FLUX.1 [pro] v1.1 — 12B-param commercial-grade model by Black Forest Labs. 6× faster than v1, highest benchmark Elo. $0.04/MP.
Multiple FLUX Pro variants for different quality and resolution needs — all on the same Runflow API.
Commercial-grade — 6× faster, highest Elo, $0.04/MP
4MP high-res output with integrated upscaling and raw mode, $0.06/image
Open-weight, 12B params, $0.025/MP — non-commercial license
Speed-optimised — sub-second at $0.003/MP, Apache 2.0
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 | Strong | Enhanced composition and fine detail — top Elo among commercial models |
| Fashion | Strong | Superior multi-subject coherence for editorial scenes |
| Product | Strong | Sharp detail rendering with accurate lighting |
| Creative | Strong | Improved text-in-image capabilities and artistic fidelity |
Full parameter reference for the flux-pro-v1-1 model endpoint.
| Parameter | Type | Description |
|---|---|---|
| prompt | string | Text description of the image to generate. |
| image_size | object | string | Output size. Presets: square_hd, square, portrait_4_3, portrait_16_9, landscape_4_3, landscape_16_9. Or custom {width, height}. Default: landscape_4_3. |
| num_images | integer | Number of images to generate per request. Range: 1–4. Default: 1. |
| output_format | string | Output format. Options: "jpeg", "png". Default: "jpeg". |
| safety_tolerance | string | Content moderation strictness. 1 = most strict, 6 = most permissive. Default: 2. |
| enhance_prompt | boolean | Automatically enhance the prompt for better results. Default: false. |
| seed | integer | Random seed for reproducible outputs. |
| sync_mode | boolean | Return media as data URI without storing in request history. Default: false. |
Flux AI models are available on many platforms. Here's what makes the Runflow image generation API different.
FLUX.1 [pro] v1.1 achieved the highest overall Elo score on the Artificial Analysis image arena — beating all commercial models at launch.
Dramatically reduced inference time over the original FLUX.1 [pro] while improving composition, detail, and text-in-image quality.
Noticeably better at complex scenes with multiple people, objects, or architectural elements — fewer artefacts and more natural spatial relationships.
The enhance_prompt parameter automatically refines your input for better results — useful when working with short or ambiguous prompts.
Every output is scored by Runflow's Sentinel system before delivery, catching low-quality or off-prompt results automatically.
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.