falImage to 3DAvailable now
fal-ai/meshy/v6-preview/image-to-3d
fal-ai/meshy/v6-preview/image-to-3d is an image to 3D tool from fal that runs in the background and returns 3D models and images. Pay as you go from $1.04 per generation, with one API key.
Try itfrom $1.04 / generation
Pricing
should_texture: false $1.04, true $1.56 per generation. enable_rigging adds $0.26 per generation. enable_rigging and enable_animation add $0.156 per generation. The final charge comes from usage.
Limits
- Runs
- In the background
- Returns
- 3d, image
- Longest queue wait
- 3600s
- Run deadline
- 1800s
- Largest inline input
- 1024 KB
- Largest input file
- 500 MB
- Largest output
- 4768 MB
- Outputs per run
- 24
Input
| Field | Kind | Default | Description |
|---|---|---|---|
image_url required | URL or file | — | Image URL or base64 data URI for 3D model creation. Supports .jpg, .jpeg, and .png formats. Also supports AVIF and HEIF formats which will be automatically converted. |
model_type | one of standard, lowpoly, smart-topology, smart-topology-t2 | standard | Type of 3D mesh generation. 'standard' produces a regular high-detail mesh; 'lowpoly' produces a low-poly mesh optimized for cleaner polygons; 'smart-topology' (Smart Topology T2.5) and 'smart-topology-t2' (Smart Topology T2) produce clean, triangle-only meshes with natively separated parts — T2.5 has sharper detail, T2 is faster. When set to 'lowpoly', the remesh controls (topology, target_polycount, should_remesh) are ignored by Meshy. |
topology | one of quad, triangle | triangle | Specify the topology of the generated model. Quad for smooth surfaces, Triangle for detailed geometry. |
target_polycount | number (whole) 100 to 300000 | 30000 | Target number of polygons in the generated model. When model_type is a smart topology option and this is left unset, that model's default is used instead (15,000 for T2.5, 4,000 for T2); the maximum is 30,000 for T2.5 and 15,000 for T2. |
symmetry_mode | one of off, auto, on | auto | Controls symmetry behavior during model generation. Off disables symmetry, Auto determines it automatically, On enforces symmetry. |
should_remesh | true or false | true | Whether to enable the remesh phase |
should_texture | true or false | true | Whether to generate textures |
enable_pbr | true or false | false | Generate PBR Maps (metallic, roughness, normal) in addition to base color |
is_a_t_pose | true or false | false | Deprecated: use pose_mode instead. When true, generates a T-pose model. |
pose_mode | one of a-pose, t-pose, | Pose mode for the generated model. 'a-pose' generates an A-pose, 't-pose' generates a T-pose, empty string for no specific pose. | |
texture_prompt | text | — | Text prompt to guide the texturing process |
texture_image_url | URL or file | — | 2D image to guide the texturing process |
enable_rigging | true or false | false | Automatically rig the generated model as a humanoid character. Includes basic walking and running animations. Best results with humanoid characters that have clearly defined limbs. |
rigging_height_meters | number | 1.7 | Approximate height of the character in meters. Only used when enable_rigging is true. |
enable_animation | true or false | false | Apply an animation preset to the rigged model. Requires enable_rigging to be true. |
animation_action_id | number (whole) | 92 | Animation preset ID from Meshy's library. Only used when enable_animation is true; in that case it must be in [0, 696] (``0`` is the "Idle" preset) and is otherwise rejected with a 422. See https://docs.meshy.ai/en/api/animation-library for available action IDs. |
Same request in code
curl https://api.spiral.ai/v1/runs \
-H "Authorization: Bearer $SPIRAL_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: $(uuidgen)" \
-d '{
"provider": "fal",
"model": "fal-ai/meshy/v6-preview/image-to-3d",
"input": {
"image_url": "https://v3b.fal.media/files/b/zebra/3osHJDI8IZ2wl6sGtEUeB_image.png"
}
}'