Qwen Image 3 Image Editing

Edits images from one to three reference images and a natural-language instruction, preserving key details such as facial features and identity while applying the requested changes

Inference$ Commercial useFrom 2 credits per run

About Qwen Image 3 Image Editing

Edits images from one to three reference images and a natural-language instruction, preserving key details such as facial features and identity while applying the requested changes

stylizedtransformtypography

Pricing

A run with the default settings costs 2 credits. The exact cost updates in the playground as you change settings, and you're only charged when you press Run. Failed runs are refunded automatically.

Inputs

prompttextarearequired

Text prompt describing the desired edit. Supports Chinese and English. Max 5000 characters.

negative_prompttextareadefault: ""

Content to avoid in the generated image. Max 500 characters.

image_sizeselect

The size of the generated image. If not provided, the model determines the resolution automatically. Total number of pixels must be between 512x512 and 2048x2048.

Options: square_hd, square, portrait_4_3, portrait_16_9, landscape_4_3, landscape_16_9

enable_prompt_expansionbooleandefault: true

Enable automatic LLM prompt rewriting for better results.

seedinteger

Random seed for reproducibility (0-2147483647).

enable_safety_checkerbooleandefault: true

Enable content moderation for input and output. Disabling it requires account authorization; unauthorized requests are always checked.

sync_modebooleandefault: false

If `True`, the media will be returned as a data URI and the output data won't be available in the request history.

num_imagesintegerdefault: 1

The number of images to generate.

output_formatselectdefault: "png"

The format of the generated image.

Options: jpeg, png, webp

image_urlsfile-listrequired

Reference images for editing (1-3 images required). Order matters: reference as 'image 1', 'image 2', 'image 3' in prompt. Resolution: 384-2048px each dimension. Max size: 10MB each. Formats: JPEG, JPG, PNG (no alpha), WEBP.

More from Qwen Image 3

Qwen Image 3 Text to Image

Generates images from a text prompt at resolutions up to 2048×2048, with automatic prompt rewriting and prompt-guided resolution selection, building on Qwen's strength in complex text rendering and precise prompt adherence

stylizedtransform

text-to-image

Related image to image models

Nano Banana Pro

Nano Banana Pro is Google's new state-of-the-art image generation and editing model

realismtypography

image-to-image

Nano Banana 2

Nano Banana 2 is Google's new state-of-the-art image generation and editing model

image-to-image

Nano Banana 2.1 Edit

Nano Banana 2.1 Edit by Google transforms reference images using text instructions, with output resolutions up to 4K and optional video or PDF context.

image editingimage to image

image-to-image

GPT Image 2.5 Sunburst Edit

Editing built for the tightest control, edits scoped precisely to the instruction, with subject and composition preserved across many rounds of revision.

stylizedtransform

image-to-image

✦ new

GPT Image 2.6 Sunburst Edit

Editing built for the tightest control, edits scoped precisely to the instruction, with subject and composition preserved across many rounds of revision.

stylizedtransform

image-to-image

GPT Image 2 API

GPT Image 2, OpenAI's latest image model, is capable of making fine-grained, detailed edits to images.

gpt-image-2openai

image-to-image

Birefnet Background Removal V2

bilateral reference framework (BiRefNet) for high-resolution dichotomous image segmentation (DIS)

background removalsegmentation

image-to-image

Nano Banana

Google's famous original image generation and editing model

image-editing

image-to-image

GPT Image 2.5 Flare Edit

Precise image editing that changes only what's asked, keeping subject, composition, and background intact, with reference subjects staying recognizable across styles and successive edits.

stylizedtransform

image-to-image

✦ new

GPT Image 2.6 Flare Edit

Precise image editing that changes only what's asked, keeping subject, composition, and background intact, with reference subjects staying recognizable across styles and successive edits.

stylizedtransform

image-to-image

Seedream 5.0 Pro Image Editing

Seedream 5.0 Pro is grounded, region-precise image editing model that changes one element while keeping the rest of the frame intact with layer separation, sketch completion, and up to 10 reference images.

realismtypography

image-to-image

SeedVR2

Use SeedVR2 to upscale your images

upscale

image-to-image