Instructions to use HaileyStorm/FLUX.1-Merges with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use HaileyStorm/FLUX.1-Merges with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("HaileyStorm/FLUX.1-Merges", 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
Model loading / 1 file versions
#1
by Mikerhinos - opened
Hi, do you have any info on how to load these 3 files versions in ComfyUI ?
Or when the single file versions will be available on Civitai ?
Just saw the combining py file sorry :/
Mikerhinos changed discussion status to closed
You’re good!
The 10:1 is uploading to Civit now, but it’s taking forever. Rest will follow, hopefully all today. Might be easier to use that combine script though.
I'm going around updating people because Comfy will now load the single fine version of these models! No changes necessary. See https://github.com/comfyanonymous/ComfyUI/commit/75b9b55b221fc95f7137a91e2349e45693e342b8
For you, the point of the update is also: those files have long since finished uploading to Civit. I'm also planning on merging fp8 versions.