Kontext-Watermark-Remover API & Inference Endpoint

Sample Inferences : Demo

Quick start with diffusers🧨

Required Packages

markdown
!pip install diffusers torch gradio transformers
!pip install pillow gradio-imageslider huggingface_hub
!pip install sentencepiece spaces peft torchvision accelerate

Run Demo

py
import os
import gradio as gr
import numpy as np
import spaces
import torch
import random
from PIL import Image
from typing import Iterable

from diffusers import FluxKontextPipeline
from diffusers.utils import load_image
from huggingface_hub import hf_hub_download
from gradio_imageslider import ImageSlider

device = torch.device("cuda" if torch.cuda.is_available() else "cpu")

# --- Main Model Initialization ---
MAX_SEED = np.iinfo(np.int32).max
pipe = FluxKontextPipeline.from_pretrained("black-forest-labs/FLUX.1-Kontext-dev", torch_dtype=torch.bfloat16).to("cuda")

# --- Load New Adapter ---
pipe.load_lora_weights("prithivMLmods/Kontext-Watermark-Remover", weight_name="Kontext-Watermark-Remover.safetensors", adapter_name="watermark_remover")


@spaces.GPU
def infer(input_image, prompt, seed=42, randomize_seed=False, guidance_scale=2.5, steps=28, progress=gr.Progress(track_tqdm=True)):
    """
    Perform image editing, returning a pair for the ImageSlider.
    """
    if not input_image:
        raise gr.Error("Please upload an image for editing.")

    pipe.set_adapters(["watermark_remover"], adapter_weights=[1.0])

    if randomize_seed:
        seed = random.randint(0, MAX_SEED)
    
    original_image = input_image.copy().convert("RGB")
    
    image = pipe(
        image=original_image, 
        prompt=prompt,
        guidance_scale=guidance_scale,
        width = original_image.size[0],
        height = original_image.size[1],
        num_inference_steps=steps,
        generator=torch.Generator().manual_seed(seed),
    ).images[0]

    return (original_image, image), seed, gr.Button(visible=True)

css="""
#col-container {
    margin: 0 auto;
    max-width: 960px;
}
#main-title h1 {font-size: 2.1em !important;}
"""

with gr.Blocks(css=css) as demo:
    
    with gr.Column(elem_id="col-container"):
        gr.Markdown("# **Photo-Mate-i2i: Watermark Remover**", elem_id="main-title")
        gr.Markdown("Image manipulation with FLUX.1 Kontext. This demo focuses on watermark removal.")
        
        with gr.Row():
            with gr.Column():
                input_image = gr.Image(label="Upload Image with Watermark", type="pil", height="300")
                with gr.Row():
                    prompt = gr.Text(
                        label="Edit Prompt",
                        show_label=False,
                        max_lines=1,
                        placeholder="e.g., 'Remove the watermark'",
                        container=False,
                        value="[photo content], remove any watermark text or logos from the image while preserving the background, texture, lighting, and overall realism. Ensure the edited areas blend seamlessly with surrounding details, leaving no visible traces of watermark removal."
                    )
                    run_button = gr.Button("Run", variant="primary", scale=0)
                with gr.Accordion("Advanced Settings", open=False):
                    
                    seed = gr.Slider(
                        label="Seed",
                        minimum=0,
                        maximum=MAX_SEED,
                        step=1,
                        value=0,
                    )
                    
                    randomize_seed = gr.Checkbox(label="Randomize seed", value=True)
                    
                    guidance_scale = gr.Slider(
                        label="Guidance Scale",
                        minimum=1,
                        maximum=10,
                        step=0.1,
                        value=2.5,
                    )       
                    
                    steps = gr.Slider(
                        label="Steps",
                        minimum=1,
                        maximum=30,
                        value=28,
                        step=1
                    )
                    
            with gr.Column():
                output_slider = ImageSlider(label="Before / After", show_label=False, interactive=False)
                reuse_button = gr.Button("Reuse this image", visible=False)
                
    gr.on(
        triggers=[run_button.click, prompt.submit],
        fn=infer,
        inputs=[input_image, prompt, seed, randomize_seed, guidance_scale, steps],
        outputs=[output_slider, seed, reuse_button]
    )
    
    reuse_button.click(
        fn=lambda images: images[1] if isinstance(images, (list, tuple)) and len(images) > 1 else images,
        inputs=[output_slider],
        outputs=[input_image]
    )

demo.launch(mcp_server=True, ssr_mode=False, show_error=True)

Parameter Settings

Table with columns: Setting, Value
Setting	Value
Module Type	Adapter
Base Model	FLUX.1 Kontext Dev - fp8
Trigger Words	[photo content], remove any watermark text or logos from the image while preserving the background, texture, lighting, and overall realism. Ensure the edited areas blend seamlessly with surrounding details, leaving no visible traces of watermark removal.
Image Processing Repeats	50
Epochs	25
Save Every N Epochs	1

markdown
Labeling: florence-community/Florence-2-large-ft (natural language & English)

Total Images Used for Training : 150 Image Pairs (75 Start, 75 End)

Training Parameters

Table with columns: Setting, Value
Setting	Value
Seed	-
Clip Skip	-
Text Encoder LR	0.00001
UNet LR	0.00005
LR Scheduler	constant
Optimizer	AdamW8bit
Network Dimension	64
Network Alpha	32
Gradient Accumulation Steps	-

Label Parameters

Table with columns: Setting, Value
Setting	Value
Shuffle Caption	-
Keep N Tokens	-

Advanced Parameters

Table with columns: Setting, Value
Setting	Value
Noise Offset	0.03
Multires Noise Discount	0.1
Multires Noise Iterations	10
Conv Dimension	-
Conv Alpha	-
Batch Size	-
Steps	2900 & 400(warm up)
Sampler	euler

Sample Inferences : Inference Providers

Screenshot 2025-10-27 at 18-01-05 prithivMLmods_Kontext-Watermark-Remover · Hugging Face

Trigger words

You should use [photo content] to trigger the image generation.

You should use remove any watermark text or logos from the image while preserving the background to trigger the image generation.

You should use texture to trigger the image generation.

You should use lighting to trigger the image generation.

You should use and overall realism. Ensure the edited areas blend seamlessly with surrounding details to trigger the image generation.

You should use leaving no visible traces of watermark removal. to trigger the image generation.

Download model

Download them in the Files & versions tab.

Sample Inferences : Demo

Quick start with diffusers🧨

Required Packages

markdown
!pip install diffusers torch gradio transformers
!pip install pillow gradio-imageslider huggingface_hub
!pip install sentencepiece spaces peft torchvision accelerate

Run Demo

py
import os
import gradio as gr
import numpy as np
import spaces
import torch
import random
from PIL import Image
from typing import Iterable

from diffusers import FluxKontextPipeline
from diffusers.utils import load_image
from huggingface_hub import hf_hub_download
from gradio_imageslider import ImageSlider

device = torch.device("cuda" if torch.cuda.is_available() else "cpu")

# --- Main Model Initialization ---
MAX_SEED = np.iinfo(np.int32).max
pipe = FluxKontextPipeline.from_pretrained("black-forest-labs/FLUX.1-Kontext-dev", torch_dtype=torch.bfloat16).to("cuda")

# --- Load New Adapter ---
pipe.load_lora_weights("prithivMLmods/Kontext-Watermark-Remover", weight_name="Kontext-Watermark-Remover.safetensors", adapter_name="watermark_remover")


@spaces.GPU
def infer(input_image, prompt, seed=42, randomize_seed=False, guidance_scale=2.5, steps=28, progress=gr.Progress(track_tqdm=True)):
    """
    Perform image editing, returning a pair for the ImageSlider.
    """
    if not input_image:
        raise gr.Error("Please upload an image for editing.")

    pipe.set_adapters(["watermark_remover"], adapter_weights=[1.0])

    if randomize_seed:
        seed = random.randint(0, MAX_SEED)
    
    original_image = input_image.copy().convert("RGB")
    
    image = pipe(
        image=original_image, 
        prompt=prompt,
        guidance_scale=guidance_scale,
        width = original_image.size[0],
        height = original_image.size[1],
        num_inference_steps=steps,
        generator=torch.Generator().manual_seed(seed),
    ).images[0]

    return (original_image, image), seed, gr.Button(visible=True)

css="""
#col-container {
    margin: 0 auto;
    max-width: 960px;
}
#main-title h1 {font-size: 2.1em !important;}
"""

with gr.Blocks(css=css) as demo:
    
    with gr.Column(elem_id="col-container"):
        gr.Markdown("# **Photo-Mate-i2i: Watermark Remover**", elem_id="main-title")
        gr.Markdown("Image manipulation with FLUX.1 Kontext. This demo focuses on watermark removal.")
        
        with gr.Row():
            with gr.Column():
                input_image = gr.Image(label="Upload Image with Watermark", type="pil", height="300")
                with gr.Row():
                    prompt = gr.Text(
                        label="Edit Prompt",
                        show_label=False,
                        max_lines=1,
                        placeholder="e.g., 'Remove the watermark'",
                        container=False,
                        value="[photo content], remove any watermark text or logos from the image while preserving the background, texture, lighting, and overall realism. Ensure the edited areas blend seamlessly with surrounding details, leaving no visible traces of watermark removal."
                    )
                    run_button = gr.Button("Run", variant="primary", scale=0)
                with gr.Accordion("Advanced Settings", open=False):
                    
                    seed = gr.Slider(
                        label="Seed",
                        minimum=0,
                        maximum=MAX_SEED,
                        step=1,
                        value=0,
                    )
                    
                    randomize_seed = gr.Checkbox(label="Randomize seed", value=True)
                    
                    guidance_scale = gr.Slider(
                        label="Guidance Scale",
                        minimum=1,
                        maximum=10,
                        step=0.1,
                        value=2.5,
                    )       
                    
                    steps = gr.Slider(
                        label="Steps",
                        minimum=1,
                        maximum=30,
                        value=28,
                        step=1
                    )
                    
            with gr.Column():
                output_slider = ImageSlider(label="Before / After", show_label=False, interactive=False)
                reuse_button = gr.Button("Reuse this image", visible=False)
                
    gr.on(
        triggers=[run_button.click, prompt.submit],
        fn=infer,
        inputs=[input_image, prompt, seed, randomize_seed, guidance_scale, steps],
        outputs=[output_slider, seed, reuse_button]
    )
    
    reuse_button.click(
        fn=lambda images: images[1] if isinstance(images, (list, tuple)) and len(images) > 1 else images,
        inputs=[output_slider],
        outputs=[input_image]
    )

demo.launch(mcp_server=True, ssr_mode=False, show_error=True)

Parameter Settings

Table with columns: Setting, Value
Setting	Value
Module Type	Adapter
Base Model	FLUX.1 Kontext Dev - fp8
Trigger Words	[photo content], remove any watermark text or logos from the image while preserving the background, texture, lighting, and overall realism. Ensure the edited areas blend seamlessly with surrounding details, leaving no visible traces of watermark removal.
Image Processing Repeats	50
Epochs	25
Save Every N Epochs	1

markdown
Labeling: florence-community/Florence-2-large-ft (natural language & English)

Total Images Used for Training : 150 Image Pairs (75 Start, 75 End)

Training Parameters

Table with columns: Setting, Value
Setting	Value
Seed	-
Clip Skip	-
Text Encoder LR	0.00001
UNet LR	0.00005
LR Scheduler	constant
Optimizer	AdamW8bit
Network Dimension	64
Network Alpha	32
Gradient Accumulation Steps	-

Label Parameters

Table with columns: Setting, Value
Setting	Value
Shuffle Caption	-
Keep N Tokens	-

Advanced Parameters

Table with columns: Setting, Value
Setting	Value
Noise Offset	0.03
Multires Noise Discount	0.1
Multires Noise Iterations	10
Conv Dimension	-
Conv Alpha	-
Batch Size	-
Steps	2900 & 400(warm up)
Sampler	euler

Sample Inferences : Inference Providers

Screenshot 2025-10-27 at 18-01-05 prithivMLmods_Kontext-Watermark-Remover · Hugging Face

Trigger words

You should use [photo content] to trigger the image generation.

You should use remove any watermark text or logos from the image while preserving the background to trigger the image generation.

You should use texture to trigger the image generation.

You should use lighting to trigger the image generation.

You should use and overall realism. Ensure the edited areas blend seamlessly with surrounding details to trigger the image generation.

You should use leaving no visible traces of watermark removal. to trigger the image generation.

Download model

Download them in the Files & versions tab.

Kontext-Watermark-Remover

README

Sample Inferences : Demo

Quick start with diffusers🧨

Required Packages

Run Demo

Parameter Settings

Training Parameters

Label Parameters

Advanced Parameters

Sample Inferences : Inference Providers

Trigger words

Download model

Explore FriendliAI today

README

Sample Inferences : Demo

Quick start with diffusers🧨

Required Packages

Run Demo

Parameter Settings

Training Parameters

Label Parameters

Advanced Parameters

Sample Inferences : Inference Providers

Trigger words

Download model