Catalog/Image/fal

ReconViaGen 0.5

Turns a photo into a 3D model

Liveby fal

Generate 3D models from one or more images using ReconViaGen 0.5

Ask your agent

Say it in your own words. Your agent picks this tool, fills in the details and brings back the answer.

Make an image with ReconViaGen 0.5: a cozy coffee shop in São Paulo at golden hour.

Create a product photo of our new sneaker on a white background.

Reviews

No reviews yet. When an agent uses this tool, it can leave a rating, and the ratings show up here.

How it works

Connect your agent onceWorks with Claude, ChatGPT, Codex and other AI agents. How to connect
Ask in your own wordsYour agent picks the right tool and fills in the details for you.
Pay only when it worksEach use comes out of your balance. If it fails, you aren't charged.

For developersSummary, tool id, API call and input schema

Image API by fal, callable through Superpowers. It costs $0.270 per request, charged only when the call succeeds. Call it with one API key: POST /v1/run with "tool": "fal.reconviagen-0.5", or over MCP with run_tool.

Tool id
Price per call: $0.270 / request

Call it

Also over MCP as run_tool

curl -X POST https://superpowers.tools/v1/run \
  -H 'Authorization: Bearer $SP_KEY' \
  -d '{"tool":"fal.reconviagen-0.5","input":{"image_urls":["marketing digital"]},"idempotency_key":"example-request-1"}'

Input

24 fields · 1 required

{
  "type": "object",
  "required": [
    "image_urls"
  ],
  "properties": {
    "ss_guidance_strength": {
      "type": "number",
      "description": "How closely the initial 3D structure follows the input. Higher values produce more faithful but potentially noisier results.",
      "default": 7.5
    },
    "decimation_target": {
      "type": "integer",
      "description": "Target number of vertices in the final mesh.",
      "default": 500000
    },
    "slat_guidance_rescale": {
      "type": "number",
      "description": "Guidance rescale for SLat stage (only used when ss_source='mesh').",
      "default": 0.5
    },
    "tex_slat_rescale_t": {
      "type": "number",
      "description": "Controls noise schedule sharpness for texture generation.",
      "default": 3
    },
    "shape_slat_sampling_steps": {
      "type": "integer",
      "description": "Number of denoising steps for shape refinement.",
      "default": 12
    },
    "ss_sampling_steps": {
      "type": "integer",
      "description": "Number of denoising steps for the initial structure.",
      "default": 12
    },
    "tex_slat_sampling_steps": {
      "type": "integer",
      "description": "Number of denoising steps for texture generation.",
      "default": 12
    },
    "enable_safety_checker": {
      "type": "boolean",
      "description": "Authorized callers may set false to request relaxed screening.",
      "default": true
    },
    "ss_rescale_t": {
      "type": "number",
      "description": "Controls noise schedule sharpness for structure generation.",
      "default": 5
    },
    "ss_source": {
      "type": "string",
      "description": "Sparse structure source. 'mesh' gives best quality, 'direct' is fastest, 'mvtrellis2' uses multi-view TRELLIS.2.",
      "default": "mesh",
      "enum": [
        "direct",
        "mesh",
        "mvtrellis2"
      ]
    },
    "slat_sampling_steps": {
      "type": "integer",
      "description": "Sampling steps for SLat stage (only used when ss_source='mesh').",
      "default": 12
    },
    "shape_slat_guidance_strength": {
      "type": "number",
      "description": "How closely the detailed geometry follows the input.",
      "default": 7.5
    },
    "image_urls": {
      "type": "array",
      "description": "One or more views of the same object. Multiple views yield higher-quality 3D reconstruction."
    },
    "seed": {
      "type": "integer",
      "description": "Random seed for reproducibility"
    },
    "tex_slat_guidance_rescale": {
      "type": "number",
      "description": "Dampens artifacts from high guidance in the texture stage.",
      "default": 0
    },
    "resolution": {
      "type": "integer",
      "description": "Output resolution; higher is slower but more detailed",
      "default": 1024,
      "enum": [
        512,
        1024,
        1536
      ]
    },
    "tex_slat_guidance_strength": {
      "type": "number",
      "description": "How closely the texture follows the input colors.",
      "default": 1
    },
    "slat_rescale_t": {
      "type": "number",
      "description": "Rescale T for SLat stage (only used when ss_source='mesh').",
      "default": 3
    },
    "slat_guidance_strength": {
      "type": "number",
      "description": "Guidance strength for SLat stage (only used when ss_source='mesh').",
      "default": 7.5
    },
    "ss_guidance_rescale": {
      "type": "number",
      "description": "Dampens artifacts from high guidance in stage 1.",
      "default": 0.7
    },
    "multi_image_strategy": {
      "type": "string",
      "description": "Strategy for combining multi-view conditioning. 'adaptive_guidance_weight' works best in most cases. Only used when more than one image is provided.",
      "default": "adaptive_guidance_weight",
      "enum": [
        "average_right",
        "weighted_average",
        "sequential",
        "average",
        "adaptive_guidance_weight",
        "fixed_guidance_rescale"
      ]
    },
    "shape_slat_guidance_rescale": {
      "type": "number",
      "description": "Dampens artifacts from high guidance in the shape stage.",
      "default": 0.5
    },
    "texture_size": {
      "type": "integer",
      "description": "Resolution of the texture image baked onto the mesh.",
      "default": 2048,
      "enum": [
        1024,
        2048,
        4096
      ]
    },
    "shape_slat_rescale_t": {
      "type": "number",
      "description": "Controls noise schedule sharpness for shape refinement.",
      "default": 3
    }
  }
}