# Z-Image

> Z-Image is a 6-billion-parameter open image model family from Alibaba's Tongyi Lab, built on a single-stream diffusion transformer. Z-Image-Turbo arrived in November 2025 and Z-Image in January 2026, with open weights. On Kenerate, Z Image Base costs 3 credits, renders up to 2048 px, and remixes one uploaded image with a strength slider — in our test, higher strength changed more of the image.

URL: https://kenerateai.com/model/z-image
Publisher: Kenerate AI (https://kenerateai.com)
Last updated: 27 September 2026

## Key facts
- Maker: Alibaba Tongyi Lab
- Size: 6B parameters
- On Kenerate: Z Image Base · 3 credits
- Image to image: Strength slider

## Steps
1. Open Z Image Base — Pick it in /app/image. Any credit pack unlocks it.
2. Write the prompt — Plain sentences work; say “photorealistic” for photos.
3. Remix an image (optional) — Upload one image and set Reference strength in Advanced settings — lower keeps more.
4. Download — Up to 2048 px, no watermark.

## In depth

### What makes Z-Image different
Most large image models use two streams for text and image. Z-Image uses a single-stream diffusion transformer at 6 billion parameters, which keeps it small enough for 16 GB consumer GPUs while producing photoreal results [1].

### When to pick Z Image Base
Pick it for cheap photoreal drafts and for image-to-image where you want control over how much changes. For polished finals switch to Seedream 5.0 Pro; for text-heavy designs, GPT Image 2.

References:
[1] Tongyi-MAI — Z-Image (GitHub): https://github.com/Tongyi-MAI/Z-Image

## FAQ
Q: What is Z-Image?
A: An open 6-billion-parameter image model family from Alibaba's Tongyi Lab. Z-Image-Turbo was released in November 2025 and Z-Image in January 2026.

Q: How much does Z-Image cost on Kenerate?
A: Z Image Base is 3 credits an image — about 3.5¢ on the $15 pack.

Q: Is Z-Image open source?
A: Yes, Tongyi Lab released the weights under Apache 2.0.

Q: How does the strength slider work on Z Image Base?
A: It appears under Advanced settings when you upload an image (10–100 %, default 75 %). In our test, 35 % kept the sketch, 60 % inked it, and 85 % turned it into a full painting.

Q: Can Z-Image write text?
A: Short text, yes — our 'OPEN LATE' neon sign came out correctly. For long text, GPT Image 2 is stronger.

## Related pages
- Qwen Image: https://kenerateai.com/model/qwen-image
- Flux 2: https://kenerateai.com/model/flux-2
- Image to image AI: https://kenerateai.com/image-to-image-ai
- All models: https://kenerateai.com/model

## Sources
- Tongyi-MAI — Z-Image (GitHub): https://github.com/Tongyi-MAI/Z-Image