ModelFoldModelFold
⚡ Usar con la API

Qwen-Image-Edit is an open-source image editing model based on Qwen-Image, supporting semantic and appearance editing with precise, visually coherent results. It also handles bilingual (Chinese and English) text editing while preserving font, size, and style, making it a versatile tool for advanced visual content manipulation.

Precio: 8 créditos / imagen.

Inicia sesión para probar este modelo
Las ejecuciones se cobran de tu monedero.
Instrucción

The prompt to generate the image with

Imagen de referencia

The URL of the image to edit.

acceleration

Acceleration level for image generation. Options: 'none', 'regular'. Higher acceleration increases speed. 'regular' balances speed and quality. Default value: "none"

image_size

The size of the generated image. Default value: landscape_4_3

num_inference_steps25

The number of inference steps to perform. Default value: 30

seed

The same seed and the same prompt given to the same version of the model will output the same image every time.

guidance_scale4

The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt when looking for a related image to show you. Default value: 4

sync_mode

If set to true, the function will wait for the image to be generated and uploaded before returning the response. This will increase the latency of the function but it allows you to get the image directly in the response without going through the CDN.

num_images
enable_safety_checker

If set to true, the safety checker will be enabled. Default value: true

output_format

The format of the generated image. Default value: "png"

negative_prompt

The negative prompt for the generation Default value: " "

nsfw_checker

A configurable parameter. Defaults to true in the Playground.

No se garantiza que se pueda filtrar todo el contenido. Si los resultados no son satisfactorios, tendrás que tomar las medidas que consideres necesarias.

Resultado
≡
README
Guía completa de Qwen Image Edit

Qwen-Image-Edit Pricing per Image

Current pricing is shown in the pricing card and the estimate before generation. One credit equals $0.005. Review actual charges in account usage logs.

Qwen Image Edit API: AI-Powered Editing Mastery

Discover Qwen Image Edit API, the open-source AI tool from Alibaba's Qwen team. Unlock precise text rendering, semantic transformations, and appearance controls for seamless edits. Elevate your creative workflow today.

Qwen Image Edit API: AI-Powered Editing Mastery

What is Qwen Image Edit API?

Qwen Image Edit API is an advanced open-source image editing foundation model developed by Alibaba's Qwen team, extending the capabilities of the 20B Qwen-Image model.

Dual-Mode AI Editor:

Combines visual-semantic control via Qwen2.5-VL and appearance control through VAE Encoder for versatile edits.

Bilingual Text Mastery:

Supports precise editing of English and Chinese text, matching original fonts, sizes, and styles seamlessly.

Open-Source Innovation:

Fully accessible under Apache 2.0 license, enabling free use, fine-tuning, and deployment on platforms like Hugging Face.

What's New in Qwen Image Edit API?

Semantic and Appearance Modes:

New dual-path processing for high-level changes like style transfers and pixel-accurate tweaks like object removal.

Enhanced Text Editing:

Superior handling of complex calligraphy and multi-language text, with flawless integration into images.

Benchmark Leadership:

Sets new SOTA results on public editing datasets, surpassing open models in style consistency and efficiency.

Key Features of Qwen Image Edit API

Enchanting Edits: Dual-Mode Mastery

Qwen Image Edit's core strength lies in its dual editing modes, blending semantic understanding with appearance precision for magical results.

Pixel Wizardry: Superior Text Rendering

Effortlessly add, edit, or delete bilingual text while preserving original aesthetics – a game-changer for posters and graphics.

Creative Alchemy: Multi-Language Support

Handles English, Chinese, and more with native rendering, ensuring cultural accuracy in global designs.

Swift Sorcery: Fast Generation Speeds

Generate or edit high-quality images in seconds, optimized for real-time applications on various platforms.

Layout Legends: Advanced Controls

Fine-tune aspect ratios, poses, and layouts with intuitive prompts for professional-level outputs.

Object Odysseys: Seamless Additions/Removals

Add or remove elements like backgrounds or objects in product photos, ideal for e-commerce enhancements.

How to Use Qwen Image Edit on ModelFold API

Get started with our product in just a few simple steps...

  1. 1

    Prepare Your Input:

    Upload an image and craft a prompt describing edits, e.g., "Add a red hat to the character" or "Change background to beach."

  2. 2

    Set Up Edits:

    Configure supported size, inference steps, seed and guidance options in the Playground. API integrations use POST /v1/images/generations with model qwen/image-edit.

  3. ✓

    Generate and Download:

    Click generate. View and download the edited image.

FAQs About Qwen Image Edit

What is Qwen Image Edit?⌄

Qwen Image Edit is an open-source image editing model based on Qwen-Image. It supports semantic editing (high-level changes like style or composition) and appearance editing (precise modifications like object addition/removal), delivering visually coherent results. It excels in bilingual (Chinese and English) text editing, preserving original font, size, and style for advanced visual manipulation.

How much does using Qwen Image Edit on ModelFold cost?⌄

Pricing is shown in the pricing card above.

Is Qwen Image Edit free and open-source?⌄

The model is open-source under Apache 2.0 for self-hosting and fine-tuning. Hosted API usage on ModelFold is charged at the rates displayed on this page.

What hardware is required for local use?⌄

Local hardware requirements depend on precision, quantization, resolution and the inference framework. Refer to official deployment instructions. ModelFold hosted usage does not require your own GPU.

Where can I find support or contribute?⌄

Visit the QwenLM community on GitHub or Hugging Face for discussion and contributions. For ModelFold integration, see the API section and documentation on this page.

Tarifas
image edit8 créditos image

Precio fijo por ejecución, independientemente de la duración.

Inicio rápido
curl https://ai.modelfold.online/v1/images/generations \
  -H "Authorization: Bearer $MODELFOLD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"qwen/image-edit","prompt":"..."}'