Seedream 5.5
Text to image · Image editing
Starting price $0.05 / image
By Alibaba
Qwen Group Photo puts people from separate portraits into one shared photo, in a setting you describe.
qwen-image-edit-plus-lora-gallery/group-photoQuote the input, start the generation with the quote, then poll the job. Set RAYWAKE_API_KEY first; see Authentication.
# 1. Price the exact input (quotes are valid for up to 10 minutes)
curl -s https://api.raywake.com/v1/quotes \
-H "Authorization: Bearer $RAYWAKE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "qwen-image-edit-plus-lora-gallery/group-photo",
"input": {
"image_urls": [
"https://example.com/input.png"
],
"prompt": "Three friends standing arm in arm on a pier at sunset, the sea behind them, a warm summer evening."
}
}'
# 2. Start the generation with the quote_id from step 1
curl -s https://api.raywake.com/v1/generate \
-H "Authorization: Bearer $RAYWAKE_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: $(uuidgen)" \
-d '{"model": "qwen-image-edit-plus-lora-gallery/group-photo", "quote_id": "QUOTE_ID", "input": {"image_urls":["https://example.com/input.png"],"prompt":"Three friends standing arm in arm on a pier at sunset, the sea behind them, a warm summer evening."}}'
# 3. Poll until the status is terminal
curl -s https://api.raywake.com/v1/jobs/JOB_ID \
-H "Authorization: Bearer $RAYWAKE_API_KEY"| Name | Type | Description |
|---|---|---|
image_urlsrequired | array of image URLs | The URLs of the images to combine into a group photo. Provide 2 or more individual portrait images. |
image_size | string (enum) | The size of the generated image. If not provided, the size of the final input image will be used. |
guidance_scale | number | The CFG (Classifier Free Guidance) scale. Controls how closely the model follows the prompt. |
num_inference_steps | integer | The number of inference steps to perform. |
acceleration | string (enum) | Acceleration level for image generation. 'regular' balances speed and quality. |
negative_prompt | string | The negative prompt for the generation |
seed | integer | Random seed for reproducibility. Same seed with same prompt will produce same result. |
sync_mode | boolean | If `True`, the media will be returned as a data URI and won't be saved in history. |
output_format | string (enum) | The format of the output image |
num_images | integer | Number of images to generate |
prompt | string | Describe the group photo scene, setting, and style. The model will maintain character consistency and add vintage effects like grain, blur, and retro filters. |
lora_scale | number | The scale factor for the LoRA model. Controls the strength of the LoRA effect. |
A succeeded job lists its results under outputs, stored on our side. See Jobs for every field.
"outputs": [
{ "type": "image", "url": "https://…", "mime_type": "image/png", "thumbnail_url": "https://…" }
]The exact charge for your input comes from a quote. How charges settle
Fields marked * are required. Review the price before generating.
Upload two or more portraits, one person each, and describe the scene. The model places everyone in the same picture, keeps each face recognizable and adds a vintage film look with grain, soft blur and retro color.
Make one to four images per run, as PNG, JPEG or WebP, in a square, portrait or landscape size.
Check every face, subject count and relative height. The composite does not document a real gathering.