# z-image-turbo

> Z-Image Turbo: fast text-to-image generation

This file is intended for AI coding agents wiring an application to this specific Chutes model.

## Important URLs

- Model page: https://chutes.ai/app/chute/vonkaiser-z-image-turbo
- Model llms.txt: https://chutes.ai/app/chute/vonkaiser-z-image-turbo/llms.txt
- Model OpenAPI 3.1 spec (this chute, callable): https://chutes.ai/app/chute/vonkaiser-z-image-turbo/openapi.json
- Global Chutes llms.txt: https://chutes.ai/llms.txt
- Full Chutes docs export: https://chutes.ai/llms-full.txt
- Management API OpenAPI (account/billing/keys, NOT this model): https://api.chutes.ai/openapi.json

## Model Identifiers

- Name: `z-image-turbo`
- Chute ID: `2cc39ac2-4e9f-50de-849f-e99e45729396`
- Slug: `vonkaiser-z-image-turbo`
- Owner: `vonkaiser`

## Authentication

- Use `Authorization: Bearer $CHUTES_API_KEY` for inference calls.
- Send JSON request bodies with `Content-Type: application/json` unless the endpoint documentation says otherwise.
- The request body is FLAT — send the request fields at the top level (no `input_args`/`args` wrapper).
- This model is served on its own host (`https://vonkaiser-z-image-turbo.chutes.ai`). Call the endpoint paths listed below directly.
- For base64 media fields, send raw base64 strings in API requests. The web playground may use temporary Blob upload references internally for large files before proxying to Chutes.

## Playground Notes

- Use short negative prompts for obvious exclusions rather than long lists.
- Keep dimensions moderate while iterating, then increase quality settings for final runs.

## Endpoints

### 1. POST /generate

- Base URL: `https://vonkaiser-z-image-turbo.chutes.ai`
- Output content type: `image/png`
- Playground note: Start with a concrete subject, style, composition, lighting, and output constraints.

Request fields:

- `seed` (integer, optional) Default: null.
- `shift` (number, optional) Default: 3.
- `width` (integer, optional) Default: 1024.
- `height` (integer, optional) Default: 1024.
- `prompt` (string, required)
- `guidance_scale` (number, optional) Default: 0.
- `max_sequence_length` (integer, optional) Default: 512.
- `num_inference_steps` (integer, optional) Default: 9.

Example call:

```bash
curl -X POST "https://vonkaiser-z-image-turbo.chutes.ai/generate" \
  -H "Authorization: Bearer $CHUTES_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "seed": 42,
  "shift": 3,
  "width": 1024,
  "height": 1024,
  "prompt": "a serene mountain lake at sunset",
  "guidance_scale": 0,
  "max_sequence_length": 512,
  "num_inference_steps": 9
}' \
  --output output.png
```

Playground presets:

- Clean product render
- Editorial illustration

## Model Facts

- Parameters: 6B
- Architecture: Scalable Single-Stream Diffusion Transformer (S3-DiT) with a Qwen3 text encoder and flow-matching scheduler
- Modalities: text in → image out
- License: Apache-2.0
- Released: 2025-11
- Transformer: 30 layers, hidden dim 3840, 30 attention heads
- Distillation: 8 NFEs (function evaluations); CFG disabled
- Scheduler: FlowMatchEulerDiscreteScheduler
- Text rendering: Bilingual (English and Chinese), per model card
- Output format on Chutes: image/png
- Hugging Face: https://huggingface.co/Tongyi-MAI/Z-Image-Turbo

## Recommended Parameters

- `num_inference_steps`: 8 (model card: Turbo is distilled to 8 NFEs; the chute defaults to 9 steps)
- `guidance_scale`: 0 (CFG is baked out by distillation (model card marks CFG as off for Turbo); chute default is 0)

## Best For

- Fast photorealistic text-to-image with sub-second-class latency budgets
- Rendering legible English and Chinese text inside images
- High-volume generation pipelines where per-image cost and speed matter
- Prompt-faithful product renders and editorial illustration from concrete prompts
- Interactive UIs that need quick draft-to-final iteration

Not ideal for:

- Image editing or image-to-image tasks (use an edit model such as Qwen-Image-Edit; Z-Image-Turbo is generation-only)
- Workflows that rely on strong negative prompting or CFG sweeps — the Turbo distillation disables CFG
- Maximum output diversity across seeds; the model card rates Turbo's diversity as low relative to base Z-Image

## FAQ

### How many inference steps should I use with Z-Image Turbo?

The model is distilled for 8 function evaluations, and the chute defaults to 9 steps. Stick close to the default; unlike standard diffusion models, raising the step count substantially does not buy proportional quality because the distillation targets a fixed short schedule.

### Why is guidance_scale 0, and can I use a negative prompt?

Turbo is distilled with classifier-free guidance baked out, so the chute defaults guidance_scale to 0 and exposes no negative prompt field. Express exclusions inside the positive prompt. If you need CFG and negative prompting, the non-distilled base Z-Image model supports both.

### What license is Z-Image Turbo under? Can I use it commercially?

Apache-2.0, per the Hugging Face repo Tongyi-MAI/Z-Image-Turbo. Apache-2.0 permits commercial use, modification, and redistribution with attribution and license notice.

### How do I call this chute from code?

POST a flat JSON body to https://vonkaiser-z-image-turbo.chutes.ai/generate with an Authorization: Bearer header carrying your Chutes API key. The response body is the PNG image itself, not JSON, so write it straight to a file or blob.

### Can it render text inside images?

Yes. Bilingual text rendering (English and Chinese) is one of the model card's headline capabilities. Quote the exact text you want in the prompt and keep it short for best fidelity.

### What image sizes does it support?

The chute defaults to 1024x1024 and accepts width and height fields. Keep dimensions moderate while iterating; larger canvases cost more compute and take longer.

### Is Z-Image Turbo an editing model?

No, it is text-to-image only. The Z-Image family includes a separate Z-Image-Edit variant for instruction-based editing, and Chutes hosts dedicated edit models such as Qwen-Image-Edit-2511.


## Model Guide & Sources

- Full model guide: https://chutes.ai/docs/models/vonkaiser-z-image-turbo
- Source: https://huggingface.co/Tongyi-MAI/Z-Image-Turbo
- Source: https://chutes.ai/app/chute/vonkaiser-z-image-turbo/llms.txt

## Agent Integration Checklist

- Pick the endpoint path that matches the desired task.
- Set `CHUTES_API_KEY` in the server-side environment only.
- Validate required fields before sending requests.
- For media models, keep file upload, base64 conversion, and output preview/download handling explicit in the app UI.