Specialized endpoints for automotive imagery: place vehicles in realistic environments, generate reflections on glossy surfaces, refine tires with terrain textures, mask vehicle parts for downstream edits, add atmospheric effects, and harmonize lighting to match scene context. Commercially safe, royalty-free, built on Bria's product vehicle pipeline.
\nUse this skill when the user is working with any vehicle image — cars, trucks, SUVs, motorcycles, vans. Triggers on:
\nFor non-vehicle image work, use bria-ai (general image generation/editing) or remove-background (transparent PNGs). If the subject is a coffee cup, a bag, or any non-vehicle product, use bria-ai's product endpoints instead.
\nThis skill does one category of thing well: vehicle-aware image operations.
\nBefore making any API call, you need a valid Bria access token.
\nif [ -f ~/.bria/credentials ]; then\n BRIA_ACCESS_TOKEN=$(grep '^access_token=' \"$HOME/.bria/credentials\" | cut -d= -f2-)\n BRIA_API_KEY=$(grep '^api_token=' \"$HOME/.bria/credentials\" | cut -d= -f2-)\nfi\nif [ -z \"$BRIA_ACCESS_TOKEN\" ]; then\n echo \"NO_CREDENTIALS\"\nelif [ -n \"$BRIA_API_KEY\" ]; then\n echo \"READY\"\nelse\n echo \"CREDENTIALS_FOUND\"\nfi\nIf the output is READY, skip straight to making API calls — no introspection needed.\nIf the output is CREDENTIALS_FOUND, skip to Step 3.\nIf the output is NO_CREDENTIALS, proceed to Step 2.
2a. Request a device code:
\nDEVICE_RESPONSE=$(curl -s -X POST \"https://engine.prod.bria-api.com/v2/auth/device/authorize\" \\\n -H \"Content-Type: application/json\")\necho \"$DEVICE_RESPONSE\"\nParse the response fields:
\ndevice_code — used to poll for the token (keep this, don't show to user)user_code — the code the user must enter (e.g. BRIA-XXXX)interval — seconds between poll attempts2b. Show the user a single sign-in link. Tell them exactly this — nothing more:
\n\n\nConnect your Bria account: Click here to sign in\nYour code is — it's already filled in.
\n
Do NOT show two links. Do NOT show the raw URL separately. Do NOT use verification_uri from the API response. Keep it to one clickable link.
2c. Poll for the token. After showing the user the code, immediately start polling:
\nfor i in $(seq 1 60); do\n TOKEN_RESPONSE=$(curl -s -X POST \"https://engine.prod.bria-api.com/v2/auth/token\" \\\n -d \"grant_type=urn:ietf:params:oauth:grant-type:device_code\" \\\n -d \"device_code=$DEVICE_CODE\")\n ACCESS_TOKEN=$(printf '%s' \"$TOKEN_RESPONSE\" | sed -n 's/.*\"access_token\" *: *\"\\([^\"]*\\)\".*/\\1/p')\n if [ -n \"$ACCESS_TOKEN\" ]; then\n BRIA_ACCESS_TOKEN=\"$ACCESS_TOKEN\"\n REFRESH_TOKEN=$(printf '%s' \"$TOKEN_RESPONSE\" | sed -n 's/.*\"refresh_token\" *: *\"\\([^\"]*\\)\".*/\\1/p')\n mkdir -p ~/.bria\n printf 'access_token=%s\\nrefresh_token=%s\\n' \"$BRIA_ACCESS_TOKEN\" \"$REFRESH_TOKEN\" > \"$HOME/.bria/credentials\"\n echo \"AUTHENTICATED\"\n break\n fi\n sleep 5\ndone\nIf the output contains AUTHENTICATED, proceed to Step 3. Otherwise the code expired — start over from Step 2a.
Do not proceed with any API call until authentication is confirmed.
\nINTROSPECT=$(curl -s -X POST \"https://engine.prod.bria-api.com/v2/auth/token/introspect\" \\\n -d \"token=$BRIA_ACCESS_TOKEN\")\nBILLING_STATUS=$(printf '%s' \"$INTROSPECT\" | sed -n 's/.*\"billing_status\" *: *\"\\([^\"]*\\)\".*/\\1/p')\nif [ \"$BILLING_STATUS\" = \"blocked\" ]; then\n BILLING_MSG=$(printf '%s' \"$INTROSPECT\" | sed -n 's/.*\"billing_message\" *: *\"\\([^\"]*\\)\".*/\\1/p')\n echo \"BILLING_ERROR: $BILLING_MSG\"\nfi\nACTIVE=$(printf '%s' \"$INTROSPECT\" | sed -n 's/.*\"active\" *: *\\([^,}]*\\).*/\\1/p' | tr -d ' ')\nif [ \"$ACTIVE\" = \"false\" ]; then\n printf '' > \"$HOME/.bria/credentials\"\n echo \"TOKEN_EXPIRED\"\nfi\nBRIA_API_KEY=$(printf '%s' \"$INTROSPECT\" | sed -n 's/.*\"api_token\" *: *\"\\([^\"]*\\)\".*/\\1/p')\nif [ -n \"$BRIA_API_KEY\" ]; then\n grep -v '^api_token=' \"$HOME/.bria/credentials\" > \"$HOME/.bria/credentials.tmp\" 2>/dev/null || true\n printf 'api_token=%s\\n' \"$BRIA_API_KEY\" >> \"$HOME/.bria/credentials.tmp\"\n mv \"$HOME/.bria/credentials.tmp\" \"$HOME/.bria/credentials\"\nfi\nBILLING_ERROR: ... — relay the message to the user exactly as shown and stop.TOKEN_EXPIRED — tell the user their session expired and restart from Step 2.BRIA_API_KEY is cached. Proceed.| Endpoint | \nPath | \nWhat it does | \n
|---|---|---|
| Vehicle Shot by Text | \nPOST /v1/product/vehicle/shot_by_text | \nPlace a vehicle in a text-described environment (road, garage, mountain, city night) | \n
| Vehicle Segmentation | \nPOST /v1/product/vehicle/segment | \nReturn binary masks for windshield, rear window, side windows, body, wheels, hubcaps, tires | \n
| Generate Reflections | \nPOST /v1/product/vehicle/generate_reflections | \nPaint realistic reflections onto glass, metal, and glossy bodywork | \n
| Refine Tires | \nPOST /v1/product/vehicle/refine_tires | \nReplace tire textures with snow, mud, or grass using a tire mask | \n
| Apply Effects | \nPOST /v1/product/vehicle/apply_effect | \nOverlay atmospheric effects: dust, snow, fog, light leaks, lens flare | \n
| Harmonize | \nPOST /v1/product/vehicle/harmonize | \nApply lighting presets: hot-day, cold-day, hot-night, cold-night | \n
The typical multi-step pipeline: segment → refine tires / add reflections → apply effects → harmonize lighting.
\nUse bria_call for all API calls. It handles URL passthrough, local file base64 encoding, JSON construction, API call, and async polling in a single function call. The API key is auto-loaded from ~/.bria/credentials.
First, source the helper script at references/code-examples/bria_client.sh (resolve relative to this skill's directory).
source <SKILL_DIR>/references/code-examples/bria_client.sh\n\n# Place vehicle in a text-described scene\nRESULT=$(bria_call /v1/product/vehicle/shot_by_text \"/path/to/car.png\" \\\n '\"scene_description\": \"coastal highway at sunset, dramatic sky\", \"placement_type\": \"automatic\", \"num_results\": 1')\n\n# Segment vehicle parts → returns URLs for body, wheels, windows, tires, etc.\nRESULT=$(bria_call /v1/product/vehicle/segment \"/path/to/car.png\")\n\n# Add reflections (pairs well with segment output)\nRESULT=$(bria_call /v1/product/vehicle/generate_reflections \"/path/to/car.png\")\n\n# Refine tires with snow texture (requires a tire mask)\nRESULT=$(bria_call /v1/product/vehicle/refine_tires \"/path/to/car.png\" \\\n --key image \\\n '\"tire_mask\": \"https://cdn.example.com/tires_mask.png\", \"surface\": \"snow\"')\n\n# Apply atmospheric dust effect\nRESULT=$(bria_call /v1/product/vehicle/apply_effect \"/path/to/car.png\" \\\n '\"effect\": \"dust\", \"layers\": false')\n\n# Harmonize to cold-night lighting\nRESULT=$(bria_call /v1/product/vehicle/harmonize \"/path/to/car.png\" \\\n '\"preset\": \"cold-night\"')\n\necho \"$RESULT\"\nCalling convention: bria_call <endpoint> <image_or_empty> [--key <json_key>] [extra JSON fields...]
\"\" (empty) for endpoints without a primary image input'\"key\": \"value\"'See API Endpoints Reference for the full parameter list, placement options, response schemas, and error codes.
\nsource <SKILL_DIR>/references/code-examples/bria_client.sh\n\n# 1. Place the vehicle in a scene\nSCENE_URL=$(bria_call /v1/product/vehicle/shot_by_text \"/path/to/car.png\" \\\n '\"scene_description\": \"empty mountain road with snow flurries\", \"placement_type\": \"automatic\"')\n\n# 2. Harmonize lighting to match a cold night\nFINAL_URL=$(bria_call /v1/product/vehicle/harmonize \"$SCENE_URL\" \\\n '\"preset\": \"cold-night\"')\n\ncurl -sL \"$FINAL_URL\" -o car_cold_night.jpg\n# 1. Segment tires\nMASKS=$(bria_call /v1/product/vehicle/segment \"/path/to/car.png\")\nTIRES_MASK=$(printf '%s' \"$MASKS\" | sed -n 's/.*\"tires\" *: *\"\\([^\"]*\\)\".*/\\1/p')\n\n# 2. Apply mud surface to tires\nMUDDY=$(bria_call /v1/product/vehicle/refine_tires \"/path/to/car.png\" \\\n --key image \\\n \"\\\"tire_mask\\\": \\\"$TIRES_MASK\\\", \\\"surface\\\": \\\"mud\\\"\")\n\n# 3. Add dust effect\nFINAL=$(bria_call /v1/product/vehicle/apply_effect \"$MUDDY\" \\\n '\"effect\": \"dust\"')\n\ncurl -sL \"$FINAL\" -o offroad.jpg\n# Add reflections on glass and bodywork\nSHOWROOM=$(bria_call /v1/product/vehicle/generate_reflections \"/path/to/car.png\")\n\n# Harmonize to bright hot-day lighting\nFINAL=$(bria_call /v1/product/vehicle/harmonize \"$SHOWROOM\" \\\n '\"preset\": \"hot-day\"')\n\ncurl -sL \"$FINAL\" -o showroom.jpg\n| Placement | \nWhat it controls | \n
|---|---|
original | \nKeep the vehicle's current position and size | \n
automatic | \nAuto-select up to 7 good placements | \n
manual_placement | \nUse a predefined position (top-left, center, etc.) | \n
custom_coordinates | \nFull control via x/y/width/height | \n
manual_padding | \nPixel-based padding around the subject | \n
automatic_aspect_ratio | \nCenter the subject; resize canvas to target ratio | \n
See the full list of conditional parameters in API Endpoints Reference.
\nPair shot_by_text for the environment with harmonize for a final lighting pass — the two together produce the most cohesive results.
bria_call handles auth, base64, JSON, pollingshot_by_text)