FLUX.2 [klein] Base 9B Edit is a high-quality image editing model with 9B parameters, offering precise modifications using natural language instructions. Ready-to-use REST inference API, best performance, no cold starts, affordable pricing.
En attente

$0.016par exécution·~62 / $1


WaveSpeed AI FLUX.2 Klein Base 9B Edit is a high-quality image editing model built for prompt-driven transformations, compositing, and style changes. Upload one or more source images, describe the edit in natural language, and generate polished results with stronger detail and better prompt understanding than the 4B variant.
Higher-quality editing The 9B parameter model delivers richer detail, stronger prompt adherence, and better overall edit quality than the 4B variant.
Natural-language editing Describe the change you want in plain language — transform style, replace elements, change mood, or combine multiple images.
Multi-image support Upload multiple reference images and perform compositing or cross-image edits such as “Put the person in image1 into image2.”
Flexible output sizing
Optionally set output dimensions, or leave size empty to preserve the original input dimensions.
Prompt Enhancer Built-in prompt enhancement can help improve edit quality and clarity.
Production-ready workflow Suitable for high-quality creative editing, marketing visuals, and more complex multi-image transformations.
| Parameter | Required | Description |
|---|---|---|
| prompt | Yes | Text description of the desired edit. |
| images | Yes | Source images to edit. Multiple images are supported. |
| size | No | Output dimensions. Leave empty to match the input image dimensions. |
| seed | No | Random seed for reproducibility. Use -1 for random generation. |
-1 for random generation, or enter a fixed seed for reproducible results.Put the person in image1 into image2, keep realistic lighting and proportions, and match the scene naturally.
| Item | Cost |
|---|---|
| Per image | $0.016 |
size and seed do not affect pricingimage1, image2, and so on.size empty when you want to preserve the original image dimensions.seed when comparing different prompt variations on the same images.prompt and images are required.size is not specified, the output matches the input image dimensions.