Instructions to use SurjoLabs/Surjo-Image-Preview with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use SurjoLabs/Surjo-Image-Preview with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("SurjoLabs/Surjo-Image-Preview", 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 config.json from SurjoLabs/Surjo-Image-Preview: direct link, hf CLI and curl.
- Browser
- Download file 511 Bytes
-
https://huggingface.co/SurjoLabs/Surjo-Image-Preview/resolve/main/config.json
- Command line
-
hf download hf://SurjoLabs/Surjo-Image-Preview/config.json
-
curl -L -o config.json https://huggingface.co/SurjoLabs/Surjo-Image-Preview/resolve/main/config.json
511 Bytes
| { | |
| "_class_name": "SurjoImagePreviewDiT", | |
| "auto_map": { | |
| "AutoModel": "modeling_surjo_image_preview.SurjoImagePreviewDiT" | |
| }, | |
| "deepsup": true, | |
| "dim": 512, | |
| "freq_dim": 256, | |
| "heads": 8, | |
| "in_ch": 128, | |
| "loop_iters": 2, | |
| "mlp_ratio": 4.0, | |
| "model_type": "surjo_image_preview", | |
| "n_tokens": 256, | |
| "repa_dim": 384, | |
| "rope_theta": 10000.0, | |
| "split": [ | |
| 7, | |
| 4, | |
| 7 | |
| ], | |
| "t_scale": 1000.0, | |
| "text_dim": 1024, | |
| "transformers_version": "5.13.1", | |
| "xsa": true | |
| } |