Instructions to use common-canvas/CommonCanvas-S-C with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use common-canvas/CommonCanvas-S-C with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("common-canvas/CommonCanvas-S-C", 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
possibility of making it possible to use controlnet with common canvas?
#1
by BriggoBoy - opened
not sure if this would work but it would be great :)
Agreed! I tried it out in ComfyUI and am just getting weird noise right now, or errors.
You'd have to effectively train new controlnet models to get it to work. I'd love to see some trained for both the SD2 and SDXL Common Canvas models.