image-to-image
FireRed Image Edit enables precise image editing with natural-language instructions, supporting both English and Chinese prompts with multi-image references. Ready-to-use REST inference API, best performance, no cold starts, affordable pricing.
Idle
Tu solicitud costará $0.08 por ejecución.
Con $1 puedes ejecutar este modelo aproximadamente 12 veces.
Una cosa más:
EjemplosVer todo
README
FireRed Image Edit
FireRed Image Edit is a powerful AI image editing model that combines elements from multiple reference images into a single cohesive output. Upload reference images of people, objects, or styles, then describe how to combine them — the model intelligently merges elements while maintaining natural composition and lighting.
Why Choose This?
-
Multi-image composition Combine elements from multiple reference images into one seamless result.
-
Natural language editing Describe your edit in plain text — reference images by Figure number for precise control.
-
Flexible sizing Specify custom output size, or leave blank to match the first image's aspect ratio.
-
Intelligent blending Automatically adapts lighting, perspective, and style for realistic integration.
-
Prompt Enhancer Built-in tool to automatically improve your edit descriptions.
Parameters
| Parameter | Required | Description |
|---|---|---|
| prompt | Yes | Text description of the desired edit (use "Figure 1", "Figure 2" to reference images) |
| images | Yes | Reference images to combine (click "+ Add Item" to add more) |
| size | No | Output size; if empty, matches the first image's aspect ratio |
How to Use
- Upload reference images — add all images containing elements you want to combine.
- Write your prompt — describe the edit using "Figure 1", "Figure 2", etc. to reference specific images.
- Set size (optional) — specify output dimensions, or leave blank to use first image's ratio.
- Use Prompt Enhancer (optional) — click to automatically refine your description.
- Run — submit and download your edited image.
Pricing
| Output | Cost |
|---|---|
| Per image | $0.08 |
Best Use Cases
- Virtual Try-On — Put a person in different outfits from reference photos.
- Character Compositing — Combine character features with new environments or accessories.
- Product Visualization — Show products on different models or in various settings.
- Creative Compositing — Merge elements from multiple sources for unique imagery.
- Marketing & Ads — Create customized visuals by combining brand assets.
Pro Tips
- Use "Figure 1", "Figure 2", etc. in your prompt to reference images in upload order.
- Clear, front-facing reference images produce the best element extraction.
- The first image determines the default output aspect ratio when size is not specified.
- Describe the scene context (location, lighting, mood) for more cohesive results.
- For best results, use reference images with similar lighting conditions.
Notes
- Both prompt and images are required fields.
- Ensure uploaded image URLs are publicly accessible.
- Output size defaults to first image's aspect ratio if not specified.