Luma Photon Flash
Playground
Try it on WaveSpeedAI!Luma Photon Flash is a Luma text-to-image model that generates images directly from text prompts. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Features
Generate images at incredible speed and unbeatable value with Luma Photon Flash. At just $0.005 per image, this ultra-fast text-to-image model delivers quality results for rapid prototyping, high-volume generation, and budget-conscious creative work.
Looking for higher quality? Try Luma Photon for enhanced output.
Why It Looks Great
- Unbeatable price: Just $0.005 per image — generate 200 images for $1.
- Flash speed: Optimized for the fastest possible generation.
- Atmospheric scenes: Creates mood-driven, emotionally resonant imagery.
- Prompt Enhancer: Built-in tool to refine your descriptions automatically.
- High-volume ready: Perfect for batch generation and rapid iteration.
Parameters
| Parameter | Required | Description |
|---|---|---|
| prompt | Yes | Text description of the image you want to generate. |
How to Use
- Write your prompt — describe the scene, mood, and atmosphere.
- Use Prompt Enhancer (optional) — click to automatically enrich your description.
- Run — click the button to generate.
- Download — preview and save your image.
Pricing
Flat rate per image.
| Output | Cost |
|---|---|
| Per image | $0.005 |
| 100 images | $0.50 |
| 1,000 images | $5.00 |
Best Use Cases
- Rapid Prototyping — Test concepts and ideas at minimal cost.
- High-Volume Generation — Produce large batches affordably.
- Mood Boards — Generate multiple atmospheric images for inspiration.
- Social Media Content — Create visuals for posts and stories quickly.
- Creative Exploration — Experiment freely without budget concerns.
Example Prompts
- “Teen girl journaling in bed by phone flashlight, stuffed animals around her, stickers on the wall, cozy and introspective vibe”
- “Neon-lit ramen shop at night, steam rising, lonely customer at counter”
- “Cat sleeping on a sunny windowsill, dust particles in light, peaceful afternoon”
- “Abandoned amusement park at dusk, nostalgic and slightly eerie atmosphere”
- “Couple sharing headphones on a train, city lights passing by window”
Model Comparison
| Model | Cost | Speed | Best For |
|---|---|---|---|
| Photon Flash | $0.005 | Fastest | High-volume, prototyping, budget work |
| Photon | Higher | Standard | Quality output, final deliverables |
Pro Tips for Best Results
- Include mood and atmosphere: “cozy”, “introspective”, “nostalgic”, “peaceful”.
- Describe lighting conditions: “phone flashlight”, “neon-lit”, “sunny”.
- Add environmental details for richer scenes.
- At $0.005, generate many variations and pick the best.
- Perfect for exploring ideas before committing to higher-quality generation.
- Flash excels at atmospheric, mood-driven scenes.
Notes
- The most affordable text-to-image option available.
- Flash mode prioritizes speed and cost efficiency.
- Ideal for testing prompts before using premium models.
- Processing is optimized for rapid turnaround.
Authentication
For authentication details, please refer to the Authentication Guide.
API Endpoints
Submit Task & Query Result
set -euo pipefail
export WAVESPEED_API_KEY="your-api-key"
REQUEST_BODY=$(cat <<'JSON'
{
"prompt": "A cinematic ocean wave at sunrise, highly detailed"
}
JSON
)
# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
-X POST "https://api.wavespeed.ai/api/v3/luma/photon-flash" \
-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
doneParameters
Task Submission Parameters
Request Parameters
| Parameter | Type | Required | Default | Range | Description |
|---|---|---|---|---|---|
| prompt | string | Yes | - | The positive prompt for the generation. | |
| enable_base64_output | boolean | No | false | - | If set to `true`, the prediction's `output` strings are returned as **naked base64** (no `data:<mime>;base64,` prefix). When `false` (default), outputs are returned as URLs pointing to our CDN. |
Response Parameters
| Parameter | Type | Description |
|---|---|---|
| code | integer | HTTP status code (e.g., 200 for success) |
| message | string | Status message (e.g., “success”) |
| data.id | string | Unique identifier for the prediction, Task Id |
| data.model | string | Model ID used for the prediction |
| data.outputs | array | Output values, usually URL strings; some models return text strings or structured result objects (empty when status is not completed) |
| data.urls | object | Object containing related API endpoints |
| data.urls.get | string | URL to retrieve the prediction result |
| data.status | string | Status of the task: created, processing, completed, or failed |
| data.created_at | string | ISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”) |
| data.error | string | Error message (empty if no error occurred) |
| data.timings | object | Object containing timing details |
| data.timings.inference | integer | Inference time in milliseconds |
Result Request Parameters
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
| id | string | Yes | - | Task ID |
Result Response Parameters
| Parameter | Type | Description |
|---|---|---|
| code | integer | HTTP status code (e.g., 200 for success) |
| message | string | Status message (e.g., “success”) |
| data | object | The prediction data object containing all details |
| data.id | string | Unique identifier for the prediction |
| data.model | string | Model ID used for the prediction |
| data.outputs | array<string | object> | Array of generated outputs (empty when status is not completed). Items are usually URL strings, but may be text strings or structured result objects, depending on the model. |
| data.urls | object | Object containing related API endpoints |
| data.urls.get | string | URL to poll for the prediction result |
| data.status | string | Status: created, processing, completed, or failed |
| data.created_at | string | ISO timestamp of when the request was created |
| data.error | string | Error message (empty if no error occurred) |
| data.timings | object | Object containing timing details |
| data.timings.inference | integer | Inference time in milliseconds |