someaistuff.
fal-aiReleased Dec 2, 2025

Z Image Turbo

Z-Image Turbo is a super fast text-to-image model of 6B parameters developed by Tongyi-MAI.

Compare
Provider endpoints1
Benchmark results1
Open weights
Measured performance

Benchmark results

All leaderboards ↗
AA-Image-T2I ↗2.1
935.51

Text-to-image · all categories

95% CI 924.51–946.51 · n=8,170

Independent result
Access & cost

Prices across providers

1 quote

Model specifications

Developer
fal-ai
Modality
Image
Context
Not reported
Maximum output
Not reported
Weights
Open weights
Released
Dec 2, 2025
Provider listed
Nov 26, 2025
First discovered
Oct 16, 2026

Exact identities

  • falfal-ai/z-image/turbo
  • aa-imaged48735c9-9f0f-45b6-ad45-cc03eec252c8

Sources

fal ↗Artificial Analysis Image Arena ↗

Updated Oct 21, 2026

More from fal-ai

View all ↗
fal-aiListed 2 days ago

MOSS Image

MOSS-Image-SFT is a text-to-image model specializing in Chinese and English text rendering and structured layout control for precise text placement and object arrangement.

No reported score
No reported score
Listed from $0.05/ megapixel · USDfal
+Compare
fal-aiListed 18 days ago

Marigold V2 Depth

Estimate depth from a single image with Marigold V2, a diffusion-based depth model built on Qwen-Image-Edit, returning a colorized depth map.

No reported score
No reported score
Price not listed
+Compare
fal-aiListed Aug 26

VGGT-1B

Turn images or video into a detailed 3D scene with depth, camera poses, and a colored point cloud.

1BNo reported score
No reported score
Listed from $0.000975/ compute second · USDfal
+Compare
fal-aiListed Jul 29

Ideogram Object Removal

Prompt-free object removal from an image and mask, erasing objects with their shadows and reflections and reconstructing the scene cleanly.

No reported score
No reported score
Listed from $0.03/ generation · USDfal
+Compare