Sign in
Lookbook Studio

Hand it off through the API

Upload the photos, hand off the work, and get the result files when it’s done.

Work handed off through the API is kept as a project, as it is on screen, and comes off the same balance.

  1. Create a key

    Sign in and create one under “API keys” in the left menu. Each person has one key per workspace.

    Every request carries the key in an Authorization: Bearer header. The code below reads the key and the address from these two lines.

    shell
    export FLOW_API_KEY="<api_key>"
    export FLOW_URL="https://flow.unblanq.com"
  2. Upload photos

    Call once for each photo, with slot set to main_item_reference_images. Keep the descriptor from each answer.

    It takes PNG, JPEG and WebP, up to 6 photos in one hand-off. An uploaded photo is kept until the expires_at in its descriptor.

    curl
    curl -X POST \
      "$FLOW_URL/v1/agencies/agency%3Afashion_atelier/actions/fashion_studio_create_product_cuts/uploads" \
      -H "Authorization: Bearer $FLOW_API_KEY" \
      -F "slot=main_item_reference_images" \
      -F "file=@<file>"
  3. Hand it off

    Put the descriptor of each photo in apparel.main_item_reference_images and send. idempotency_key is your own reference for this request.

    Use result.run_id from the answer to check the status, and result.admission.target_id to find the result.

    Send the same idempotency_key with the same inputs again within 24 hours, and nothing new is handed off: you get the first answer back (deduplicated: true). If the inputs differ, it is refused with 409.

    curl
    curl -X POST \
      "$FLOW_URL/v1/agencies/agency%3Afashion_atelier/actions/fashion_studio_create_product_cuts/runs" \
      -H "Authorization: Bearer $FLOW_API_KEY" \
      -H "Content-Type: application/json" \
      -d '{
        "inputs": {
          "schema_version": "fashion_studio_create_product_cuts.input.v12",
          "generation_mode": "initial",
          "initial_source": {"mode": "uploads"},
          "product": {"title": "Tracksuit", "target_gender": "unisex"},
          "apparel": {
            "main_item_title": "Tracksuit",
            "main_item_reference_images": [<descriptor>, <descriptor>]
          },
          "model": {"selection_mode": "auto", "pose_mode": "auto"},
          "space": {"mode": "auto"},
          "outputs": {
            "model_editorial": {"enabled": true, "count": 4},
            "product_detail": {"enabled": true, "count": 4, "style": "styled_flat_lay"}
          }
        },
        "idempotency_key": "request-001"
      }'
  4. Check the status

    Call it every few seconds until the work ends. It has ended when status is one of succeeded, failed, cancelled.

    If it failed, public_errors says why.

    curl
    curl "$FLOW_URL/v1/runs/<run_id>" \
      -H "Authorization: Bearer $FLOW_API_KEY"
  5. Get the result

    The result is kept as a project. First find, in the list, the record_id of the item whose record_key is your target_id. If it isn’t on the first page, put the answer’s next_cursor in cursor for the next page.

    Read with that record_id, and the result files come back as a list in result.outputs. Pick the record_id and revision_id of the one you want. Never put the target_id where the record_id goes.

    To download, send the project’s record_id, and the record_id (as output_record_id) and revision_id of the file you picked. Call the answer’s result.download_url with the same key to get the file.

    curl
    # 1. List: the record_id of the item whose record_key is your target_id
    curl -X POST \
      "$FLOW_URL/v1/agencies/agency%3Afashion_atelier/actions/fashion_studio_list_products/runs" \
      -H "Authorization: Bearer $FLOW_API_KEY" \
      -H "Content-Type: application/json" \
      -d '{"inputs": {"relation": "owned", "limit": 50}}'
    
    # 2. Read: the result files are listed in result.outputs
    curl -X POST \
      "$FLOW_URL/v1/agencies/agency%3Afashion_atelier/actions/fashion_studio_read_product/runs" \
      -H "Authorization: Bearer $FLOW_API_KEY" \
      -H "Content-Type: application/json" \
      -d '{"inputs": {"record_id": "<record_id>"}}'
    
    # 3. Download: the file’s address is in result.download_url
    curl -X POST \
      "$FLOW_URL/v1/agencies/agency%3Afashion_atelier/actions/fashion_studio_download_product_version/runs" \
      -H "Authorization: Bearer $FLOW_API_KEY" \
      -H "Content-Type: application/json" \
      -d '{
        "inputs": {
          "record_id": "<record_id>",
          "output_record_id": "<output_record_id>",
          "revision_id": "<revision_id>",
          "output_format": "png"
        }
      }'
    
    # 4. Get the file: download_url goes after $FLOW_URL
    curl -L "$FLOW_URL<download_url>" \
      -H "Authorization: Bearer $FLOW_API_KEY" \
      -o <filename>

What you sendfashion_studio_create_product_cuts

NameTypeRequiredDescription
apparel object No The main item’s name and photos, required for a new project.
camera object No The camera type (camera_class) and film style (film_profile). If you don’t send it, it’s dslr.
composition_preferences object | null No Choose the aspect ratio (aspect_ratio), focus (focus) and framing (framing). If you don’t send it, they’re auto.
design_text object No Write the language of the text in story cuts and creative cuts as a sentence in language_direction.
environment_setting object No The weather (weather) and time of day (time_of_day). If you don’t send it, it’s clear, late morning to early afternoon.
generation_mode enum: "initial", "additional" Yes Send initial to make a new project.
initial_source object | null No What the project starts from, required for a new project. To start from the photos you uploaded, send {"mode": "uploads"}.
model object No The model in the cuts, and the poses, required for a new project. With auto, it picks a model that fits the target gender from the models you made or that were shared with you (for an administrator, also those of the people they administer), and sets the poses automatically.
outputs object | null No The resolution (resolution_tier) and the number of cuts of each type. If you send it, turn on at least one of model_editorial, product_detail, story_card and creative with enabled.
product object Yes The product name (title) and the target gender (target_gender: female, male or unisex).
round_request_id stringminLength: 1 · maxLength: 256 Yes This request’s reference.
schema_version const: "fashion_studio_create_product_cuts.input.v12" Yes The version of the input format. Send the value shown, as it is.
smart_retouch object No Smart Retouch. With on (the default), you get each model cut and creative cut as one retouched image.
smart_retry object No Smart Retry. Turn it on (enabled), and it remakes any cut whose result has a problem, adding a charge each time.
space object No The shooting space, required for a new project. With auto, it’s set automatically.

You don’t need to send product.product_version_id, product.product_id or round_request_id: Flow fills them in from idempotency_key.

Lookbook Studio

Hand it off now