Text-to-Image
Seedream 4.0 is a SOTA multimodal image creation model built on leading architecture. It breaks through the boundaries of traditional text-to-image models by natively supporting text, single-image, and multi-image inputs. Users can freely combine text and images to achieve diverse creative modes within a single model—such as multi-image blending, image editing, and sequentially batch image generation, featuring subject consistency, making image creation more free and controllable.
1,195
Sep 2025
image
$0.03/img
Catalog
Category rows come directly from Artificial Analysis when the endpoint exposes category-level Elo scores.
| Category | Elo | 95% CI | Appearances |
|---|---|---|---|
| People: Groups & Activities | 1,286 | -30/30 | 1,151 |
| Fantasy & Mythical | 1,253 | -24/24 | 1,552 |
| General | 1,250 | -18/18 | 2,894 |
| General | 1,250 | -37/37 | 650 |
| General & Photorealistic | 1,248 | -15/15 | 4,115 |
| Anime | 1,242 | -34/34 | 894 |
| General | 1,226 | -14/14 | 4,357 |
| General | 1,225 | -14/14 | 4,617 |
| Traditional Art |
| 1,222 |
| -35/35 |
| 711 |
| General | 1,221 | -14/14 | 4,200 |
| General | 1,219 | -11/11 | 6,519 |
| General | 1,208 | -32/32 | 940 |