Instructions to use Kontext-Style/Vector_lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Kontext-Style/Vector_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("Kontext-Style/Vector_lora") prompt = "Turn this cat into a dog" 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
Comfyui setup
I want to use this model with ComfyUI, but I don’t really know how to set up the node system properly. This is my current node setup (screenshot attached), but it doesn’t give the correct output/response.
Can someone help me figure out what I’m doing wrong?
not know pretty so how to setup node system my node system is this but not response correct response
Hi @mbilalbark ,
Thanks for your feedback! We're not very familiar with ComfyUI either, but you can check out our demo space at Kontext-Style/Kontext-Style-LoRAs for the correct prompt usage. Alternatively, you can discuss with other ComfyUI users in this thread: Owen777/Kontext-Style-Loras/discussions/2#689c0a206d7a663bcb95716c for more insights.
Let us know if you need further assistance!