Instructions to use DiffusersVersionsOfModels/sana-1.6b-1024px with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use DiffusersVersionsOfModels/sana-1.6b-1024px with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("DiffusersVersionsOfModels/sana-1.6b-1024px", 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
- Local Apps Settings
- Draw Things
- DiffusionBee
Download vae/config.json from DiffusersVersionsOfModels/sana-1.6b-1024px: direct link, hf CLI and curl.
- Browser
- Download file 974 Bytes
-
https://huggingface.co/DiffusersVersionsOfModels/sana-1.6b-1024px/resolve/refs%2Fpr%2F1/vae/config.json
- Command line
-
hf download hf://DiffusersVersionsOfModels/sana-1.6b-1024px@refs/pr/1/vae/config.json
-
curl -L -o config.json https://huggingface.co/DiffusersVersionsOfModels/sana-1.6b-1024px/resolve/refs%2Fpr%2F1/vae/config.json
974 Bytes
| { | |
| "_class_name": "DCAE", | |
| "_diffusers_version": "0.32.0.dev0", | |
| "_name_or_path": "Efficient-Large-Model/dc_ae_f32c32_sana_1.0_diffusers", | |
| "decoder_act": "silu", | |
| "decoder_block_type": [ | |
| "ResBlock", | |
| "ResBlock", | |
| "ResBlock", | |
| "EViTS5GLU", | |
| "EViTS5GLU", | |
| "EViTS5GLU" | |
| ], | |
| "decoder_depth_list": [ | |
| 3, | |
| 3, | |
| 3, | |
| 3, | |
| 3, | |
| 3 | |
| ], | |
| "decoder_norm": "rms2d", | |
| "decoder_width_list": [ | |
| 128, | |
| 256, | |
| 512, | |
| 512, | |
| 1024, | |
| 1024 | |
| ], | |
| "downsample_block_type": "Conv", | |
| "encoder_act": "silu", | |
| "encoder_block_type": [ | |
| "ResBlock", | |
| "ResBlock", | |
| "ResBlock", | |
| "EViTS5GLU", | |
| "EViTS5GLU", | |
| "EViTS5GLU" | |
| ], | |
| "encoder_depth_list": [ | |
| 2, | |
| 2, | |
| 2, | |
| 3, | |
| 3, | |
| 3 | |
| ], | |
| "encoder_norm": "rms2d", | |
| "encoder_width_list": [ | |
| 128, | |
| 256, | |
| 512, | |
| 512, | |
| 1024, | |
| 1024 | |
| ], | |
| "in_channels": 3, | |
| "latent_channels": 32, | |
| "scaling_factor": 0.41407, | |
| "upsample_block_type": "InterpolateConv" | |
| } | |