ndreca / hunyuan3d-2
Scaling Diffusion Models for High Resolution Textured 3D Assets Generation
Prediction
ndreca/hunyuan3d-2:844eb9a93c3b9a43a8cab12096019bfcb263a5db616a9f67833ed97926382ef8IDqwc23hxqaxrm80cptzp966vc3gStatusSucceededSourceWebHardwareL40STotal durationCreatedInput
- seed
- 1234
- image
- steps
- 50
- num_chunks
- 200000
- max_facenum
- 40000
- guidance_scale
- 5.5
- octree_resolution
- 512
- remove_background
{ "seed": 1234, "image": "https://replicate.delivery/pbxt/MVC2B2XKgv4X13qIpW6t2m59EVfY2CqaS9e2CSsWNHPJjQAd/image.png", "steps": 50, "num_chunks": 200000, "max_facenum": 40000, "guidance_scale": 5.5, "octree_resolution": 512, "remove_background": false }Install Replicate’s Node.js client library:npm install replicateImport and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run ndreca/hunyuan3d-2 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "ndreca/hunyuan3d-2:844eb9a93c3b9a43a8cab12096019bfcb263a5db616a9f67833ed97926382ef8", { input: { seed: 1234, image: "https://replicate.delivery/pbxt/MVC2B2XKgv4X13qIpW6t2m59EVfY2CqaS9e2CSsWNHPJjQAd/image.png", steps: 50, num_chunks: 200000, max_facenum: 40000, guidance_scale: 5.5, octree_resolution: 512, remove_background: false } } ); 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 replicateImport the client:import replicateRun ndreca/hunyuan3d-2 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "ndreca/hunyuan3d-2:844eb9a93c3b9a43a8cab12096019bfcb263a5db616a9f67833ed97926382ef8", input={ "seed": 1234, "image": "https://replicate.delivery/pbxt/MVC2B2XKgv4X13qIpW6t2m59EVfY2CqaS9e2CSsWNHPJjQAd/image.png", "steps": 50, "num_chunks": 200000, "max_facenum": 40000, "guidance_scale": 5.5, "octree_resolution": 512, "remove_background": False } ) print(output)To learn more, take a look at the guide on getting started with Python.
Run ndreca/hunyuan3d-2 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": "ndreca/hunyuan3d-2:844eb9a93c3b9a43a8cab12096019bfcb263a5db616a9f67833ed97926382ef8", "input": { "seed": 1234, "image": "https://replicate.delivery/pbxt/MVC2B2XKgv4X13qIpW6t2m59EVfY2CqaS9e2CSsWNHPJjQAd/image.png", "steps": 50, "num_chunks": 200000, "max_facenum": 40000, "guidance_scale": 5.5, "octree_resolution": 512, "remove_background": false } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
Output
Loading...{ "completed_at": "2025-05-16T07:11:40.431327Z", "created_at": "2025-05-16T07:08:57.047000Z", "data_removed": false, "error": null, "id": "qwc23hxqaxrm80cptzp966vc3g", "input": { "seed": 1234, "image": "https://replicate.delivery/pbxt/MVC2B2XKgv4X13qIpW6t2m59EVfY2CqaS9e2CSsWNHPJjQAd/image.png", "steps": 50, "num_chunks": 200000, "max_facenum": 40000, "guidance_scale": 5.5, "octree_resolution": 512, "remove_background": false }, "logs": "Diffusion Sampling:: 0%| | 0/50 [00:00<?, ?it/s]\nDiffusion Sampling:: 2%|▏ | 1/50 [00:00<00:05, 9.43it/s]\nDiffusion Sampling:: 6%|▌ | 3/50 [00:00<00:03, 15.43it/s]\nDiffusion Sampling:: 10%|█ | 5/50 [00:00<00:03, 14.23it/s]\nDiffusion Sampling:: 14%|█▍ | 7/50 [00:00<00:03, 13.78it/s]\nDiffusion Sampling:: 18%|█▊ | 9/50 [00:00<00:03, 13.56it/s]\nDiffusion Sampling:: 22%|██▏ | 11/50 [00:00<00:02, 13.44it/s]\nDiffusion Sampling:: 26%|██▌ | 13/50 [00:00<00:02, 13.37it/s]\nDiffusion Sampling:: 30%|███ | 15/50 [00:01<00:02, 13.32it/s]\nDiffusion Sampling:: 34%|███▍ | 17/50 [00:01<00:02, 13.29it/s]\nDiffusion Sampling:: 38%|███▊ | 19/50 [00:01<00:02, 13.26it/s]\nDiffusion Sampling:: 42%|████▏ | 21/50 [00:01<00:02, 13.23it/s]\nDiffusion Sampling:: 46%|████▌ | 23/50 [00:01<00:02, 13.22it/s]\nDiffusion Sampling:: 50%|█████ | 25/50 [00:01<00:01, 13.22it/s]\nDiffusion Sampling:: 54%|█████▍ | 27/50 [00:02<00:01, 13.21it/s]\nDiffusion Sampling:: 58%|█████▊ | 29/50 [00:02<00:01, 13.21it/s]\nDiffusion Sampling:: 62%|██████▏ | 31/50 [00:02<00:01, 13.20it/s]\nDiffusion Sampling:: 66%|██████▌ | 33/50 [00:02<00:01, 13.20it/s]\nDiffusion Sampling:: 70%|███████ | 35/50 [00:02<00:01, 13.20it/s]\nDiffusion Sampling:: 74%|███████▍ | 37/50 [00:02<00:00, 13.20it/s]\nDiffusion Sampling:: 78%|███████▊ | 39/50 [00:02<00:00, 13.21it/s]\nDiffusion Sampling:: 82%|████████▏ | 41/50 [00:03<00:00, 13.19it/s]\nDiffusion Sampling:: 86%|████████▌ | 43/50 [00:03<00:00, 13.20it/s]\nDiffusion Sampling:: 90%|█████████ | 45/50 [00:03<00:00, 13.20it/s]\nDiffusion Sampling:: 94%|█████████▍| 47/50 [00:03<00:00, 13.19it/s]\nDiffusion Sampling:: 98%|█████████▊| 49/50 [00:03<00:00, 13.19it/s]\nDiffusion Sampling:: 100%|██████████| 50/50 [00:03<00:00, 13.27it/s]\n2025-05-16 07:11:06,594 - hy3dgen.shapgen - INFO - FlashVDMVolumeDecoding Resolution: [63, 126, 252, 504]\nFlashVDM Volume Decoding: 0%| | 0/2 [00:00<?, ?it/s]\nFlashVDM Volume Decoding: 100%|██████████| 2/2 [00:00<00:00, 37.96it/s]\nDecimating mesh... Deleting 993960 faces\nDecimation done. Resulting mesh has 40000 faces", "metrics": { "predict_time": 37.961812965, "total_time": 163.384327 }, "output": { "mesh": "https://replicate.delivery/xezq/Lkb4vqSOwmY7Dhcp38vMexJeQe4XctzpCIBWB3HSZlWY5SapA/mesh.glb" }, "started_at": "2025-05-16T07:11:02.469514Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/qwc23hxqaxrm80cptzp966vc3g", "cancel": "https://api.replicate.com/v1/predictions/qwc23hxqaxrm80cptzp966vc3g/cancel" }, "version": "844eb9a93c3b9a43a8cab12096019bfcb263a5db616a9f67833ed97926382ef8" }Generated inDiffusion Sampling:: 0%| | 0/50 [00:00<?, ?it/s] Diffusion Sampling:: 2%|▏ | 1/50 [00:00<00:05, 9.43it/s] Diffusion Sampling:: 6%|▌ | 3/50 [00:00<00:03, 15.43it/s] Diffusion Sampling:: 10%|█ | 5/50 [00:00<00:03, 14.23it/s] Diffusion Sampling:: 14%|█▍ | 7/50 [00:00<00:03, 13.78it/s] Diffusion Sampling:: 18%|█▊ | 9/50 [00:00<00:03, 13.56it/s] Diffusion Sampling:: 22%|██▏ | 11/50 [00:00<00:02, 13.44it/s] Diffusion Sampling:: 26%|██▌ | 13/50 [00:00<00:02, 13.37it/s] Diffusion Sampling:: 30%|███ | 15/50 [00:01<00:02, 13.32it/s] Diffusion Sampling:: 34%|███▍ | 17/50 [00:01<00:02, 13.29it/s] Diffusion Sampling:: 38%|███▊ | 19/50 [00:01<00:02, 13.26it/s] Diffusion Sampling:: 42%|████▏ | 21/50 [00:01<00:02, 13.23it/s] Diffusion Sampling:: 46%|████▌ | 23/50 [00:01<00:02, 13.22it/s] Diffusion Sampling:: 50%|█████ | 25/50 [00:01<00:01, 13.22it/s] Diffusion Sampling:: 54%|█████▍ | 27/50 [00:02<00:01, 13.21it/s] Diffusion Sampling:: 58%|█████▊ | 29/50 [00:02<00:01, 13.21it/s] Diffusion Sampling:: 62%|██████▏ | 31/50 [00:02<00:01, 13.20it/s] Diffusion Sampling:: 66%|██████▌ | 33/50 [00:02<00:01, 13.20it/s] Diffusion Sampling:: 70%|███████ | 35/50 [00:02<00:01, 13.20it/s] Diffusion Sampling:: 74%|███████▍ | 37/50 [00:02<00:00, 13.20it/s] Diffusion Sampling:: 78%|███████▊ | 39/50 [00:02<00:00, 13.21it/s] Diffusion Sampling:: 82%|████████▏ | 41/50 [00:03<00:00, 13.19it/s] Diffusion Sampling:: 86%|████████▌ | 43/50 [00:03<00:00, 13.20it/s] Diffusion Sampling:: 90%|█████████ | 45/50 [00:03<00:00, 13.20it/s] Diffusion Sampling:: 94%|█████████▍| 47/50 [00:03<00:00, 13.19it/s] Diffusion Sampling:: 98%|█████████▊| 49/50 [00:03<00:00, 13.19it/s] Diffusion Sampling:: 100%|██████████| 50/50 [00:03<00:00, 13.27it/s] 2025-05-16 07:11:06,594 - hy3dgen.shapgen - INFO - FlashVDMVolumeDecoding Resolution: [63, 126, 252, 504] FlashVDM Volume Decoding: 0%| | 0/2 [00:00<?, ?it/s] FlashVDM Volume Decoding: 100%|██████████| 2/2 [00:00<00:00, 37.96it/s] Decimating mesh... Deleting 993960 faces Decimation done. Resulting mesh has 40000 facesPrediction
ndreca/hunyuan3d-2:844eb9a93c3b9a43a8cab12096019bfcb263a5db616a9f67833ed97926382ef8ID9yaezcmgz5rm80cptzktqa9r14StatusSucceededSourceWebHardwareL40STotal durationCreatedInput
- seed
- 1234
- image
- steps
- 50
- num_chunks
- 200000
- max_facenum
- 40000
- guidance_scale
- 5.5
- octree_resolution
- 512
- remove_background
{ "seed": 1234, "image": "https://replicate.delivery/pbxt/N18In1Vq4K2L2cdy210S3ZIJ2UzwG4ih0JyP7UEIE6fXDZeb/image.png", "steps": 50, "num_chunks": 200000, "max_facenum": 40000, "guidance_scale": 5.5, "octree_resolution": 512, "remove_background": false }Install Replicate’s Node.js client library:npm install replicateImport and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run ndreca/hunyuan3d-2 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "ndreca/hunyuan3d-2:844eb9a93c3b9a43a8cab12096019bfcb263a5db616a9f67833ed97926382ef8", { input: { seed: 1234, image: "https://replicate.delivery/pbxt/N18In1Vq4K2L2cdy210S3ZIJ2UzwG4ih0JyP7UEIE6fXDZeb/image.png", steps: 50, num_chunks: 200000, max_facenum: 40000, guidance_scale: 5.5, octree_resolution: 512, remove_background: false } } ); 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 replicateImport the client:import replicateRun ndreca/hunyuan3d-2 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "ndreca/hunyuan3d-2:844eb9a93c3b9a43a8cab12096019bfcb263a5db616a9f67833ed97926382ef8", input={ "seed": 1234, "image": "https://replicate.delivery/pbxt/N18In1Vq4K2L2cdy210S3ZIJ2UzwG4ih0JyP7UEIE6fXDZeb/image.png", "steps": 50, "num_chunks": 200000, "max_facenum": 40000, "guidance_scale": 5.5, "octree_resolution": 512, "remove_background": False } ) print(output)To learn more, take a look at the guide on getting started with Python.
Run ndreca/hunyuan3d-2 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": "ndreca/hunyuan3d-2:844eb9a93c3b9a43a8cab12096019bfcb263a5db616a9f67833ed97926382ef8", "input": { "seed": 1234, "image": "https://replicate.delivery/pbxt/N18In1Vq4K2L2cdy210S3ZIJ2UzwG4ih0JyP7UEIE6fXDZeb/image.png", "steps": 50, "num_chunks": 200000, "max_facenum": 40000, "guidance_scale": 5.5, "octree_resolution": 512, "remove_background": false } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
Output
Loading...{ "completed_at": "2025-05-16T07:06:20.692344Z", "created_at": "2025-05-16T07:03:19.545000Z", "data_removed": false, "error": null, "id": "9yaezcmgz5rm80cptzktqa9r14", "input": { "seed": 1234, "image": "https://replicate.delivery/pbxt/N18In1Vq4K2L2cdy210S3ZIJ2UzwG4ih0JyP7UEIE6fXDZeb/image.png", "steps": 50, "num_chunks": 200000, "max_facenum": 40000, "guidance_scale": 5.5, "octree_resolution": 512, "remove_background": false }, "logs": "Diffusion Sampling:: 0%| | 0/50 [00:00<?, ?it/s]\nDiffusion Sampling:: 4%|▍ | 2/50 [00:00<00:02, 19.08it/s]\nDiffusion Sampling:: 8%|▊ | 4/50 [00:00<00:03, 14.71it/s]\nDiffusion Sampling:: 12%|█▏ | 6/50 [00:00<00:03, 13.66it/s]\nDiffusion Sampling:: 16%|█▌ | 8/50 [00:00<00:03, 13.22it/s]\nDiffusion Sampling:: 20%|██ | 10/50 [00:00<00:03, 13.00it/s]\nDiffusion Sampling:: 24%|██▍ | 12/50 [00:00<00:02, 12.86it/s]\nDiffusion Sampling:: 28%|██▊ | 14/50 [00:01<00:02, 12.77it/s]\nDiffusion Sampling:: 32%|███▏ | 16/50 [00:01<00:02, 12.72it/s]\nDiffusion Sampling:: 36%|███▌ | 18/50 [00:01<00:02, 12.67it/s]\nDiffusion Sampling:: 40%|████ | 20/50 [00:01<00:02, 12.64it/s]\nDiffusion Sampling:: 44%|████▍ | 22/50 [00:01<00:02, 12.61it/s]\nDiffusion Sampling:: 48%|████▊ | 24/50 [00:01<00:02, 12.59it/s]\nDiffusion Sampling:: 52%|█████▏ | 26/50 [00:02<00:01, 12.57it/s]\nDiffusion Sampling:: 56%|█████▌ | 28/50 [00:02<00:01, 12.55it/s]\nDiffusion Sampling:: 60%|██████ | 30/50 [00:02<00:01, 12.53it/s]\nDiffusion Sampling:: 64%|██████▍ | 32/50 [00:02<00:01, 12.52it/s]\nDiffusion Sampling:: 68%|██████▊ | 34/50 [00:02<00:01, 12.51it/s]\nDiffusion Sampling:: 72%|███████▏ | 36/50 [00:02<00:01, 12.51it/s]\nDiffusion Sampling:: 76%|███████▌ | 38/50 [00:02<00:00, 12.51it/s]\nDiffusion Sampling:: 80%|████████ | 40/50 [00:03<00:00, 12.51it/s]\nDiffusion Sampling:: 84%|████████▍ | 42/50 [00:03<00:00, 12.50it/s]\nDiffusion Sampling:: 88%|████████▊ | 44/50 [00:03<00:00, 12.50it/s]\nDiffusion Sampling:: 92%|█████████▏| 46/50 [00:03<00:00, 12.50it/s]\nDiffusion Sampling:: 96%|█████████▌| 48/50 [00:03<00:00, 12.50it/s]\nDiffusion Sampling:: 100%|██████████| 50/50 [00:03<00:00, 12.50it/s]\nDiffusion Sampling:: 100%|██████████| 50/50 [00:03<00:00, 12.71it/s]\n2025-05-16 07:05:39,438 - hy3dgen.shapgen - INFO - FlashVDMVolumeDecoding Resolution: [63, 126, 252, 504]\nFlashVDM Volume Decoding: 0%| | 0/2 [00:00<?, ?it/s]\nFlashVDM Volume Decoding: 100%|██████████| 2/2 [00:00<00:00, 560.14it/s]\nDecimating mesh... Deleting 2191980 faces\nDecimation done. Resulting mesh has 40000 faces", "metrics": { "predict_time": 45.523528244, "total_time": 181.147344 }, "output": { "mesh": "https://replicate.delivery/xezq/Coie3FDmMw0SeUvauFoPgOvePbI33XIgK7if4p0jafam9KplC/mesh.glb" }, "started_at": "2025-05-16T07:05:35.168816Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/9yaezcmgz5rm80cptzktqa9r14", "cancel": "https://api.replicate.com/v1/predictions/9yaezcmgz5rm80cptzktqa9r14/cancel" }, "version": "844eb9a93c3b9a43a8cab12096019bfcb263a5db616a9f67833ed97926382ef8" }Generated inDiffusion Sampling:: 0%| | 0/50 [00:00<?, ?it/s] Diffusion Sampling:: 4%|▍ | 2/50 [00:00<00:02, 19.08it/s] Diffusion Sampling:: 8%|▊ | 4/50 [00:00<00:03, 14.71it/s] Diffusion Sampling:: 12%|█▏ | 6/50 [00:00<00:03, 13.66it/s] Diffusion Sampling:: 16%|█▌ | 8/50 [00:00<00:03, 13.22it/s] Diffusion Sampling:: 20%|██ | 10/50 [00:00<00:03, 13.00it/s] Diffusion Sampling:: 24%|██▍ | 12/50 [00:00<00:02, 12.86it/s] Diffusion Sampling:: 28%|██▊ | 14/50 [00:01<00:02, 12.77it/s] Diffusion Sampling:: 32%|███▏ | 16/50 [00:01<00:02, 12.72it/s] Diffusion Sampling:: 36%|███▌ | 18/50 [00:01<00:02, 12.67it/s] Diffusion Sampling:: 40%|████ | 20/50 [00:01<00:02, 12.64it/s] Diffusion Sampling:: 44%|████▍ | 22/50 [00:01<00:02, 12.61it/s] Diffusion Sampling:: 48%|████▊ | 24/50 [00:01<00:02, 12.59it/s] Diffusion Sampling:: 52%|█████▏ | 26/50 [00:02<00:01, 12.57it/s] Diffusion Sampling:: 56%|█████▌ | 28/50 [00:02<00:01, 12.55it/s] Diffusion Sampling:: 60%|██████ | 30/50 [00:02<00:01, 12.53it/s] Diffusion Sampling:: 64%|██████▍ | 32/50 [00:02<00:01, 12.52it/s] Diffusion Sampling:: 68%|██████▊ | 34/50 [00:02<00:01, 12.51it/s] Diffusion Sampling:: 72%|███████▏ | 36/50 [00:02<00:01, 12.51it/s] Diffusion Sampling:: 76%|███████▌ | 38/50 [00:02<00:00, 12.51it/s] Diffusion Sampling:: 80%|████████ | 40/50 [00:03<00:00, 12.51it/s] Diffusion Sampling:: 84%|████████▍ | 42/50 [00:03<00:00, 12.50it/s] Diffusion Sampling:: 88%|████████▊ | 44/50 [00:03<00:00, 12.50it/s] Diffusion Sampling:: 92%|█████████▏| 46/50 [00:03<00:00, 12.50it/s] Diffusion Sampling:: 96%|█████████▌| 48/50 [00:03<00:00, 12.50it/s] Diffusion Sampling:: 100%|██████████| 50/50 [00:03<00:00, 12.50it/s] Diffusion Sampling:: 100%|██████████| 50/50 [00:03<00:00, 12.71it/s] 2025-05-16 07:05:39,438 - hy3dgen.shapgen - INFO - FlashVDMVolumeDecoding Resolution: [63, 126, 252, 504] FlashVDM Volume Decoding: 0%| | 0/2 [00:00<?, ?it/s] FlashVDM Volume Decoding: 100%|██████████| 2/2 [00:00<00:00, 560.14it/s] Decimating mesh... Deleting 2191980 faces Decimation done. Resulting mesh has 40000 faces
Want to make some of these yourself?
Run this model