Z AI Glm Image Edit

Z AI Glm Image Edit

Playground

GLM-Image Edit is a powerful image-to-image editing model that transforms images based on text prompts. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

GLM-Image Image-Edit is Z.AI’s powerful image transformation model that modifies images based on text prompts. Upload up to 4 reference images and describe the changes you want — the model reimagines your images while preserving key elements and applying your requested modifications.

Why Choose This?

• Multi-image reference Upload up to 4 reference images to guide the transformation with richer context.

• Text-guided transformation Describe changes in natural language — lighting, style, time of day, environment, and more.

• Flexible output sizing Custom width and height from 256 to 1536 pixels for any aspect ratio.

• Prompt Enhancer Built-in tool to automatically improve your prompts for better results.

• LLM-powered prompt expansion Optional feature to automatically enhance short prompts with more detail.

Parameters

Output Format Options

• jpeg — Smaller file size, good for photos and web use (default)
• png — Lossless quality, supports transparency, best for graphics

How to Use

1. Write your prompt — describe the transformation you want (e.g., “change to daytime”, “add snow”, “make it cyberpunk style”).
2. Upload reference images — add 1-4 images using ”+ Add Item” button.
3. Set size — adjust width and height (256-1536 pixels).
4. Set seed — use -1 for random results, or specify a number for reproducibility.
5. Choose output format — jpeg for smaller files, png for lossless quality.
6. Enable prompt expansion (optional) — check this to let LLM enhance your prompt.
7. Run — click Run, preview the result, and iterate if needed.

Pricing

Simple flat-rate pricing regardless of image size or number of reference images.

Best Use Cases

• Lighting Changes — Transform day to night, add golden hour, change weather conditions.
• Style Transfer — Apply artistic styles while preserving composition.
• Scene Modification — Add or remove elements, change seasons, modify environments.
• Creative Reimagining — Generate variations based on multiple reference images.
• Content Adaptation — Adjust images for different moods or contexts.

Pro Tips

• Be specific in your transformation prompt — describe exactly what should change.
• Use multiple reference images when you want to blend styles or elements from different sources.
• Enable prompt expansion for short prompts; disable it for precise control.
• Start with default 1024x1024 size, then adjust for specific aspect ratios.
• Use the same seed to compare different prompts on the same reference images.

Notes

• Maximum 4 reference images per generation.
• Size range: 256-1536 pixels for both width and height.
• enable_sync_mode is only available through the API.
• Please ensure your prompts comply with content guidelines.

Related Models

• Z.AI GLM-Image Text-to-Image — Generate images from text prompts only.
• Z.AI CogView-4 — Z.AI’s high-quality text-to-image model with flexible quality modes.
• Qwen Image Edit 2511 — Precise image editing with text instructions.

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",
  "images": [
    "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg"
  ],
  "seed": -1,
  "output_format": "jpeg",
  "enable_prompt_expansion": false
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/z-ai/glm-image/edit" \
  -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