# Recraft V4

Source: https://docs.prodia.com/models/recraft-v4/

Recraft V4 is the model to choose when your images need to contain readable text. While most image generation models struggle with typography — producing garbled or misspelled text — Recraft V4 can accurately place and render multi-line text within generated images. Combined with native SVG vector output, this makes it uniquely suited for design workflows like logos, signage, social media graphics, and marketing materials.

### Architecture

Recraft V4 is a ground-up rebuild with tens of billions of parameters, trained on NVIDIA Blackwell GPUs interconnected via Quantum-2 InfiniBand using bfloat16 precision. Rather than focusing on parameter count alone, Recraft optimized for total compute operations (FLOPS) per generation — scaling both parameters and inference operations for better output quality.

The exact architecture is proprietary, but V4 represents a significant scale increase over Recraft V2 (\~20B parameters released in March 2024).

### What sets Recraft V4 apart

*Native text rendering:*
The `text_layout` parameter lets you specify text content and bounding box positions using normalized coordinates (0–1). The model renders the text as part of the image generation process — not as a post-processing overlay — so text integrates naturally with the scene's lighting, perspective, and style.

*Vector (SVG) output:*
The `txt2vec` job types produce SVG vector graphics instead of raster images. This is valuable for logos, icons, and illustrations that need to scale to any size without quality loss. You can also control the color palette with the `controls` parameter.

*Pro variant (2x resolution):*
Standard sizes max out at 1536x1024. The Pro variant doubles this to 3072x1536 — useful for print-quality output, large-format displays, or when you need extra detail.

### Recraft V3 vs V4

| Feature        | Recraft V3                           | Recraft V4                                  |
| -------------- | ------------------------------------ | ------------------------------------------- |
| Prompt length  | 1,000 chars                          | 10,000 chars                                |
| Max resolution | 2048x1024                            | 1536x1024 (Standard), 3072x1536 (Pro)       |
| Text rendering | Basic                                | Precise `text_layout` with bounding boxes   |
| Styles         | 5 styles, 40+ substyles              | Prompt-driven (no explicit style parameter) |
| img2img        | Yes                                  | Not yet (use V3)                            |
| Vector output  | `img2vec` (rasterize then vectorize) | Native `txt2vec` (generate as vector)       |
| Color controls | Yes                                  | Vector only                                 |

> note:
>
> Recraft V3 remains available via `inference.recraft.txt2img.v1`, `inference.recraft.img2img.v1`, and `inference.recraft.img2vec.v1`. Use V3 when you need img2img, explicit style/substyle control, or color controls for raster output.

### When to use Recraft V4

- *Marketing graphics* — social media posts, banners, and ads with text overlays that render correctly
- *Logos and branding* — use `txt2vec` for scalable SVG logos with precise color control
- *Signage and packaging* — generate realistic product mockups with accurate label text
- *Infographics* — combine visual elements with readable data labels and titles
- *Print materials* — Pro variant's high resolution suits posters, brochures, and large-format output

For photorealistic images without text, [FLUX.2](https://docs.prodia.com/models/flux-2/) generally produces higher-fidelity results. For image editing (img2img), use Recraft V3 or FLUX.2.

### Job types

| Job type                              | Description                            | ETA   |
| ------------------------------------- | -------------------------------------- | ----- |
| `inference.recraft.v4.txt2img.v1`     | Generate a raster image                | \~18s |
| `inference.recraft.v4.pro.txt2img.v1` | Generate a high-res raster image (Pro) | \~40s |
| `inference.recraft.v4.txt2vec.v1`     | Generate an SVG vector graphic         | \~28s |
| `inference.recraft.v4.pro.txt2vec.v1` | Generate a high-res SVG vector (Pro)   | \~45s |

### Parameters

- `prompt` (required) — text description, up to 10,000 characters
- `size` — output dimensions from preset list (see below)
- `text_layout` — array of text elements, each with:
  - `text` — the text content to render
  - `bbox` — bounding box as 4 corner points, each `[x, y]` normalized to 0–1 range
- `controls` (vector types only) — color palette:
  - `colors` — array of `{"rgb": [r, g, b]}` objects
  - `background_color` — optional `{"rgb": [r, g, b]}` background

*Standard sizes:* `1024x1024`, `1536x768`, `768x1536`, `1280x832`, `832x1280`, `1216x896`, `896x1216`, `1152x896`, `896x1152`, `832x1344`, `1280x896`, `896x1280`, `1344x768`, `768x1344`

*Pro sizes:* `2048x2048`, `3072x1536`, `1536x3072`, `2560x1664`, `1664x2560`, `2432x1792`, `1792x2432`, `2304x1792`, `1792x2304`, `1664x2688`, `2560x1792`, `1792x2560`, `2688x1536`, `1536x2688`

### Prompting tips

- *Describe text placement in the prompt too:* while `text_layout` controls exact position, mentioning the text in your prompt (e.g., "a coffee shop sign reading COFFEE HOUSE") helps the model understand the visual context
- *Use bounding boxes generously:* the bbox defines where text appears. Place it where text would naturally occur in the scene — on signs, labels, banners, etc.
- *Long prompts work well:* with 10,000 characters of prompt space, you can describe complex scenes in detail. Be specific about materials, lighting, and composition
- *Vector color control:* for SVG output, specify your brand colors via `controls.colors` to ensure on-brand output

### Examples

Image with rendered text:

```json
{
  "type": "inference.recraft.v4.txt2img.v1",
  "config": {
    "prompt": "A vintage coffee shop storefront with a hand-painted wooden sign, warm afternoon light, brick walls with ivy",
    "size": "1280x832",
    "text_layout": [
      {
        "text": "COFFEE HOUSE",
        "bbox": [[0.2, 0.15], [0.8, 0.15], [0.8, 0.35], [0.2, 0.35]]
      },
      {
        "text": "Est. 1987",
        "bbox": [[0.35, 0.38], [0.65, 0.38], [0.65, 0.45], [0.35, 0.45]]
      }
    ]
  }
}
```

SVG logo with brand colors:

```json
{
  "type": "inference.recraft.v4.txt2vec.v1",
  "config": {
    "prompt": "A minimalist mountain logo, clean geometric shapes, modern design",
    "size": "1024x1024",
    "controls": {
      "colors": [
        {"rgb": [37, 99, 235]},
        {"rgb": [255, 255, 255]}
      ],
      "background_color": {"rgb": [15, 23, 42]}
    }
  }
}
```

### Guides

[Generating Images](https://docs.prodia.com/guides/generating-images/) — Step-by-step guide for generating images with Prodia.

[Vectorizing Images](https://docs.prodia.com/guides/vectorizing-images/) — Guide for generating and working with vector images.