/seed2 creditsMidjourney onlySeed
Retrieve the numeric seed used for a completed Midjourney generation. Once you have the seed, you can pass it back to /imagine via --seed in the prompt to produce images in a similar style and layout, even with a modified prompt. Useful for creating consistent image series or reproducing a specific aesthetic across multiple generations. Midjourney only.
Request Parameters
| Parameter | Type | Required | Description |
|---|---|---|---|
| task_id | string | Required | Task ID of a completed generation task. |
| webhook_url | string | Optional | URL where we POST the completed task result. |
| webhook_secret | string | Optional | Sent as x-webhook-secret header in webhook delivery. |
Example Request
curl -X POST https://api.journeyapi.com/api/v1/seed \
-H "Authorization: YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"task_id": "550e8400-e29b-41d4-a716-446655440000"
}'Immediate Response
Returns immediately with a task ID. Use /fetch or webhooks to get the result.
{
"task_id": "hh2k0g22-k41n-63p6-m938-668877662222",
"task_type": "seed",
"seed": "3847291056"
}Response Fields
| Field | Type | Description |
|---|---|---|
| task_id | string | UUID of the seed task. |
| task_type | string | Always "seed". |
| seed | string | The numeric seed value used for the generation. |
Tips
- 1Use the seed with --seed in your /imagine prompt to reproduce similar results.
- 2Same prompt + same seed ≈ same image, but not pixel-perfect identical.
Quirks & Gotchas
Note that the field is called task_id (not parent_task_id) — you're referencing the task whose seed you want.
The seed is returned as a string, not a number.
Seed retrieval requires a specific Discord bot DM configuration on the upstream provider. If seeds are not available on your plan, the task will fail.
Expert Tips & Best Practices
Using seeds for consistent image series
If you generate an image with a specific mood or layout you want to replicate, retrieve its seed and include --seed <value> in subsequent /imagine prompts. The seed influences the noise pattern used during generation, so similar prompts with the same seed tend to produce images with consistent spatial layouts and color relationships — useful for product photography series or character consistency across scenes.