Setting things up…
AI image model
Qwen Image 2.0 Edit
Qwen Image 2.0 edit model with enhanced editing quality and improved instruction understanding. Ready-to-use REST inference API, best performance, no cold starts, affordable pricing.
image outputfrom 3 creditsrefunded on failure
What you'll need
- Images — Reference images for editing (1-3 images, 384-3072px each dimension)
- Prompt — Text prompt describing the desired edit, supports Chinese and English (max 800 characters)
About Qwen Image 2.0 Edit
Qwen Image 2.0 Edit is an AI image model you can run directly in the Percify playground — fill in the inputs and generate right in your browser, or call it programmatically through the Percify API. Each run returns a ready-to-download image hosted on our CDN, and credits are only charged for successful results.
More AI image models
View the full catalogGPT Image 2OpenAI image generation — excellent prompt-following and clean text rendering; takes reference images.Z-Image Turbo Img2ImgImage 2 Image version of z-image-turbo with lora support.Flux Kontext ProA state-of-the-art text-based image editing model that delivers high-quality outputs with excellent prompt following and consistent results for transforming images through natural languageZ-Image TurboZ-Image Turbo is a super fast text-to-image model of 6B parameters developed by Tongyi-MAI.Flux SchnellThe fastest image generation model tailored for local development and personal useFlux 2 Klein 4BVery fast image generation and editing model. 4 steps distilled, sub-second inference for production and near real-time applications.Flux 2 DevQuality image generation and editing with support for reference imagesSeedReam 5 LiteSeedream 5.0 lite: image generation with built-in reasoning, example-based editing, and deep domain knowledgeFlux Kontext FastUltra fast flux kontext endpointGrok Imagine ImageSOTA image model from xAIImage Head SwapSwap a face onto any photo while keeping the body, pose and background.Infinite YouGenerate consistent, photorealistic portraits of a person from one reference image.