Instructions to use lucataco/flux-queso with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use lucataco/flux-queso with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("lucataco/flux-queso") prompt = "a portrait photo of TOK" image = pipe(prompt).images[0] - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Issue with dog color
#1
by ogupavel - opened
I am facing an issue with the color of a dog when I try to train it. Looks like you face the same. I am using this model on Replicate: https://replicate.com/lucataco/flux-dev-lora and this LoRA you trained: https://huggingface.co/lucataco/flux-queso/.
In the attached files, I have included an example of a generation where the simple prompt 'a portrait photo of TOK' shows a different color. Does anyone know how to fix this?
