Fast endpoint for Flux Kontext. Specialized for precise image editing and manipulation through text prompts with pro-level editing fidelity.

The text description to generate an image from. This is the core input that drives the output

prompt

The input image for image-to-image generation. Upload an image file and it will be automatically processed

img_cond_path

Aspect ratio of the output image. "match_input_image" will use the same ratio as the input image

aspect_ratio

How many denoising steps to run during generation. More steps may improve quality, at the cost of speed

num_inference_steps

CFG controls how closely the image follows the prompt. Higher values = stronger prompt adherence, but may reduce creativity

guidance_scale

If enabled, content will be checked for safety violations

enable_safety_checker

output_format

Applies to jpeg and webp formats. Defines compression quality (1-100)

output_quality

FLUX.1 Kontext Dev

Physics-aware image editing that preserves pose, lighting, reflections, and shadows. Provide one image and a precise instruction for realistic, consistent edits.

Provide a clear, well-lit image for best results

Use a clean, well-lit photo. Higher quality inputs lead to better realism.

image

Describe the physical change and what must be preserved (pose, camera angle, lighting).

jpeg for compact delivery; png for lossless editing.

Set a specific seed for reproducible edits; -1 uses a random seed.

seed

NVIDIA Chrono Edit

Edit images using a prompt. Extends Qwen-Image's unique text rendering capabilities to image editing tasks, enabling precise text editing.

Precise text edit within the existing design

Upload a clear image. For text edits, include the area with text you want to change.

Describe the desired edit. This model excels at precise text edits (including Chinese characters) and localized changes.

Qwen Image Edit

Google's latest image editing model in Gemini 2.5. Edit images using natural language instructions.

Supports multiple images. They will be sent as an array to the API.

image_input

Describe the desired edit in plain English.

Nano Banana (Gemini 2.5 Image Edit)

Quickly change someone's hairstyle and hair color using FLUX Kontext.

Classic bob cut with blonde hair transformation

Upload a clear photo of the person whose hairstyle you want to change. For best results, use a well-lit photo with the face clearly visible.

input_image

Choose the desired hairstyle. Select "Random" to let the AI choose an interesting style.

haircut

Choose the desired hair color. Select "No change" to keep the original color, or "Random" for a surprise.

hair_color

Change Haircut

The transformed image with the new hairstyle and/or hair color

Transform your hairstyle into a fun broccoli haircut! Upload your photo and see how you would look with this unique vegetable-inspired hairstyle. Perfect for creative portraits and fun social media content.

Upload a clear photo of yourself for the broccoli hairstyle transformation. For best results, use a front-facing photo with good lighting.

Broccoli Hairstyle Try On

Your photo transformed with a broccoli hairstyle

Transform your face into various artistic styles and personas. Become a character in anime, cartoon, pixel art, or take on personas like ninja, robot, vampire, and more.

Image of the person to transform. Must be jpeg, png, gif, or webp format.

style

persona

num_images

Aspect ratio of the generated image. Use "match_input_image" to match the aspect ratio of the input image

Whether to preserve the background from the original image

preserve_background

Whether to preserve the outfit from the original image

preserve_outfit

Safety tolerance level. 0 is most strict, 2 is most permissive

safety_tolerance

Face to Many Kontext

Edit images with natural language instructions. Explore fast, high-quality image editing apps.

图片编辑

FLUX.1 Kontext 开发版

NVIDIA Chrono Edit

Qwen 图像编辑

Nano Banana（Gemini 2.5 图像编辑）

发型变换

西兰花发型试戴

人脸多风格转换

Image Generation

Video Generation

Video Effects

Audio Generation