API docs / Image models

qwen-image-2512 API

Generates photorealistic images from text prompts with improved human rendering, natural textures, and accurate text rendering. Features more realistic human portraits with age-appropriate details like wrinkles and natural skin texture, enhanced landscape and organic texture detail, and superior text integration including Chinese characters. Supports image-to-image generation and various aspect ratios including square, widescreen, portrait, and custom dimensions. Built on a 20 billion parameter Multimodal Diffusion Transformer architecture with optimized performance options for faster generation.

Model id
qwen/qwen-image-2512
Provider
qwen
Output
Image
Price
From 7 credits per run, the same as on voor.ai. Options such as length or resolution can change it.

Request

POST https://voor.ai/v1/generations with "model": "qwen/qwen-image-2512". Poll GET /v1/tasks/{id} or receive the signed webhook. See the overview for keys, idempotency, webhooks and errors.

curl https://voor.ai/v1/generations \
  -H "Authorization: Bearer $VOOR_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
  "model": "qwen/qwen-image-2512",
  "input": {
    "prompt": "A red fox standing in fresh snow at golden hour, soft light"
  },
  "callback_url": "https://example.com/webhooks/voor"
}'

# Then poll the task (or wait for the webhook):
curl https://voor.ai/v1/tasks/TASK_ID \
  -H "Authorization: Bearer $VOOR_API_KEY"

Input parameters

NameTypeDetails
promptrequiredstring

Text prompt for image generation.

reference_imagesarray of URLs

Input image for image2image generation. The aspect ratio of your output will match this image.

Up to 1 files · Accepts image/*

aspect_ratiostring

Default: 16:9

One of: 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, custom

seednumber

Random seed. Set for reproducible generation.

negative_promptstring

Negative prompt for image generation.

Default:

guidancenumber

Guidance for generated image. Use higher values for stronger prompt adherence.

Default: 4

Min 0 · Max 10

stepsnumber

Number of denoising steps. Use less steps for faster generation.

Default: 40

Min 20 · Max 50

output_formatstring

Default: webp

One of: webp, jpg, png

go_fastboolean

Use the model with additional optimizations for faster generation.

Default: true

heightnumber

Height of the generated image. Only used when aspect_ratio=custom. Must be a multiple of 16.

Min 256 · Max 2048

output_qualitynumber

Quality when saving the output images, from 0 to 100. 100 is best quality, 0 is lowest quality. Not relevant for .png outputs.

Default: 95

Min 0 · Max 100

strengthnumber

Strength for image2image generation. 1.0 corresponds to full destruction of information in image.

Default: 0.8

Min 0 · Max 1

widthnumber

Width of the generated image. Only used when aspect_ratio=custom. Must be a multiple of 16.

Min 256 · Max 2048