Instructions to use luccazai/sana_manga with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use luccazai/sana_manga with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Efficient-Large-Model/Sana_1600M_1024px", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("luccazai/sana_manga") prompt = "a destroyed building, manga style artwork in the style of sks" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
sana manga finetuning

- Prompt
- a destroyed building, manga style artwork in the style of sks
Model description
SANA 1.6B Finetuning with Ophiscus/MangaImageDataset dataset. 2500 epochs, with prior preservation
Download model
Download them in the Files & versions tab.
- Downloads last month
- 6
Model tree for luccazai/sana_manga
Unable to build the model tree, the base model loops to the model itself. Learn more.