Instructions to use ogkalu/Comic-Diffusion with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use ogkalu/Comic-Diffusion with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("ogkalu/Comic-Diffusion", 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
- Draw Things
- DiffusionBee
| license: creativeml-openrail-m | |
| tags: | |
| - text-to-image | |
| V2 is here. Trained on 6 styles at once, it allows anyone to create unique but consistent styles by mixing any number of the tokens. Even changing the order of the same list influences results so there's a lot to experiment with here. This was created so anyone could create their comic projects with ease and flexibility. It is the culmination of all my experimentation with dreambooth thus far. | |
| The tokens for V2 are - | |
| - charliebo artstyle | |
| - holliemengert artstyle | |
| - marioalberti artstyle | |
| - pepelarraz artstyle | |
| - andreasrocha artstyle | |
| - jamesdaly artstyle | |
| None of the artists used are affiliated with this. | |
| **Generated by V2:** | |
|  | |
|  | |
|  | |
|  | |
| V1 was trained solely on James Daly 3. He is **not** affiliated with this. The correct token for V1 is comicmay artsyle. | |
| **Generated by V1:** | |
|  | |
|  | |
|  | |
|  | |
|  |