Design-grade image generation with professional typography, native vector output, and brand-aware style control — built for production design workflows.
Explore all 4 variants in the Recraft V4 family.
Standard text-to-image generation
Standard text-to-vector generation
Premium text-to-image with typography and style control
Premium vector art generation
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 quality |
| Fashion | Pending | Fashion quality |
| Product | Pending | Product quality |
| Creative | Pending | Creative quality |
Full parameter reference for the recraft-v4-pro-text-to-image model endpoint.
| Parameter | Type | Description |
|---|---|---|
| prompt | string | Text description of the image to generate. Supports detailed design briefs with style, color, and layout instructions. Up to 10,000 characters. |
| image_size | object | string | Output dimensions. Use preset strings (square_hd, landscape_4_3, etc.) or specify {width, height} up to 2048. |
| colors | array[object] | Array of preferred colors as RGB objects. The model biases generation toward these colors for brand consistency. |
| background_color | object | Preferred background color as an RGB object. Useful for generating assets on brand-specific backgrounds. |
| enable_safety_checker | boolean | If set to true, the safety checker will be enabled. |
Flux AI models are available on many platforms. Here's what makes the Runflow image generation API different.
Generate production-ready SVG vector art directly — no raster-to-vector conversion needed. Ideal for logos, icons, and scalable brand assets.
Best-in-class text rendering with accurate letterforms, kerning, and multi-line layouts that work in real designs without manual correction.
Specify color palettes, background colors, and style tokens to keep outputs aligned with brand guidelines across campaigns.
Outputs have clean lines, balanced whitespace, and visual hierarchy that matches professional design standards — not just photorealism.
Handles multi-word headlines, taglines, and body copy in images — a weakness of most competing models.
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.