Reve 2 Serverless API
Generate and edit 4K images with sharp in-image text.
POST /v2/reve-2 · submit + poll 1# pip install "segmind>=1.1.0"
2# export SEGMIND_API_KEY="YOUR_API_KEY"
3import segmind
4
5# Async (v2): submit to the queue and block until COMPLETED.
6# run() returns the final result dict (600s deadline, 1.0s poll by default).
7result = segmind.run(
8 "reve-2",
9 prompt="A cinematic close-up portrait of an elderly Japanese ceramicist in his sunlit workshop, weathered hands cradling a freshly glazed tea bowl, fine clay dust drifting in a shaft of warm afternoon light, shelves of pottery softly blurred behind him, ultra-detailed skin texture, natural catchlights in the eyes, photorealistic, shot on 85mm lens, shallow depth of field",
10 aspect_ratio="3:2",
11 remove_background=False,
12)
13print(result["status"]) # COMPLETED
14print(result.get("output")) # model output (e.g. media URL)
15print(result["metrics"]["inference_time"]) # server compute seconds
16
17# --- Or submit + poll manually (track request_id, control the cadence) ---
18from segmind import SegmindClient, InferenceFailed, InferenceTimeout
19
20client = SegmindClient() # reads SEGMIND_API_KEY
21payload = {
22 "prompt": "A cinematic close-up portrait of an elderly Japanese ceramicist in his sunlit workshop, weathered hands cradling a freshly glazed tea bowl, fine clay dust drifting in a shaft of warm afternoon light, shelves of pottery softly blurred behind him, ultra-detailed skin texture, natural catchlights in the eyes, photorealistic, shot on 85mm lens, shallow depth of field",
23 "aspect_ratio": "3:2",
24 "remove_background": False,
25}
26job = client.submit_async("reve-2", **payload)
27print(job.request_id) # available immediately
28try:
29 result = job.wait(timeout=600, interval=1.0)
30except InferenceTimeout as e:
31 print("still running:", e.request_id)
32except InferenceFailed as e:
33 print("failed:", e.detail) 1# pip install "segmind>=1.1.0"
2# export SEGMIND_API_KEY="YOUR_API_KEY"
3import segmind
4
5# Async (v2): submit to the queue and block until COMPLETED.
6# run() returns the final result dict (600s deadline, 1.0s poll by default).
7result = segmind.run(
8 "reve-2",
9 prompt="A cinematic close-up portrait of an elderly Japanese ceramicist in his sunlit workshop, weathered hands cradling a freshly glazed tea bowl, fine clay dust drifting in a shaft of warm afternoon light, shelves of pottery softly blurred behind him, ultra-detailed skin texture, natural catchlights in the eyes, photorealistic, shot on 85mm lens, shallow depth of field",
10 aspect_ratio="3:2",
11 remove_background=False,
12)
13print(result["status"]) # COMPLETED
14print(result.get("output")) # model output (e.g. media URL)
15print(result["metrics"]["inference_time"]) # server compute seconds
16
17# --- Or submit + poll manually (track request_id, control the cadence) ---
18from segmind import SegmindClient, InferenceFailed, InferenceTimeout
19
20client = SegmindClient() # reads SEGMIND_API_KEY
21payload = {
22 "prompt": "A cinematic close-up portrait of an elderly Japanese ceramicist in his sunlit workshop, weathered hands cradling a freshly glazed tea bowl, fine clay dust drifting in a shaft of warm afternoon light, shelves of pottery softly blurred behind him, ultra-detailed skin texture, natural catchlights in the eyes, photorealistic, shot on 85mm lens, shallow depth of field",
23 "aspect_ratio": "3:2",
24 "remove_background": False,
25}
26job = client.submit_async("reve-2", **payload)
27print(job.request_id) # available immediately
28try:
29 result = job.wait(timeout=600, interval=1.0)
30except InferenceTimeout as e:
31 print("still running:", e.request_id)
32except InferenceFailed as e:
33 print("failed:", e.detail)API Endpoint
https://api.segmind.com/v1/reve-2Parameters
promptrequiredstringText describing the image to generate. To edit or remix the reference images, refer to them inline with a <frame>N</frame> tag, where N is the image's 0-based index in the Reference images list — e.g. "Remove the people in the background of <frame>0</frame>" edits the first image, and "put the hat from <frame>1</frame> onto <frame>0</frame>" combines two.
"a red fox sitting in a snowy pine forest at golden hour, soft backlight through the trees, photorealistic, shallow depth of field"aspect_ratiooptionalstringOutput aspect ratio. "Auto" lets Reve pick the best fit for the prompt.
"auto""auto""4:1""3:1""21:9""2:1""17:9""16:9""3:2""4:3""5:4"+8 moreimage_urlsoptionalstring[]Optional reference images to edit or remix — up to 8. Refer to them from the prompt with <frame>N</frame>, where N is the 0-based index in this list (first image = <frame>0</frame>). Leave empty for plain text-to-image.
[]remove_backgroundoptionalbooleanReturn a transparent-background PNG. Adds $0.01.
falseResponse Type
Returns: Text/JSON
Asynchronous requests (v2)
Use Async for video, long-running (>~60s), or high-concurrency workloads; Sync is simplest for fast image & LLM calls. Async submits a request and you poll it to completion.
- 1
POST /v2/reve-2Submit — returns request_id, status_url, response_url
- 2
GET /v2/requests/{id}/statusPoll — until COMPLETED or FAILED
- 3
GET /v2/requests/{id}Result — final response body
Status states
- A FAILED request is served as HTTP 422 — the body still carries the error detail.
- An unknown or expired request_id returns HTTP 404.
- Results are retained for 1 hour, then expire.
- Content / RAI blocks surface as FAILED, not a separate state.
- Track completion by polling the status endpoint.
Common Error Codes
The API returns standard HTTP status codes. Detailed error messages are provided in the response body.
Bad Request
Invalid parameters or request format
Unauthorized
Missing or invalid API key
Forbidden
Insufficient permissions
Not Found
Model or endpoint not found
Insufficient Credits
Not enough credits to process request
Rate Limited
Too many requests
Server Error
Internal server error
Bad Gateway
Service temporarily unavailable
Timeout
Request timed out