Instructions to use DFloat11/FLUX.1-Krea-dev-DF11 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use DFloat11/FLUX.1-Krea-dev-DF11 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("DFloat11/FLUX.1-Krea-dev-DF11", 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
ComfyUI?
How do you use it in ComfyUI?
You do not, because DF11 only works with the transformers and diffusers library for now. Hopefully wider software integration will happen soon.
@Hesajon Just in case you missed it, it is now possible to use this model in ComfyUI now, just follow the instructions and download the weights from here: https://huggingface.co/DFloat11/FLUX.1-Krea-dev-DF11-ComfyUI. I also have a bunch of other DF11 models, but the current implementation of the official DF11 custom node (as well as the tensor naming format) requires that DF11 models for ComfyUI and diffusers have to be created separately, which I am rather reluctant to do so (and the original developer has only created 1 such DF11 model for ComfyUI so far).
Currently, I have created 2 more ComfyUI-compatible DF11 models (3 if you are ok with manually patching the code to add Chroma support, otherwise only Flux-based models are supported). Do check out my profile here: https://huggingface.co/mingyi456