Prediction

Model

fishwowater/trellis-image:8fcea9ca

qbx85b9yg9rmc0cpcsvamxfrcw

Status

Succeeded

Source

Web

Hardware

L40S

Total duration

4m 51s

Created

8 months ago

Webhook

–

Input

images: https://replicate.delivery/pbxt/MtJOwdC4hShWyq0IVWZLiKGbtmprk9eVNi70kql6QNQDvElA/T.png
seed: 0
randomize_seed: true
generate_color: true
generate_normal: false
generate_model: true
save_gaussian_ply: false
return_no_background: false
ss_guidance_strength: 7.5
ss_sampling_steps: 12
slat_guidance_strength: 3
slat_sampling_steps: 12
mesh_simplify: 0.95
texture_size: 1024
tex_bake_mode: rgb

{
  "generate_color": true,
  "generate_model": true,
  "generate_normal": false,
  "images": [
    "https://replicate.delivery/pbxt/MtJOwdC4hShWyq0IVWZLiKGbtmprk9eVNi70kql6QNQDvElA/T.png"
  ],
  "mesh_simplify": 0.95,
  "randomize_seed": true,
  "return_no_background": false,
  "save_gaussian_ply": false,
  "seed": 0,
  "slat_guidance_strength": 3,
  "slat_sampling_steps": 12,
  "ss_guidance_strength": 7.5,
  "ss_sampling_steps": 12,
  "tex_bake_mode": "rgb",
  "texture_size": 1024
}

Install Replicate’s Node.js client library:

npm install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=r8_GIv**********************************

This is your API token. Keep it to yourself.

Import and set up the client:

import Replicate from "replicate";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run fishwowater/trellis-image using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "fishwowater/trellis-image:8fcea9cab82961f9fe5b6250c800ef0d652c15c4c280a069562d8d907d77f778",
  {
    input: {
      generate_color: true,
      generate_model: true,
      generate_normal: false,
      images: ["https://replicate.delivery/pbxt/MtJOwdC4hShWyq0IVWZLiKGbtmprk9eVNi70kql6QNQDvElA/T.png"],
      mesh_simplify: 0.95,
      randomize_seed: true,
      return_no_background: false,
      save_gaussian_ply: false,
      seed: 0,
      slat_guidance_strength: 3,
      slat_sampling_steps: 12,
      ss_guidance_strength: 7.5,
      ss_sampling_steps: 12,
      tex_bake_mode: "rgb",
      texture_size: 1024
    }
  }
);

console.log(output);

To learn more, take a look at the guide on getting started with Node.js.

Install Replicate’s Python client library:

pip install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=r8_GIv**********************************

This is your API token. Keep it to yourself.

Import the client:

import replicate

Run fishwowater/trellis-image using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "fishwowater/trellis-image:8fcea9cab82961f9fe5b6250c800ef0d652c15c4c280a069562d8d907d77f778",
    input={
        "generate_color": True,
        "generate_model": True,
        "generate_normal": False,
        "images": ["https://replicate.delivery/pbxt/MtJOwdC4hShWyq0IVWZLiKGbtmprk9eVNi70kql6QNQDvElA/T.png"],
        "mesh_simplify": 0.95,
        "randomize_seed": True,
        "return_no_background": False,
        "save_gaussian_ply": False,
        "seed": 0,
        "slat_guidance_strength": 3,
        "slat_sampling_steps": 12,
        "ss_guidance_strength": 7.5,
        "ss_sampling_steps": 12,
        "tex_bake_mode": "rgb",
        "texture_size": 1024
    }
)

print(output)

To learn more, take a look at the guide on getting started with Python.

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=r8_GIv**********************************

This is your API token. Keep it to yourself.

Run fishwowater/trellis-image using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "version": "fishwowater/trellis-image:8fcea9cab82961f9fe5b6250c800ef0d652c15c4c280a069562d8d907d77f778",
    "input": {
      "generate_color": true,
      "generate_model": true,
      "generate_normal": false,
      "images": ["https://replicate.delivery/pbxt/MtJOwdC4hShWyq0IVWZLiKGbtmprk9eVNi70kql6QNQDvElA/T.png"],
      "mesh_simplify": 0.95,
      "randomize_seed": true,
      "return_no_background": false,
      "save_gaussian_ply": false,
      "seed": 0,
      "slat_guidance_strength": 3,
      "slat_sampling_steps": 12,
      "ss_guidance_strength": 7.5,
      "ss_sampling_steps": 12,
      "tex_bake_mode": "rgb",
      "texture_size": 1024
    }
  }' \
  https://api.replicate.com/v1/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.

Output

Object output with 2 properties

model_file(output.glb)

Download output

Use your mouse to zoom and rotate the model

color_video(output_color.mp4)

Download output

{
  "id": "qbx85b9yg9rmc0cpcsvamxfrcw",
  "model": "fishwowater/trellis-image",
  "version": "8fcea9cab82961f9fe5b6250c800ef0d652c15c4c280a069562d8d907d77f778",
  "input": {
    "generate_color": true,
    "generate_model": true,
    "generate_normal": false,
    "images": [
      "https://replicate.delivery/pbxt/MtJOwdC4hShWyq0IVWZLiKGbtmprk9eVNi70kql6QNQDvElA/T.png"
    ],
    "mesh_simplify": 0.95,
    "randomize_seed": true,
    "return_no_background": false,
    "save_gaussian_ply": false,
    "seed": 0,
    "slat_guidance_strength": 3,
    "slat_sampling_steps": 12,
    "ss_guidance_strength": 7.5,
    "ss_sampling_steps": 12,
    "tex_bake_mode": "rgb",
    "texture_size": 1024
  },
  "logs": "INFO:predict:Loading and preprocessing input images...\nINFO:predict:Using randomized seed: 246380710\nINFO:predict:Running TRELLIS pipeline...\nSampling:   0%|          | 0/12 [00:00<?, ?it/s]\nSampling:  17%|█▋        | 2/12 [00:00<00:00, 12.70it/s]\nSampling:  33%|███▎      | 4/12 [00:00<00:00, 12.98it/s]\nSampling:  50%|█████     | 6/12 [00:00<00:00, 13.06it/s]\nSampling:  67%|██████▋   | 8/12 [00:00<00:00, 13.11it/s]\nSampling:  83%|████████▎ | 10/12 [00:00<00:00, 13.13it/s]\nSampling: 100%|██████████| 12/12 [00:00<00:00, 14.27it/s]\nSampling:   0%|          | 0/12 [00:00<?, ?it/s]\nSampling:   8%|▊         | 1/12 [00:00<00:01,  6.08it/s]\nSampling:  17%|█▋        | 2/12 [00:00<00:01,  7.69it/s]\nSampling:  25%|██▌       | 3/12 [00:00<00:01,  8.40it/s]\nSampling:  33%|███▎      | 4/12 [00:00<00:00,  8.76it/s]\nSampling:  42%|████▏     | 5/12 [00:00<00:00,  8.97it/s]\nSampling:  50%|█████     | 6/12 [00:00<00:00,  9.09it/s]\nSampling:  58%|█████▊    | 7/12 [00:00<00:00,  9.20it/s]\nSampling:  67%|██████▋   | 8/12 [00:00<00:00,  9.27it/s]\nSampling:  75%|███████▌  | 9/12 [00:01<00:00,  9.31it/s]\nSampling:  83%|████████▎ | 10/12 [00:01<00:00,  9.33it/s]\nSampling: 100%|██████████| 12/12 [00:01<00:00, 12.21it/s]\nSampling: 100%|██████████| 12/12 [00:01<00:00,  9.77it/s]\nINFO:predict:TRELLIS pipeline complete!\nINFO:predict:Available output formats: dict_keys(['mesh', 'gaussian'])\nINFO:predict:Starting video rendering...\nINFO:predict:Generating color video from gaussian output...\nRendering: 0it [00:00, ?it/s]\nRendering: 25it [00:00, 243.58it/s]\nRendering: 55it [00:00, 271.85it/s]\nRendering: 87it [00:00, 290.52it/s]\nRendering: 118it [00:00, 295.69it/s]\nRendering: 120it [00:00, 288.14it/s]\nINFO:predict:Available gaussian render types: ['color', 'depth']\nINFO:predict:Generated color video successfully\nINFO:predict:Video rendering complete!\nINFO:predict:Generating GLB model...\nINFO- Loaded 14867 vertices and 30203 faces.\n0% done\n2% done\n4% done\n7% done\n9% done\n11% done\n14% done\n16% done\n19% done\n21% done\n23% done\n26% done\n28% done\n30% done\n33% done\n35% done\n38% done\n40% done\n42% done\n45% done\n47% done\n50% done\n52% done\n54% done\n57% done\n59% done\n61% done\n64% done\n66% done\n69% done\n71% done\n73% done\n76% done\n78% done\n80% done\n83% done\n85% done\n88% done\n90% done\n92% done\n95% done\n97% done\n100% done\nWARNING- Some cuts were necessary to cope with non manifold configuration.\nRendering: 0it [00:00, ?it/s]\nRendering: 13it [00:00, 126.91it/s]\nRendering: 29it [00:00, 141.41it/s]\nRendering: 44it [00:00, 143.10it/s]\nRendering: 60it [00:00, 146.69it/s]\nRendering: 75it [00:00, 145.26it/s]\nRendering: 90it [00:00, 146.68it/s]\nRendering: 100it [00:00, 144.62it/s]\nINFO:predict:GLB model generation complete!\nINFO:predict:Prediction complete! Returning results...",
  "output": {
    "color_video": "https://replicate.delivery/xezq/L7JvBaiYrTLWOJpwzglwd6bkAFufHntiuDwVlYV2eqPGv4lUA/output_color.mp4",
    "combined_video": null,
    "gaussian_ply": null,
    "model_file": "https://replicate.delivery/xezq/y1jfEGovvSzeCEbKH13uUOT8bk3hRAedV8ef9iT3Lwkz4FvkC/output.glb",
    "no_background_images": null,
    "normal_video": null
  },
  "data_removed": false,
  "error": null,
  "source": "web",
  "status": "succeeded",
  "created_at": "2025-04-24T06:22:27.458Z",
  "started_at": "2025-04-24T06:26:43.260615Z",
  "completed_at": "2025-04-24T06:27:18.443946Z",
  "urls": {
    "cancel": "https://api.replicate.com/v1/predictions/qbx85b9yg9rmc0cpcsvamxfrcw/cancel",
    "get": "https://api.replicate.com/v1/predictions/qbx85b9yg9rmc0cpcsvamxfrcw",
    "web": "https://replicate.com/p/qbx85b9yg9rmc0cpcsvamxfrcw"
  },
  "metrics": {
    "predict_time": 35.183331079,
    "total_time": 290.985946
  }
}

Generated in

35.2 seconds

Tweak it Report

INFO:predict:Loading and preprocessing input images... INFO:predict:Using randomized seed: 246380710 INFO:predict:Running TRELLIS pipeline... Sampling: 0%| | 0/12 [00:00<?, ?it/s] Sampling: 17%|█▋ | 2/12 [00:00<00:00, 12.70it/s] Sampling: 33%|███▎ | 4/12 [00:00<00:00, 12.98it/s] Sampling: 50%|█████ | 6/12 [00:00<00:00, 13.06it/s] Sampling: 67%|██████▋ | 8/12 [00:00<00:00, 13.11it/s] Sampling: 83%|████████▎ | 10/12 [00:00<00:00, 13.13it/s] Sampling: 100%|██████████| 12/12 [00:00<00:00, 14.27it/s] Sampling: 0%| | 0/12 [00:00<?, ?it/s] Sampling: 8%|▊ | 1/12 [00:00<00:01, 6.08it/s] Sampling: 17%|█▋ | 2/12 [00:00<00:01, 7.69it/s] Sampling: 25%|██▌ | 3/12 [00:00<00:01, 8.40it/s] Sampling: 33%|███▎ | 4/12 [00:00<00:00, 8.76it/s] Sampling: 42%|████▏ | 5/12 [00:00<00:00, 8.97it/s] Sampling: 50%|█████ | 6/12 [00:00<00:00, 9.09it/s] Sampling: 58%|█████▊ | 7/12 [00:00<00:00, 9.20it/s] Sampling: 67%|██████▋ | 8/12 [00:00<00:00, 9.27it/s] Sampling: 75%|███████▌ | 9/12 [00:01<00:00, 9.31it/s] Sampling: 83%|████████▎ | 10/12 [00:01<00:00, 9.33it/s] Sampling: 100%|██████████| 12/12 [00:01<00:00, 12.21it/s] Sampling: 100%|██████████| 12/12 [00:01<00:00, 9.77it/s] INFO:predict:TRELLIS pipeline complete! INFO:predict:Available output formats: dict_keys(['mesh', 'gaussian']) INFO:predict:Starting video rendering... INFO:predict:Generating color video from gaussian output... Rendering: 0it [00:00, ?it/s] Rendering: 25it [00:00, 243.58it/s] Rendering: 55it [00:00, 271.85it/s] Rendering: 87it [00:00, 290.52it/s] Rendering: 118it [00:00, 295.69it/s] Rendering: 120it [00:00, 288.14it/s] INFO:predict:Available gaussian render types: ['color', 'depth'] INFO:predict:Generated color video successfully INFO:predict:Video rendering complete! INFO:predict:Generating GLB model... INFO- Loaded 14867 vertices and 30203 faces. 0% done 2% done 4% done 7% done 9% done 11% done 14% done 16% done 19% done 21% done 23% done 26% done 28% done 30% done 33% done 35% done 38% done 40% done 42% done 45% done 47% done 50% done 52% done 54% done 57% done 59% done 61% done 64% done 66% done 69% done 71% done 73% done 76% done 78% done 80% done 83% done 85% done 88% done 90% done 92% done 95% done 97% done 100% done WARNING- Some cuts were necessary to cope with non manifold configuration. Rendering: 0it [00:00, ?it/s] Rendering: 13it [00:00, 126.91it/s] Rendering: 29it [00:00, 141.41it/s] Rendering: 44it [00:00, 143.10it/s] Rendering: 60it [00:00, 146.69it/s] Rendering: 75it [00:00, 145.26it/s] Rendering: 90it [00:00, 146.68it/s] Rendering: 100it [00:00, 144.62it/s] INFO:predict:GLB model generation complete! INFO:predict:Prediction complete! Returning results...