pixal3d/pixal3d
Pixal3d is pixal3d's image-to-3D AI model. Transform photographs into production-ready 3D meshes with accurate geometry and texture mapping.
Input
PNG, JPEG, WebP, or GIF · 20 MiB maximum
URL of the input image to convert to 3D
This field is required.
Output resolution; higher is slower but more detailed Allowed values: 1024, 1536.
0.14
Scale factor applied to the inferred mesh. Affects the camera distance estimation used by the model. Range: 0.1 to 4.
010
How closely the detailed geometry follows the input image. Higher values add more detail but may introduce noise. Range: 0 to 10.
Rebuild the mesh topology for cleaner triangles. Slower but usually produces better results for downstream use.
Resolution of the texture image baked onto the mesh. Higher values capture finer surface details but produce larger files. Allowed values: 1024, 2048, 4096.
150
Number of denoising steps for the initial structure. More steps = slower but potentially higher quality. Range: 1 to 50.
16
Controls noise schedule sharpness for shape refinement. Higher values produce sharper geometric details. Range: 1 to 6.
150
Number of denoising steps for texture generation. More steps = slower but potentially cleaner textures. Range: 1 to 50.
010
How closely the initial 3D structure follows the input image. Higher values produce more faithful but potentially noisier results. Range: 0 to 10.
01
Dampens artifacts from high guidance in stage 1. Lower values allow stronger guidance effects, higher values stabilize the output. Range: 0 to 1.
4096131072
Maximum number of HR tokens used by the cascaded shape sampler. Higher values allow finer geometry; lower values reduce memory and time. Range: 4096 to 131072.
16
Controls noise schedule sharpness for structure generation. Higher values produce sharper transitions. Range: 1 to 6.
01
Dampens artifacts from high guidance in the shape stage. Increase if you see noisy geometry. Range: 0 to 1.
16
Controls noise schedule sharpness for texture generation. Higher values produce sharper texture details. Range: 1 to 6.
01
Dampens artifacts from high guidance in the texture stage. Increase if textures look noisy or have color banding. Range: 0 to 1.
150
Number of denoising steps for shape refinement. More steps = slower but potentially smoother geometry. Range: 1 to 50.
50002000000
Target number of vertices in the final mesh. Lower values produce smaller files but less detail. Range: 5000 to 2000000.
010
How closely the texture follows the input image colors. Higher values produce more vivid but potentially oversaturated textures. Range: 0 to 10.
Random seed for reproducibility
Idle
Example output — click Run to generate your own
Production endpoint
Send your first request
OpenAI-compatible endpoint with unified authentication and usage tracking.
POST
https://api.sandbase.ai/v1/runModel ID
pixal3d/pixal3d01
Input Schema
20 parameters · 1 required · 19 optional
| Parameter | Type | Required | Description |
|---|---|---|---|
image | string | Required | URL of the input image to convert to 3D |
seed | integer | Optional | Random seed for reproducibility |
remesh | boolean | Optional | Rebuild the mesh topology for cleaner triangles. Slower but usually produces better results for downstream use. · Default: true |
mesh_scale | number | Optional | Scale factor applied to the inferred mesh. Affects the camera distance estimation used by the model. · Min: 0.1 · Max: 4 · Default: 1 |
resolution | integer | Optional | Output resolution; higher is slower but more detailed · Options: 1024, 1536 · Default: 1024 10241536 |
ss_rescale_t | number | Optional | Controls noise schedule sharpness for structure generation. Higher values produce sharper transitions. · Min: 1 · Max: 6 · Default: 5 |
texture_size | integer | Optional | Resolution of the texture image baked onto the mesh. Higher values capture finer surface details but produce larger files. · Options: 1024, 2048, 4096 · Default: 2048 102420484096 |
max_num_tokens | integer | Optional | Maximum number of HR tokens used by the cascaded shape sampler. Higher values allow finer geometry; lower values reduce memory and time. · Min: 4096 · Max: 131072 · Default: 49152 |
decimation_target | integer | Optional | Target number of vertices in the final mesh. Lower values produce smaller files but less detail. · Min: 5000 · Max: 2000000 · Default: 200000 |
ss_sampling_steps | integer | Optional | Number of denoising steps for the initial structure. More steps = slower but potentially higher quality. · Min: 1 · Max: 50 · Default: 12 |
tex_slat_rescale_t | number | Optional | Controls noise schedule sharpness for texture generation. Higher values produce sharper texture details. · Min: 1 · Max: 6 · Default: 3 |
ss_guidance_rescale | number | Optional | Dampens artifacts from high guidance in stage 1. Lower values allow stronger guidance effects, higher values stabilize the output. · Min: 0 · Max: 1 · Default: 0.7 |
shape_slat_rescale_t | number | Optional | Controls noise schedule sharpness for shape refinement. Higher values produce sharper geometric details. · Min: 1 · Max: 6 · Default: 3 |
ss_guidance_strength | number | Optional | How closely the initial 3D structure follows the input image. Higher values produce more faithful but potentially noisier results. · Min: 0 · Max: 10 · Default: 7.5 |
tex_slat_sampling_steps | integer | Optional | Number of denoising steps for texture generation. More steps = slower but potentially cleaner textures. · Min: 1 · Max: 50 · Default: 12 |
shape_slat_sampling_steps | integer | Optional | Number of denoising steps for shape refinement. More steps = slower but potentially smoother geometry. · Min: 1 · Max: 50 · Default: 12 |
tex_slat_guidance_rescale | number | Optional | Dampens artifacts from high guidance in the texture stage. Increase if textures look noisy or have color banding. · Min: 0 · Max: 1 · Default: 0 |
tex_slat_guidance_strength | number | Optional | How closely the texture follows the input image colors. Higher values produce more vivid but potentially oversaturated textures. · Min: 0 · Max: 10 · Default: 1 |
shape_slat_guidance_rescale | number | Optional | Dampens artifacts from high guidance in the shape stage. Increase if you see noisy geometry. · Min: 0 · Max: 1 · Default: 0.5 |
shape_slat_guidance_strength | number | Optional | How closely the detailed geometry follows the input image. Higher values add more detail but may introduce noise. · Min: 0 · Max: 10 · Default: 7.5 |
02
Output Schema
| Field | Type | Description |
|---|---|---|
id | string | Unique identifier for the generation task |
status | string | Task status: pending, running, completed, failed, timeout |
model | string | Model used for the generation |
outputs | array | Array of output items |
outputs[].url | string | URL of the generated artifact |
outputs[].content_type | string | MIME type (e.g. image/png, video/mp4) |
error | object | null | Error details if failed, null on success |
error.type | string | Machine-readable error type code |
error.message | string | Human-readable error description |
Async Workflow
This model uses asynchronous execution. Submit a request and poll for the result.
- Submit — POST to /v1/run, receive an
id - Poll — GET /v1/run/{id} until status is
completed,failed, ortimeout - Retrieve — Read
outputsfrom the completed response
03
Code Examples
Ready-to-run snippets
# Step 1: Submit
curl -X POST https://api.sandbase.ai/v1/run \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_API_KEY" \
-d '{
"model": "pixal3d/pixal3d",
"image": "https://static.sandbase.ai/examples/pixal3d/pixal3d/input_image_0.png",
"remesh": true,
"mesh_scale": 1,
"resolution": 1024,
"ss_rescale_t": 5,
"texture_size": 2048,
"max_num_tokens": 49152,
"decimation_target": 200000,
"ss_sampling_steps": 12,
"tex_slat_rescale_t": 3,
"ss_guidance_rescale": 0.7,
"shape_slat_rescale_t": 3,
"ss_guidance_strength": 7.5,
"tex_slat_sampling_steps": 12,
"shape_slat_sampling_steps": 12,
"tex_slat_guidance_rescale": 0,
"tex_slat_guidance_strength": 1,
"shape_slat_guidance_rescale": 0.5,
"shape_slat_guidance_strength": 7.5,
"prompt": "a beautiful sunset over mountains"
}'
# Step 2: Poll result (replace <id>)
curl https://api.sandbase.ai/v1/run/<id> \
-H "Authorization: Bearer YOUR_API_KEY"API README
Pixal3D
Pixal3D is the Pixal3D route for image-to-3D reconstruction, turning a reference image into a production-ready result while keeping the operation distinct from neighboring endpoints. Pixal3d is pixal3d's image-to-3D AI model. Transform photographs into production-ready 3D meshes with accurate geometry and texture mapping. The workflow is designed for creators who need the model’s specific transformation to remain visible in the request, so the source, intended change, and finished artifact can be reviewed as one coherent creative decision.
In practical use, this route exposes seed, image, remesh, mesh_scale, resolution, ss_rescale_t, texture_size, max_num_tokens to shape the exact deliverable. Those controls let a team preserve the important source constraints, state subject behavior or material treatment precisely, choose supported timing or output characteristics, and reproduce successful settings across alternate takes. The result fits an iterative pipeline: establish the core brief, compare controlled variations, then pass the selected asset into editorial, design, localization, visualization, or publishing work.
Highlights
- Single-image reconstruction. Convert a reference image into a textured 3D asset with geometry inferred from the visible subject.
- Resolution tiers. Choose the documented output resolution tier to balance turnaround and surface detail.
- Background handling. Use the documented preprocessing controls to isolate the subject before reconstruction.
- Pipeline-ready asset. Receive a downloadable 3D result suitable for inspection, prototyping, and downstream scene work.
Pricing
| Configuration | Price |
|---|---|
| 1024 | $0.300000 |
| 1536 | $0.300000 |
| 2048p | $0.420000 |
| 4096p | $0.420000 |
When to Use
| Scenario | Why it fits |
|---|---|
| Exact workflow fit | Choose this route when the required deliverable is image-to-3D reconstruction, rather than a related route with different source media. |
| Directed creative iteration | Use it when subject, motion, material, speech, framing, or finish should be expressed explicitly and compared across controlled variants. |
| Existing-asset continuity | Use it when supplied images, video, audio, references, or styles must remain the anchor for the generated result. |
| Repeatable production | Use it when successful inputs need to be saved and rerun across a campaign, asset set, localization pass, or batch. |
| Pipeline handoff | Use it when the returned artifact will move into editorial, compositing, visualization, review, storage, or publishing. |
Prompt Guide
Start with the source or subject, then describe the intended transformation, movement or behavior, camera and composition, and the desired finish. Keep media URLs reachable, use only fields documented for this exact route, and change one major control at a time when comparing results. For source-led tasks, describe what should change as well as what must remain recognizable.
{
"image": "https://static.sandbase.ai/examples/pixal3d/pixal3d/input_image_0.png",
"resolution": 1024
}
Technical Specs
| Property | Value |
|---|---|
| Model ID | pixal3d/pixal3d |
| Execution mode | async |
| Required inputs | image |
seed | integer |
image | string |
remesh | boolean; default: true |
mesh_scale | number; minimum: 0.1; maximum: 4; default: 1 |
resolution | integer; options: 1024, 1536; default: 1024 |
ss_rescale_t | number; minimum: 1; maximum: 6; default: 5 |
texture_size | integer; options: 1024, 2048, 4096; default: 2048 |
max_num_tokens | integer; minimum: 4096; maximum: 131072; default: 49152 |
decimation_target | integer; minimum: 5000; maximum: 2000000; default: 200000 |
ss_sampling_steps | integer; minimum: 1; maximum: 50; default: 12 |
tex_slat_rescale_t | number; minimum: 1; maximum: 6; default: 3 |
ss_guidance_rescale | number; minimum: 0; maximum: 1; default: 0.7 |
shape_slat_rescale_t | number; minimum: 1; maximum: 6; default: 3 |
ss_guidance_strength | number; minimum: 0; maximum: 10; default: 7.5 |
tex_slat_sampling_steps | integer; minimum: 1; maximum: 50; default: 12 |
shape_slat_sampling_steps | integer; minimum: 1; maximum: 50; default: 12 |
tex_slat_guidance_rescale | number; minimum: 0; maximum: 1; default: 0 |
tex_slat_guidance_strength | number; minimum: 0; maximum: 10; default: 1 |
shape_slat_guidance_rescale | number; minimum: 0; maximum: 1; default: 0.5 |
shape_slat_guidance_strength | number; minimum: 0; maximum: 10; default: 7.5 |
Related Models
meshy/7.0/image-to-3dmeshy/7.0/multi-image-to-3dtripo3d/tripo-h3.1/text-to-3d