Instructions to use davisbro/half_illustration with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use davisbro/half_illustration with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("davisbro/half_illustration") prompt = "In the style of TOK, a photo editorial avant-garde dramatic action pose of a woman short blue hair wearing 70s round wacky sunglasses pulling glasses down looking forward, in Tokyo with large marble structures and bonsai trees at sunset with a vibrant illustrated jacket surrounded by illustrations of flowers, smoke, flames, ice cream, sparkles, rock and roll" image = pipe(prompt).images[0] - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
- DiffusionBee
Add tags for better discoverability and integration
#1
by multimodalart HF Staff - opened
This PRs add meta-tags to display the model as an adapter and help discoverability, ecosystem integration and diffusers compatibility
Besides this PR, we would suggest that a cool model card is built so folks can see examples/interact more, check out this as an example:
This is super helpful, going to use those as a template to make it more discoverable.
Thank you!
Awesome! The most important tags are
- diffusers
- lora
without those - even with the base_modeltag, the model doesn't recognize the parent in the model tree structure
And with the </gallery> widget, you can have nice image previews like in the frosting lane example!
