Reconviagen 0.5

From 300 credits/call
ae_reconviagen_0_5

Turn one or more images of the same object into a textured 3D model in GLB format.

Image
From 300 credits/call

Pricing

From 300 credits/call
ResolutionCharge
512300 credits/call
1024 / Not specified360 credits/call
1536420 credits/call

Starting price applies to Resolution: 512.

Parameters

Optional parameters use the platform defaults when omitted.

ParameterTypeRequiredDescriptionDefault
request_bodyobjectYesNo parameter description.—
request_body.seedinteger | unknownNoRandom seed for reproducibility—
request_body.ss_sourceenum (direct | mesh | mvtrellis2)NoSparse structure source. 'mesh' gives best quality, 'direct' is fastest, 'mvtrellis2' uses multi-view TRELLIS.2.mesh
request_body.image_urlsarrayYesOne or more views of the same object. Multiple views yield higher-quality 3D reconstruction.—
request_body.resolutionenum (512 | 1024 | 1536)NoOutput resolution; higher is slower but more detailed1024
request_body.ss_rescale_tnumberNoControls noise schedule sharpness for structure generation.5
request_body.texture_sizeenum (1024 | 2048 | 4096)NoResolution of the texture image baked onto the mesh.2048
request_body.slat_rescale_tnumberNoRescale T for SLat stage (only used when ss_source='mesh').3
request_body.decimation_targetintegerNoTarget number of vertices in the final mesh.500000
request_body.ss_sampling_stepsintegerNoNumber of denoising steps for the initial structure.12
request_body.tex_slat_rescale_tnumberNoControls noise schedule sharpness for texture generation.3
request_body.slat_sampling_stepsintegerNoSampling steps for SLat stage (only used when ss_source='mesh').12
request_body.ss_guidance_rescalenumberNoDampens artifacts from high guidance in stage 1.0.7
request_body.multi_image_strategyenum (average_right | weighted_average | sequential | average | adaptive_guidance_weight | fixed_guidance_rescale)NoStrategy for combining multi-view conditioning. 'adaptive_guidance_weight' works best in most cases. Only used when more than one image is provided.adaptive_guidance_weight
request_body.shape_slat_rescale_tnumberNoControls noise schedule sharpness for shape refinement.3
request_body.ss_guidance_strengthnumberNoHow closely the initial 3D structure follows the input. Higher values produce more faithful but potentially noisier results.7.5
request_body.slat_guidance_rescalenumberNoGuidance rescale for SLat stage (only used when ss_source='mesh').0.5
request_body.slat_guidance_strengthnumberNoGuidance strength for SLat stage (only used when ss_source='mesh').7.5
request_body.tex_slat_sampling_stepsintegerNoNumber of denoising steps for texture generation.12
request_body.shape_slat_sampling_stepsintegerNoNumber of denoising steps for shape refinement.12
request_body.tex_slat_guidance_rescalenumberNoDampens artifacts from high guidance in the texture stage.0
request_body.tex_slat_guidance_strengthnumberNoHow closely the texture follows the input colors.1
request_body.shape_slat_guidance_rescalenumberNoDampens artifacts from high guidance in the shape stage.0.5
request_body.shape_slat_guidance_strengthnumberNoHow closely the detailed geometry follows the input.7.5

Invocation example

Copy the request and explore its response example.

POST/agent-api/v1/tool/executeX-Api-Key

Submit first, then query with the returned task_id until the task completes.

Request coderequest.sh
curl --request POST \
  --url 'https://agentearth.ai/agent-api/v1/tool/execute?tool_name=ae_reconviagen_0_5' \
  --header "X-Api-Key: $AGENTEARTH_API_KEY" \
  --header 'Content-Type: application/json' \
  --data-raw '{
  "params": {
    "request_body": {
      "decimation_target": 200000,
      "image_urls": [
        "https://v3b.fal.media/files/b/0ab1c142/oC7XXlvi-6-iXPKY95c8A.png",
        "https://v3b.fal.media/files/b/0ab1c140/v8o3dtgTR0drprkDfFhOY.png",
        "https://v3b.fal.media/files/b/0ab1c142/JthYtHW3WVMAfuVZNxehE.png",
        "https://v3b.fal.media/files/b/0ab1c142/XqJXdq6Dq6xAjYkWdFqLG.png"
      ],
      "multi_image_strategy": "adaptive_guidance_weight",
      "resolution": 1024,
      "shape_slat_sampling_steps": 12,
      "ss_sampling_steps": 12,
      "ss_source": "mvtrellis2",
      "tex_slat_sampling_steps": 12,
      "texture_size": 2048
    }
  }
}'
Response exampleresponse.json
JSON
{
  "description": "task accepted; poll the result via query_tool with this task_id",
  "query_tool": "ae_get_result",
  "status": "created",
  "task_id": "416fde4d-527a-428d-bbd7-63b0a4d05492"
}