Instructions to use Shakker-Labs/FLUX.1-dev-ControlNet-Union-Pro-2.0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Shakker-Labs/FLUX.1-dev-ControlNet-Union-Pro-2.0 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Shakker-Labs/FLUX.1-dev-ControlNet-Union-Pro-2.0", 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
Why remove the tile controlnet?
Hey thanks for your work, was just wondering why the tile controlnet was removed since there is no standalone tile for flux?
In our training, we find that adding tile harms the performance of other conds. For standaline tile, you can use older version of union or jasperai/Flux.1-dev-Controlnet-Upscaler
In our training, we find that adding tile harms the performance of other conds. For standaline tile, you can use older version of union or jasperai/Flux.1-dev-Controlnet-Upscaler
Thank you for your work. Would you consider separating tile as an individual model?
In our training, we find that adding tile harms the performance of other conds. For standaline tile, you can use older version of union or jasperai/Flux.1-dev-Controlnet-Upscaler
Thank you for your work. Would you consider separating tile as an individual model?
Agreed on this suggestion - maybe it can stand on its own for those that need it now and then?