Reve's fast edit model — upload an existing image and transform it via a text prompt at lightning speed. Context-aware editing with automatic spatial relationship preservation.
Explore all Reve endpoints available on Runflow.
12B generation with best-in-class typography
Full-quality image editing via text prompts — $0.04/img
Lightning-speed image editing — $0.01/img
Reimagine entire scenes from references — $0.04/img
Fast scene remixing — $0.04/img
Every model on Runflow is scored per vertical — not generic leaderboard numbers. Scores come from domain-expert evaluation on real production prompts.
| Use Case | Assessment | Notes |
|---|---|---|
| Portrait | Pending | Portrait editing quality |
| Fashion | Pending | Fashion editing quality |
| Product | Pending | Product editing quality |
| Creative | Pending | Creative editing quality |
Full parameter reference for the reve-fast-edit model endpoint.
| Parameter | Type | Description |
|---|---|---|
| prompt | string | Text description of how to edit the provided image. Max 2,560 characters. Describe the desired transformation in natural language. |
| image_url | string | URL of the reference image to edit. Supports PNG, JPEG, WebP, AVIF, HEIF. Max 10 MB, 128–4096px per dimension. |
| num_images | integer | Number of edited variations to generate per request. Range: 1–4. Default: 1. |
| output_format | string | Output image format. Options: "png", "jpeg", "webp". Default: "png". |
| sync_mode | boolean | If true, returns the image as a data URI. Output won't be stored in request history. |
Flux AI models are available on many platforms. Here's what makes the Runflow image generation API different.
The fast variant prioritizes throughput — transform images in seconds, not minutes. Ideal for high-volume editing pipelines and real-time applications.
Describe edits in plain English — no masks, layers, or region selection needed. The model handles spatial relationships and context preservation automatically.
Accepts PNG, JPEG, WebP, AVIF, and HEIF inputs up to 4096×4096 and 10 MB — no pre-processing or format conversion needed.
Edits respect the original image's lighting, perspective, and style. Change backgrounds, swap objects, or adjust attributes while maintaining visual coherence.
At $0.01 per edit, Reve Fast Edit is one of the most affordable AI image editing APIs — 4x cheaper than the full-quality Reve Edit endpoint.
Same API, different strengths. Switch models with one parameter change.
Black Forest Labs
FLUX.1 [dev] is a 12B-parameter text-to-image model by Black Forest Labs. Open-w…
ByteDance
Seedream 4.5 by ByteDance — unified generation and editing in one model. Strong…
ByteDance
Seedream 4 by ByteDance — unified generation and editing model with photorealism…
Nano Banana 2 by Google — fast image generation across 4 resolution tiers (0.5K–…
OpenAI
GPT-Image 1.5 by OpenAI — high-fidelity images with strong prompt adherence. Thr…
Nano Banana Pro by Google — premium image generation with sharp detail and natur…
Get API access in minutes. No GPU setup, no infrastructure to manage. Pair with Sentinel to control the quality of every AI-generated image you ship.