Explorer
Syncing—

AI-Generated Image Detection - image-forensics and Hive compatible APIService

ai-generated-image-detection

AI-generated image detection, served through the image-forensics /v1/detect API and a Hive-compatible /api/v2/task/sync layer over the same detector. The expected endpoints are POST /v1/detect, POST /api/v2/task/sync and GET /readyz; suppliers MAY expose more (GET /v1/models, the Sightengine compatibility layer) but consumers MUST NOT depend on it. Responses are probabilities, not verdicts. This service is model-agnostic: suppliers choose their own detector and crop policy, so scores, calibration, and detection quality vary and are not guaranteed by the protocol; each native response carries a pipeline_fingerprint identifying the weights and crop policy.

Active Suppliers
5
of 5 ever configured
Service Info
Service ID
ai-generated-image-detection
Compute Units / Relay
35,000
Owner
pokt1m…pewk
Active Applications
1
Relay Mining EMA
1 relays
Service Metadata Cardsource: on-chain metadata (LCD)
{8 items
"schema":"pocket-service-card/v1"
"description":"AI-generated image detection, served through the image-forensics /v1/detect API and a Hive-compatible /api/v2/task/sync layer over the same detector. The expect..."
"rpc_types":[1 item
0:{4 items
"type":"REST"
"intent":"expected"
"backend_hint":"image-forensics service on :8000 (image-forensics-service, endpoints.detect enabled); mount at /"
"notes":"Only POST /v1/detect, POST /api/v2/task/sync (Hive envelope; Authorization: token is accepted and ignored) and GET /readyz are expected. Request body is multipa..."
}
]
"apis":[2 items
0:"image-forensics-detect"
1:"hive-task-sync"
]
"specs":[2 items
0:{3 items
"kind":"markdown"
"url":"https://raw.githubusercontent.com/pnyxai/pocket-network-services/6f3912ee520cb75a98288aaf333d6ba1ef729788/mainnet/docs_ai-generated-image-detection.md"
"sha256":"f533ae32729c370ce32f47511a8294e3650c968b1c22818ebe763161f38da755"
}
1:{3 items
"kind":"openapi"
"url":"https://raw.githubusercontent.com/RawthiL/image-forensics-service/0f312c3d70c62b1f89c4efef4843b30e32df2f9b/docs/openapi.json"
"sha256":"8458c376a583b9347f26f4f3f00d6ad2a176170f9ba5f3ebf1328590465d8ec6"
}
]
"access":"public"
"results":"variable"
"serving":{3 items
"backend":"Any server exposing POST /v1/detect, POST /api/v2/task/sync and GET /readyz with the request/response shapes of the OpenAPI document in specs[1]. Recommended: i..."
"healthcheck":[1 item
0:{3 items
"rpc_type":"REST"
"request":{2 items
"path":"/readyz"
"method":"GET"
}
"expect":{2 items
"json_path":"$.endpoints.detect.pipeline"
"matches":".+"
}
}
]
"notes":"Recommended model: Community Forensics commfor-384 (MIT) with the default five-crop policy and max aggregation. If you already run Triton, the triton image need..."
}
}