Instructions to use fal/Wojak-Kontext-Dev-LoRA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use fal/Wojak-Kontext-Dev-LoRA with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline from diffusers.utils import load_image # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("black-forest-labs/FLUX.1-Kontext-dev", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("fal/Wojak-Kontext-Dev-LoRA") prompt = "Convert to wojak style drawing" input_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/cat.png") image = pipe(image=input_image, prompt=prompt).images[0] - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
metadata
tags:
- flux
- image-to-image
- lora
- diffusers
- fal
base_model: black-forest-labs/FLUX.1-Kontext-dev
instance_prompt: Convert to wojak style drawing
license: other
license_name: flux1-dev-non-commercial-license
license_link: >-
https://huggingface.co/black-forest-labs/FLUX.1-Kontext-dev/blob/main/LICENSE.md
widget:
- text: Convert to wojak style drawing
output:
url: images/1.png
- src: inputs/1.jpg
prompt: Convert to wojak style drawing
output:
url: images/1.png
- text: Convert to wojak style drawing
output:
url: images/2.png
- src: inputs/2.png
prompt: Convert to wojak style drawing
output:
url: images/2.png
- text: Convert to wojak style drawing
output:
url: images/3.png
- src: inputs/3.webp
prompt: Convert to wojak style drawing
output:
url: images/3.png
Wojak Kontext Dev LoRA

- Prompt
- Convert to wojak style drawing

- Prompt
- Convert to wojak style drawing

- Prompt
- Convert to wojak style drawing
Model description
Trigger phrase
Convert to wojak style drawing
Download model
Weights for this model are available in Safetensors format.
Training at fal.ai
Training was done using fal.ai/models/fal-ai/flux-kontext-trainer/playground.