Instructions to use ostris/sketch_to_image_klein_4b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use ostris/sketch_to_image_klein_4b 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.2-klein-base-4B", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("ostris/sketch_to_image_klein_4b") prompt = "-" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
- DiffusionBee
Sketch to Image - Klein 4b

- Prompt
- -
Model description
This is a modern controlnet LoRA that contains two LoRAs, an image to sketch `sketch_generator_klein_4b.safetensors` and a sketch to image `sketch_to_image_klein_4b.safetensors`. They can be used separately or in a chain to function as a control generator and controlnet. These LoRAs were trained while filming a tutorial How to Train a ControlNet in AI Toolkit. Check out that video for more info.
Download model
Download them in the Files & versions tab.
- Downloads last month
- 82
Model tree for ostris/sketch_to_image_klein_4b
Base model
black-forest-labs/FLUX.2-klein-base-4B