Qwen Image Text To Image 2512 LoRA API Documentation

Qwen Image Text To Image 2512 LoRA API Documentation

Playground

Qwen-Image-2512 LoRA is an enhanced 20B MMDiT text-to-image model with LoRA support for fast customization and refined image generation. Ready-to-use REST inference API, best performance, no cold starts, affordable pricing.

Features

Qwen Image 2512 LoRA is an enhanced version of the 20B MMDiT text-to-image model with LoRA support for fine-tuned control over style, characters, or artistic domains. Combine world-class text rendering with personalized generation through custom LoRA weights.

Why Choose This?

• LoRA integration Import external.safetensors LoRA weights and control blending strength via scale parameter. Stack up to 3 LoRAs for hybrid results.

• Superior text rendering Rivals GPT-4o in English and is best-in-class for Chinese typography. Text is seamlessly integrated into images, not overlaid.

• Bilingual support Handles Chinese and English with diverse fonts and complex layouts.

• Style versatility Photorealistic, anime, impressionist, or minimalist styles — all supported with consistent quality.

• Reproducible results Lock the seed to maintain subject consistency when experimenting with different LoRAs.

Parameters

How to Use

1. Enter your prompt — describe the image with detailed narrative and any embedded text.
2. Set size — adjust width and height up to 1536x1536 pixels.
3. Add LoRAs — paste the path or URL of the LoRA.safetensors file (maximum 3 LoRAs).
4. Adjust scale — set LoRA strength (0.5 for subtle, 1.0 for full effect).
5. Set seed (optional) — use -1 for random, or specify a number for reproducibility.
6. Choose output format — select jpeg, png, or webp.
7. Run — preview results and iterate with different LoRA scales.

Pricing

Simple flat-rate pricing regardless of image size or LoRA count.

Best Use Cases

• Character Consistency — Use character LoRAs to maintain identity across multiple generations.
• Style Transfer — Apply specific art style LoRAs for consistent visual branding.
• IP Creation — Combine multiple LoRAs for unique hybrid aesthetics.
• Marketing Materials — Create on-brand visuals with custom trained styles.
• Typography Design — Generate posters, logos, and signage with readable bilingual text.

Pro Tips

• Use specific LoRAs for characters, art styles, or IP consistency.
• Combine multiple LoRAs for hybrid results (e.g., anime + steampunk).
• Adjust scale carefully — too high may distort, too low may fade.
• Lock the seed to maintain subject consistency when swapping LoRAs.

Notes

• Use Qwen Image LoRA Trainer to create compatible LoRAs for this model.
• LoRAs from official platforms (Civitai or Hugging Face) are also supported.
• Processing speed is approximately 6-10 seconds per image.

Related Models

• Qwen Image 2512 — Base text-to-image model without LoRA support.
• Qwen Image Edit 2511 — Image editing model for precise visual modifications.
• Qwen Image Edit Plus — Enhanced editing with dual-mode and bilingual text editing.

Reference

• How to train your LoRA?
• How to use your LoRA?

Authentication

For authentication details, please refer to the Authentication Guide.

API Endpoints

Submit Task & Query Result

set -euo pipefail

export WAVESPEED_API_KEY="your-api-key"

REQUEST_BODY=$(cat <<'JSON'
{
  "prompt": "A cinematic ocean wave at sunrise, highly detailed",
  "size": "1024*1024",
  "seed": -1,
  "output_format": "jpeg"
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/qwen-image/text-to-image-2512-lora" \
  -H "Authorization: Bearer ${WAVESPEED_API_KEY}" \
  -H "Content-Type: application/json" \
  -d "${REQUEST_BODY}")

TASK=$(printf '%s' "${SUBMIT_RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "${TASK}" | jq -r '.id // empty')
if [ -z "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id
' >&2
  exit 1
fi
RESULT_URL=$(printf '%s' "${TASK}" | jq -r '.urls.get // empty')
if [ -z "${RESULT_URL}" ]; then RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"; fi

# 2. Poll until the prediction finishes.
while true; do
  RESPONSE=$(curl --silent --show-error --fail-with-body \
    "${RESULT_URL}" \
    -H "Authorization: Bearer ${WAVESPEED_API_KEY}")
  RESULT=$(printf '%s' "${RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
  STATUS=$(printf '%s' "${RESULT}" | jq -r '.status // empty')

  case "${STATUS}" in
    completed) printf '%s\n' "${RESULT}" | jq '.outputs'; break ;;
    failed|cancelled|timeout) printf '%s\n' "${RESULT}" | jq . >&2; exit 1 ;;
    created|processing) sleep 2 ;;
    *) printf 'Unexpected status: %s
' "${STATUS}" >&2; exit 1 ;;
  esac
done

Parameters

Task Submission Parameters

Request Parameters

Response Parameters

Result Request Parameters

Result Response Parameters