Instructions to use kandinskylab/Kandinsky-S2V-1.0-Pro-Diffusers with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use kandinskylab/Kandinsky-S2V-1.0-Pro-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-S2V-1.0-Pro-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
Kandinsky-S2V-1.0-Pro-Diffusers: from kandinskylab/Kandinsky-6.0-S2V-Pro-Diffusers@3c0b4f4b0d, renamed for Kandinsky S2V 1.0
9383aa1 verified Download tokenizer_2/tokenizer_config.json from kandinskylab/Kandinsky-S2V-1.0-Pro-Diffusers: direct link, hf CLI and curl.
- Browser
- Download file 350 Bytes
-
https://huggingface.co/kandinskylab/Kandinsky-S2V-1.0-Pro-Diffusers/resolve/main/tokenizer_2/tokenizer_config.json
- Command line
-
hf download hf://kandinskylab/Kandinsky-S2V-1.0-Pro-Diffusers/tokenizer_2/tokenizer_config.json
-
curl -L -o tokenizer_config.json https://huggingface.co/kandinskylab/Kandinsky-S2V-1.0-Pro-Diffusers/resolve/main/tokenizer_2/tokenizer_config.json
350 Bytes
| { | |
| "add_prefix_space": false, | |
| "backend": "tokenizers", | |
| "bos_token": "<|startoftext|>", | |
| "do_lower_case": true, | |
| "eos_token": "<|endoftext|>", | |
| "errors": "replace", | |
| "is_local": true, | |
| "local_files_only": false, | |
| "model_max_length": 77, | |
| "pad_token": "<|endoftext|>", | |
| "tokenizer_class": "CLIPTokenizer", | |
| "unk_token": "<|endoftext|>" | |
| } | |