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("jerrrycans/watermark20000x2")
prompt = "remove all the watermarks from this image, all watermarks that are over this image, text watermarks, logo watermarks etc"
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]Watermark20000X2
About this LoRA
This is a LoRA for the FLUX.1-Kontext-dev image-to-image model. It can be used with diffusers or ComfyUI.
It was trained on Replicate using: https://replicate.com/replicate/fast-flux-kontext-trainer/train
Prompt instruction
You should use remove all the watermarks from this image, all watermarks that are over this image, text watermarks, logo watermarks etc as part of the prompt instruction for your image-to-image editing.
Training details
- Steps: 20000
- Learning rate: 0.001
- LoRA rank: 16
Contribute your own examples
You can use the community tab to add images that show off what you’ve made with this LoRA.
- Downloads last month
- 24
Model tree for jerrrycans/watermark20000x2
Base model
black-forest-labs/FLUX.1-Kontext-dev