Instructions to use kandinskylab/tiny-kandinsky-s2v-modular-pipe with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use kandinskylab/tiny-kandinsky-s2v-modular-pipe with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("kandinskylab/tiny-kandinsky-s2v-modular-pipe", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
Download vae/config.json from kandinskylab/tiny-kandinsky-s2v-modular-pipe: direct link, hf CLI and curl.
- Browser
- Download file 637 Bytes
-
https://huggingface.co/kandinskylab/tiny-kandinsky-s2v-modular-pipe/resolve/main/vae/config.json
- Command line
-
hf download hf://kandinskylab/tiny-kandinsky-s2v-modular-pipe/vae/config.json
-
curl -L -o config.json https://huggingface.co/kandinskylab/tiny-kandinsky-s2v-modular-pipe/resolve/main/vae/config.json
637 Bytes
| { | |
| "_class_name": "AutoencoderKLHunyuanVideo", | |
| "_diffusers_version": "0.40.0", | |
| "act_fn": "silu", | |
| "block_out_channels": [ | |
| 8, | |
| 8, | |
| 8 | |
| ], | |
| "down_block_types": [ | |
| "HunyuanVideoDownBlock3D", | |
| "HunyuanVideoDownBlock3D", | |
| "HunyuanVideoDownBlock3D" | |
| ], | |
| "in_channels": 3, | |
| "latent_channels": 4, | |
| "layers_per_block": 1, | |
| "mid_block_add_attention": false, | |
| "norm_num_groups": 4, | |
| "out_channels": 3, | |
| "scaling_factor": 0.476986, | |
| "spatial_compression_ratio": 8, | |
| "temporal_compression_ratio": 4, | |
| "up_block_types": [ | |
| "HunyuanVideoUpBlock3D", | |
| "HunyuanVideoUpBlock3D", | |
| "HunyuanVideoUpBlock3D" | |
| ] | |
| } | |