": [ | |
| [ | |
| 1, | |
| 3, | |
| 5 | |
| ], | |
| [ | |
| 1, | |
| 3, | |
| 5 | |
| ], | |
| [ | |
| 1, | |
| 3, | |
| 5 | |
| ] | |
| ], | |
| "resblock_kernel_sizes": [ | |
| 3, | |
| 7, | |
| 11 | |
| ], | |
| "upsample_initial_channel": 1536, | |
| "upsample_kernel_sizes": [ | |
| 16, | |
| 8, | |
| 4, | |
| 4, | |
| 4, | |
| 4 | |
| ], | |
| "upsample_rates": [ | |
| 8, | |
| 4, | |
| 2, | |
| 2, | |
| 2, | |
| 2 | |
| ] | |
| } | |