3D

IDOL Image to 3D Splat

IDOL: one picture of an object to a 3D Gaussian splat PLY.

Built with DINOv3.

Copyright (c) 2026 VAST

모델 라이선스

IDOL · Apache-2.0

Apache License 2.0. Keep the licence text with the weights. Card declares apache-2.0; the repo publishes no LICENSE file, so the standard text is shipped.

포함된 라이선스

고지

DINOv3 ViT-H+/16 · LicenseRef-DINOv3-License

Redistribution under the DINOv3 License with a copy of it; use must comply with trade-control law (no ITAR, military, nuclear or weapons end uses); no reverse engineering. Research publications must acknowledge DINO Materials. The text sets no commercial-use limit and no Built-with label; the label is Mesh's choice.

포함된 라이선스

BiRefNet · MIT

MIT, Copyright (c) 2024 ZhengPeng. Keep the copyright and permission notice. The HF repo has no LICENSE file; the text is from the GitHub repo.

포함된 라이선스

FLUX.2-klein-4B VAE encoder · Apache-2.0

Apache License 2.0. Keep the licence text with the weights. Only the encoder is kept.

포함된 라이선스

TripoSplat (probable IDOL denoiser ancestor) · MIT

Conservative notice preservation for probable lineage, not a claim of checkpoint identity. Keep VAST copyright and MIT permission notice.

포함된 라이선스

무료온라인무제한IDOL API 액세스

API 레퍼런스

REST로 제출

개인 API 키(msk_…)를 사용하여 내 도구에서 이 워크로드의 작업을 생성하세요. 이렇게 시작한 작업은 내 기기에서 연결한 기기와 동일한 기기에서 실행되며, 최소 한 대는 온라인이어야 합니다.

API 세부 정보 숨기기
POSThttps://cp.meshlabs.cloud/v1/organizations/jobs

X-Organization-Api-Key: msk_your_personal_api_key로 인증합니다. 헤더 이름은 조직 키와 같으며, 개인 키도 같은 엔드포인트를 사용합니다.

입력 파일:같은 API 키로 POST https://cp.meshlabs.cloud/v1/organizations/job-inputs/presign을(를) 호출하고, 반환된 upload_url에 파일을 업로드한 다음, job_spec에 download_url을(를) 전달하세요(예: input_image_url로).

요청 본문

{
  "workload_type": "idol-i2gs",
  "job_spec": {
    "input_image_url": "https://…/your-input.png",
    "mode": "synthetic",
    "steps": 50,
    "cfg_strength": 3,
    "rescale_t": 3,
    "num_gaussians": 1048576,
    "seed": 0
  }
}

job_spec 필드

필드필수기본값설명
input_image_url예—The picture: an object on a transparent background (a PNG with its alpha).
mode예—Whether the picture is a synthetic render or a real photograph. It sets the crop margin.
crop_margin아니요—The crop around the object. Defaults to 1.2 for synthetic and 1.7 for real.
steps아니요50Denoising steps.
cfg_strength아니요3Guidance against an empty condition. 0 turns it off and halves the work.
rescale_t아니요3How far the time grid is shifted towards noise.
num_gaussians아니요1048576Gaussians in the splat, a multiple of 32.
seed아니요0Random seed. No seed is seed 0.

cURL

curl -X POST https://cp.meshlabs.cloud/v1/organizations/jobs \
  -H "X-Organization-Api-Key: msk_your_personal_api_key" \
  -H "Content-Type: application/json" \
  -d '{
  "workload_type": "idol-i2gs",
  "job_spec": {
    "input_image_url": "https://…/your-input.png",
    "mode": "synthetic",
    "steps": 50,
    "cfg_strength": 3,
    "rescale_t": 3,
    "num_gaussians": 1048576,
    "seed": 0
  }
}'
GEThttps://cp.meshlabs.cloud/v1/organizations/jobs/{job_id}

status이(가) 최종 상태(COMPLETED, FAILED, CANCELED 또는 MODERATION_BLOCKED)가 될 때까지 같은 API 키로 폴링하세요. 콘텐츠 검토가 활성화된 경우, 작업은 컴퓨팅 대기열에 들어가기 전에 MODERATION_PENDING 상태로 시작할 수 있습니다. 완료된 작업의 각 출력에는 사전 서명된 download_url 값이 포함됩니다.

생성 응답

{
  "id": "3fa85f64-5717-4562-b3fc-2c963f66afa6",
  "workload_type": "idol-i2gs",
  "status": "PENDING",
  "job_spec_json": {
    "input_image_url": "https://…/your-input.png",
    "mode": "synthetic",
    "steps": 50,
    "cfg_strength": 3,
    "rescale_t": 3,
    "num_gaussians": 1048576,
    "seed": 0
  },
  "work_units": [],
  "outputs": [],
  "created_at": "2026-06-08T12:00:00Z",
  "updated_at": "2026-06-08T12:00:00Z"
}

완료 응답

{
  "id": "3fa85f64-5717-4562-b3fc-2c963f66afa6",
  "workload_type": "idol-i2gs",
  "status": "COMPLETED",
  "job_spec_json": {
    "input_image_url": "https://…/your-input.png",
    "mode": "synthetic",
    "steps": 50,
    "cfg_strength": 3,
    "rescale_t": 3,
    "num_gaussians": 1048576,
    "seed": 0
  },
  "work_units": [
    {
      "id": "…",
      "index": 0,
      "status": "COMPLETED"
    }
  ],
  "outputs": [
    {
      "id": "…",
      "output_type": "<output type>",
      "filename": "<output filename>",
      "size_bytes": 524288,
      "download_url": "<presigned output download URL>"
    }
  ],
  "created_at": "2026-06-08T12:00:00Z",
  "updated_at": "<completion timestamp>"
}

Upload one picture of an object on a transparent background and download a 3D Gaussian splat as a PLY file. IDOL runs 50 denoising steps and up to 1,048,576 Gaussians.