Instructions to use gabehubner/vae-256px-8z with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use gabehubner/vae-256px-8z with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("gabehubner/vae-256px-8z", 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 gabehubner/vae-256px-8z: direct link, hf CLI and curl.
- Browser
- Download file 467 Bytes
-
https://huggingface.co/gabehubner/vae-256px-8z/resolve/main/vae_config.json
- Command line
-
hf download hf://gabehubner/vae-256px-8z/vae_config.json
-
curl -L -o vae_config.json https://huggingface.co/gabehubner/vae-256px-8z/resolve/main/vae_config.json
467 Bytes
| { | |
| "image_size": 256, | |
| "in_channels": 3, | |
| "out_channels": 3, | |
| "hidden_channels": 128, | |
| "num_res_blocks": 3, | |
| "channel_multipliers": [ | |
| 1, | |
| 2, | |
| 2, | |
| 4, | |
| 4 | |
| ], | |
| "attention_resolutions": [ | |
| 32 | |
| ], | |
| "dropout": 0.0, | |
| "use_checkpoint": false, | |
| "use_fp16": false, | |
| "resblock_updown": true, | |
| "z_channels": 8, | |
| "double_z": true, | |
| "位_recon": 1.0, | |
| "位_kl": 1e-6, | |
| "位_lpips": 1.0, | |
| "位_id": 0.1, | |
| "位_gan": 0.5, | |
| "gan_start_step": 50000 | |
| } |