# ReconViaGen 0.5 > Generate 3D models from one or more images using ReconViaGen 0.5 ## Overview - **Endpoint**: `https://fal.run/fal-ai/reconviagen-0.5` - **Model ID**: `fal-ai/reconviagen-0.5` - **Category**: image-to-3d - **Kind**: inference **Tags**: multi-view, 3d-reconstruction ## Pricing Your request will cost **$0.25** for 512, **$0.30** for 1024 or **$0.35** for 1536. For more details, see [fal.ai pricing](https://fal.ai/pricing). ## API Information This model can be used via our HTTP API or more conveniently via our client libraries. See the input and output schema below, as well as the usage examples. ### Input Schema The API accepts the following input parameters: - **`seed`** (`integer`, _optional_): Random seed for reproducibility - **`resolution`** (`ResolutionEnum`, _optional_): Output resolution; higher is slower but more detailed Default value: `"1024"` - Default: `1024` - Options: `512`, `1024`, `1536` - **`ss_source`** (`SparseStructureSourceEnum`, _optional_): Sparse structure source. 'mesh' gives best quality, 'direct' is fastest, 'mvtrellis2' uses multi-view TRELLIS.2. Default value: `"mesh"` - Default: `"mesh"` - Options: `"direct"`, `"mesh"`, `"mvtrellis2"` - **`ss_guidance_strength`** (`float`, _optional_): How closely the initial 3D structure follows the input. Higher values produce more faithful but potentially noisier results. Default value: `7.5` - Default: `7.5` - Range: `0` to `10` - **`ss_guidance_rescale`** (`float`, _optional_): Dampens artifacts from high guidance in stage 1. Default value: `0.7` - Default: `0.7` - Range: `0` to `1` - **`ss_sampling_steps`** (`integer`, _optional_): Number of denoising steps for the initial structure. Default value: `12` - Default: `12` - Range: `1` to `50` - **`ss_rescale_t`** (`float`, _optional_): Controls noise schedule sharpness for structure generation. Default value: `5` - Default: `5` - Range: `1` to `6` - **`slat_guidance_strength`** (`float`, _optional_): Guidance strength for SLat stage (only used when ss_source='mesh'). Default value: `7.5` - Default: `7.5` - Range: `0` to `10` - **`slat_guidance_rescale`** (`float`, _optional_): Guidance rescale for SLat stage (only used when ss_source='mesh'). Default value: `0.5` - Default: `0.5` - Range: `0` to `1` - **`slat_sampling_steps`** (`integer`, _optional_): Sampling steps for SLat stage (only used when ss_source='mesh'). Default value: `12` - Default: `12` - Range: `1` to `50` - **`slat_rescale_t`** (`float`, _optional_): Rescale T for SLat stage (only used when ss_source='mesh'). Default value: `3` - Default: `3` - Range: `1` to `6` - **`shape_slat_guidance_strength`** (`float`, _optional_): How closely the detailed geometry follows the input. Default value: `7.5` - Default: `7.5` - Range: `0` to `10` - **`shape_slat_guidance_rescale`** (`float`, _optional_): Dampens artifacts from high guidance in the shape stage. Default value: `0.5` - Default: `0.5` - Range: `0` to `1` - **`shape_slat_sampling_steps`** (`integer`, _optional_): Number of denoising steps for shape refinement. Default value: `12` - Default: `12` - Range: `1` to `50` - **`shape_slat_rescale_t`** (`float`, _optional_): Controls noise schedule sharpness for shape refinement. Default value: `3` - Default: `3` - Range: `1` to `6` - **`tex_slat_guidance_strength`** (`float`, _optional_): How closely the texture follows the input colors. Default value: `1` - Default: `1` - Range: `0` to `10` - **`tex_slat_guidance_rescale`** (`float`, _optional_): Dampens artifacts from high guidance in the texture stage. - Default: `0` - Range: `0` to `1` - **`tex_slat_sampling_steps`** (`integer`, _optional_): Number of denoising steps for texture generation. Default value: `12` - Default: `12` - Range: `1` to `50` - **`tex_slat_rescale_t`** (`float`, _optional_): Controls noise schedule sharpness for texture generation. Default value: `3` - Default: `3` - Range: `1` to `6` - **`decimation_target`** (`integer`, _optional_): Target number of vertices in the final mesh. Default value: `500000` - Default: `500000` - Range: `5000` to `2000000` - **`texture_size`** (`TextureSizeEnum`, _optional_): Resolution of the texture image baked onto the mesh. Default value: `"2048"` - Default: `2048` - Options: `1024`, `2048`, `4096` - **`image_urls`** (`list`, _required_): One or more views of the same object. Multiple views yield higher-quality 3D reconstruction. - Array of string - Examples: ["https://storage.googleapis.com/falserverless/model_tests/video_models/front.png","https://storage.googleapis.com/falserverless/model_tests/video_models/back.png","https://storage.googleapis.com/falserverless/model_tests/video_models/left.png"] - **`multi_image_strategy`** (`MultiImageStrategyEnum`, _optional_): Strategy for combining multi-view conditioning. 'adaptive_guidance_weight' works best in most cases. Only used when more than one image is provided. Default value: `"adaptive_guidance_weight"` - Default: `"adaptive_guidance_weight"` - Options: `"average_right"`, `"weighted_average"`, `"sequential"`, `"average"`, `"adaptive_guidance_weight"`, `"fixed_guidance_rescale"` **Required Parameters Example**: ```json { "image_urls": [ "https://storage.googleapis.com/falserverless/model_tests/video_models/front.png", "https://storage.googleapis.com/falserverless/model_tests/video_models/back.png", "https://storage.googleapis.com/falserverless/model_tests/video_models/left.png" ] } ``` **Full Example**: ```json { "resolution": 1024, "ss_source": "mesh", "ss_guidance_strength": 7.5, "ss_guidance_rescale": 0.7, "ss_sampling_steps": 12, "ss_rescale_t": 5, "slat_guidance_strength": 7.5, "slat_guidance_rescale": 0.5, "slat_sampling_steps": 12, "slat_rescale_t": 3, "shape_slat_guidance_strength": 7.5, "shape_slat_guidance_rescale": 0.5, "shape_slat_sampling_steps": 12, "shape_slat_rescale_t": 3, "tex_slat_guidance_strength": 1, "tex_slat_sampling_steps": 12, "tex_slat_rescale_t": 3, "decimation_target": 500000, "texture_size": 2048, "image_urls": [ "https://storage.googleapis.com/falserverless/model_tests/video_models/front.png", "https://storage.googleapis.com/falserverless/model_tests/video_models/back.png", "https://storage.googleapis.com/falserverless/model_tests/video_models/left.png" ], "multi_image_strategy": "adaptive_guidance_weight" } ``` ### Output Schema The API returns the following output format: - **`model_glb`** (`File`, _required_): Generated 3D GLB file with PBR materials - Examples: {"url":"https://v3b.fal.media/files/b/0a951b66/qp0eJhESNtvkFHVd8q9M2_reconviagen_6a9848519c2d43a69dcce8c00a8803b2.glb"} - **`seed`** (`integer`, _required_): Seed used for generation. **Example Response**: ```json { "model_glb": { "url": "https://v3b.fal.media/files/b/0a951b66/qp0eJhESNtvkFHVd8q9M2_reconviagen_6a9848519c2d43a69dcce8c00a8803b2.glb" } } ``` ## Usage Examples ### cURL ```bash curl --request POST \ --url https://fal.run/fal-ai/reconviagen-0.5 \ --header "Authorization: Key $FAL_KEY" \ --header "Content-Type: application/json" \ --data '{ "image_urls": [ "https://storage.googleapis.com/falserverless/model_tests/video_models/front.png", "https://storage.googleapis.com/falserverless/model_tests/video_models/back.png", "https://storage.googleapis.com/falserverless/model_tests/video_models/left.png" ] }' ``` ### Python Ensure you have the Python client installed: ```bash pip install fal-client ``` Then use the API client to make requests: ```python import fal_client def on_queue_update(update): if isinstance(update, fal_client.InProgress): for log in update.logs: print(log["message"]) result = fal_client.subscribe( "fal-ai/reconviagen-0.5", arguments={ "image_urls": ["https://storage.googleapis.com/falserverless/model_tests/video_models/front.png", "https://storage.googleapis.com/falserverless/model_tests/video_models/back.png", "https://storage.googleapis.com/falserverless/model_tests/video_models/left.png"] }, with_logs=True, on_queue_update=on_queue_update, ) print(result) ``` ### JavaScript Ensure you have the JavaScript client installed: ```bash npm install --save @fal-ai/client ``` Then use the API client to make requests: ```javascript import { fal } from "@fal-ai/client"; const result = await fal.subscribe("fal-ai/reconviagen-0.5", { input: { image_urls: ["https://storage.googleapis.com/falserverless/model_tests/video_models/front.png", "https://storage.googleapis.com/falserverless/model_tests/video_models/back.png", "https://storage.googleapis.com/falserverless/model_tests/video_models/left.png"] }, logs: true, onQueueUpdate: (update) => { if (update.status === "IN_PROGRESS") { update.logs.map((log) => log.message).forEach(console.log); } }, }); console.log(result.data); console.log(result.requestId); ``` ## Additional Resources ### Documentation - [Model Playground](https://fal.ai/models/fal-ai/reconviagen-0.5) - [API Documentation](https://fal.ai/models/fal-ai/reconviagen-0.5/api) - [OpenAPI Schema](https://fal.ai/api/openapi/queue/openapi.json?endpoint_id=fal-ai/reconviagen-0.5) ### fal.ai Platform - [Platform Documentation](https://docs.fal.ai) - [Python Client](https://docs.fal.ai/clients/python) - [JavaScript Client](https://docs.fal.ai/clients/javascript)