Instructions to use Uglehs/Badly-Drawn-Flux with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Uglehs/Badly-Drawn-Flux 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("Uglehs/Badly-Drawn-Flux") prompt = "An MS Paint emoji of a green box-shaped dragon, the dragon has two white fangs, two white horns, a long mouth, box-shaped, waist-up, of him with his high arms spread out and a rainbow going from one hand to the other, against a white background, it is badly drawn emoji" image = pipe(prompt).images[0] - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
- DiffusionBee
Badly Drawn Lora

- Prompt
- An MS Paint emoji of a green box-shaped dragon, the dragon has two white fangs, two white horns, a long mouth, box-shaped, waist-up, of him with his high arms spread out and a rainbow going from one hand to the other, against a white background, it is badly drawn emoji
Model description
Credit to 7Zack on CivitAI
Trigger words
You should use It is badly drawn. The image is a minimalist to trigger the image generation.
You should use scribbled lines to trigger the image generation.
You should use hand-drawn sketch of a to trigger the image generation.
Download model
Weights for this model are available in Safetensors format.
Download them in the Files & versions tab.
- Downloads last month
- 14
Model tree for Uglehs/Badly-Drawn-Flux
Base model
black-forest-labs/FLUX.1-dev