jd7h / luciddreamer
High-Fidelity Text-to-3D Generation via Interval Score Matching
Prediction
jd7h/luciddreamer:fbf8e0dfef4ca0c0de45cf1afbf12c81667ee29fd79852852262aee4f167fbf5ID3atbyrtb3q54kierm4sx5u3bsaStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- cfg
- 7.5
- prompt
- A dog on a skateboard, hair waving in the wind, HDR, photorealistic, 8K
- iterations
- 1000
- neg_prompt
- unrealistic, blurry, low quality, out of focus, ugly, low contrast, dull, low resolution, distorted, boring
- init_prompt
- dog
{ "cfg": 7.5, "prompt": "A dog on a skateboard, hair waving in the wind, HDR, photorealistic, 8K", "iterations": 1000, "neg_prompt": "unrealistic, blurry, low quality, out of focus, ugly, low contrast, dull, low resolution, distorted, boring", "init_prompt": "dog" }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 jd7h/luciddreamer using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "jd7h/luciddreamer:fbf8e0dfef4ca0c0de45cf1afbf12c81667ee29fd79852852262aee4f167fbf5", { input: { cfg: 7.5, prompt: "A dog on a skateboard, hair waving in the wind, HDR, photorealistic, 8K", iterations: 1000, neg_prompt: "unrealistic, blurry, low quality, out of focus, ugly, low contrast, dull, low resolution, distorted, boring", init_prompt: "dog" } } ); // To access the file URL: console.log(output[0].url()); //=> "http://example.com" // To write the file to disk: fs.writeFile("my-image.png", output[0]);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 jd7h/luciddreamer using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "jd7h/luciddreamer:fbf8e0dfef4ca0c0de45cf1afbf12c81667ee29fd79852852262aee4f167fbf5", input={ "cfg": 7.5, "prompt": "A dog on a skateboard, hair waving in the wind, HDR, photorealistic, 8K", "iterations": 1000, "neg_prompt": "unrealistic, blurry, low quality, out of focus, ugly, low contrast, dull, low resolution, distorted, boring", "init_prompt": "dog" } ) print(output)To learn more, take a look at the guide on getting started with Python.
Run jd7h/luciddreamer 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": "jd7h/luciddreamer:fbf8e0dfef4ca0c0de45cf1afbf12c81667ee29fd79852852262aee4f167fbf5", "input": { "cfg": 7.5, "prompt": "A dog on a skateboard, hair waving in the wind, HDR, photorealistic, 8K", "iterations": 1000, "neg_prompt": "unrealistic, blurry, low quality, out of focus, ugly, low contrast, dull, low resolution, distorted, boring", "init_prompt": "dog" } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2023-12-22T16:32:55.487744Z", "created_at": "2023-12-22T16:14:30.678052Z", "data_removed": false, "error": null, "id": "3atbyrtb3q54kierm4sx5u3bsa", "input": { "cfg": 7.5, "prompt": "A dog on a skateboard, hair waving in the wind, HDR, photorealistic, 8K", "iterations": 1000, "neg_prompt": "unrealistic, blurry, low quality, out of focus, ugly, low contrast, dull, low resolution, distorted, boring", "init_prompt": "dog" }, "logs": "Using seed: 2212729883\nTest iter: [1, 200, 400, 600, 800, 1000]\nSave iter: [500, 1000]\nOptimizing\nOutput folder: ./output/Replicate [22/12 16:16:11]\nTensorboard not available: not logging progress [22/12 16:16:11]\nReading Test Transforms [22/12 16:16:11]\ncreating base model...[22/12 16:16:12]\n 0%| | 0.00/890M [00:00<?, ?iB/s]\n 1%|▍ | 10.9M/890M [00:00<00:08, 115MiB/s]\n 3%|▉ | 22.7M/890M [00:00<00:07, 120MiB/s]\n 4%|█▍ | 34.2M/890M [00:00<00:07, 114MiB/s]\n 5%|█▉ | 45.1M/890M [00:00<00:08, 106MiB/s]\n 6%|██▌ | 57.7M/890M [00:00<00:07, 115MiB/s]\n 8%|███ | 68.7M/890M [00:00<00:07, 111MiB/s]\n 9%|███▍ | 79.4M/890M [00:00<00:07, 111MiB/s]\n 10%|███▉ | 90.0M/890M [00:00<00:07, 110MiB/s]\n 12%|████▋ | 103M/890M [00:00<00:07, 118MiB/s]\n 13%|█████▏ | 115M/890M [00:01<00:06, 120MiB/s]\n 14%|█████▋ | 127M/890M [00:01<00:06, 123MiB/s]\n 16%|██████▎ | 140M/890M [00:01<00:06, 125MiB/s]\n 17%|██████▊ | 152M/890M [00:01<00:06, 114MiB/s]\n 18%|███████▎ | 163M/890M [00:01<00:07, 107MiB/s]\n 19%|███████▊ | 173M/890M [00:01<00:07, 106MiB/s]\n 21%|████████▎ | 184M/890M [00:01<00:06, 109MiB/s]\n 22%|████████▊ | 195M/890M [00:01<00:06, 109MiB/s]\n 23%|█████████▏ | 205M/890M [00:01<00:07, 100MiB/s]\n 24%|█████████▍ | 215M/890M [00:02<00:07, 97.7MiB/s]\n 25%|█████████▊ | 224M/890M [00:02<00:07, 97.0MiB/s]\n 27%|██████████▌ | 236M/890M [00:02<00:06, 104MiB/s]\n 28%|███████████ | 247M/890M [00:02<00:06, 105MiB/s]\n 29%|███████████▌ | 257M/890M [00:02<00:06, 101MiB/s]\n 30%|████████████ | 267M/890M [00:02<00:06, 104MiB/s]\n 31%|████████████▌ | 279M/890M [00:02<00:05, 109MiB/s]\n 33%|█████████████ | 290M/890M [00:02<00:05, 107MiB/s]\n 34%|█████████████▌ | 301M/890M [00:02<00:05, 109MiB/s]\n 35%|██████████████ | 312M/890M [00:02<00:05, 113MiB/s]\n 36%|██████████████▌ | 323M/890M [00:03<00:05, 108MiB/s]\n 38%|███████████████ | 334M/890M [00:03<00:05, 111MiB/s]\n 39%|███████████████▌ | 345M/890M [00:03<00:05, 107MiB/s]\n 40%|███████████████▉ | 356M/890M [00:03<00:05, 108MiB/s]\n 41%|████████████████▌ | 367M/890M [00:03<00:04, 112MiB/s]\n 42%|████████████████▉ | 378M/890M [00:03<00:04, 109MiB/s]\n 44%|█████████████████▍ | 388M/890M [00:03<00:04, 108MiB/s]\n 45%|██████████████████ | 400M/890M [00:03<00:04, 113MiB/s]\n 46%|██████████████████▌ | 412M/890M [00:03<00:04, 115MiB/s]\n 48%|███████████████████ | 424M/890M [00:04<00:04, 118MiB/s]\n 49%|███████████████████▌ | 435M/890M [00:04<00:04, 114MiB/s]\n 50%|████████████████████ | 447M/890M [00:04<00:04, 114MiB/s]\n 51%|████████████████████▌ | 458M/890M [00:04<00:04, 101MiB/s]\n 53%|█████████████████████ | 468M/890M [00:04<00:04, 100MiB/s]\n 54%|█████████████████████▍ | 478M/890M [00:04<00:04, 101MiB/s]\n 55%|█████████████████████▎ | 488M/890M [00:04<00:04, 93.0MiB/s]\n 56%|█████████████████████▊ | 498M/890M [00:04<00:04, 97.1MiB/s]\n 57%|██████████████████████▏ | 507M/890M [00:04<00:04, 94.1MiB/s]\n 58%|██████████████████████▋ | 516M/890M [00:05<00:04, 88.4MiB/s]\n 59%|███████████████████████ | 527M/890M [00:05<00:04, 93.4MiB/s]\n 60%|███████████████████████▌ | 537M/890M [00:05<00:03, 96.0MiB/s]\n 62%|████████████████████████▋ | 548M/890M [00:05<00:03, 102MiB/s]\n 63%|█████████████████████████▏ | 560M/890M [00:05<00:03, 111MiB/s]\n 64%|█████████████████████████▋ | 572M/890M [00:05<00:02, 115MiB/s]\n 66%|██████████████████████████▏ | 584M/890M [00:05<00:02, 116MiB/s]\n 67%|██████████████████████████▋ | 595M/890M [00:05<00:02, 111MiB/s]\n 68%|███████████████████████████▏ | 605M/890M [00:05<00:02, 109MiB/s]\n 69%|███████████████████████████▋ | 616M/890M [00:06<00:02, 108MiB/s]\n 70%|████████████████████████████▏ | 627M/890M [00:06<00:02, 110MiB/s]\n 72%|████████████████████████████▋ | 639M/890M [00:06<00:02, 113MiB/s]\n 73%|█████████████████████████████▏ | 650M/890M [00:06<00:02, 110MiB/s]\n 74%|█████████████████████████████▋ | 660M/890M [00:06<00:02, 110MiB/s]\n 75%|██████████████████████████████▏ | 671M/890M [00:06<00:02, 102MiB/s]\n 76%|█████████████████████████████▊ | 680M/890M [00:06<00:02, 99.7MiB/s]\n 78%|███████████████████████████████ | 691M/890M [00:06<00:02, 104MiB/s]\n 79%|███████████████████████████████▋ | 704M/890M [00:06<00:01, 112MiB/s]\n 81%|████████████████████████████████▎ | 718M/890M [00:06<00:01, 120MiB/s]\n 82%|████████████████████████████████▊ | 729M/890M [00:07<00:01, 117MiB/s]\n 83%|█████████████████████████████████▎ | 741M/890M [00:07<00:01, 118MiB/s]\n 85%|█████████████████████████████████▊ | 752M/890M [00:07<00:01, 118MiB/s]\n 86%|██████████████████████████████████▎ | 763M/890M [00:07<00:01, 116MiB/s]\n 87%|██████████████████████████████████▊ | 775M/890M [00:07<00:01, 118MiB/s]\n 88%|███████████████████████████████████▎ | 786M/890M [00:07<00:00, 111MiB/s]\n 90%|███████████████████████████████████▊ | 797M/890M [00:07<00:00, 110MiB/s]\n 91%|████████████████████████████████████▎ | 808M/890M [00:07<00:00, 112MiB/s]\n 92%|████████████████████████████████████▊ | 819M/890M [00:07<00:00, 112MiB/s]\n 93%|█████████████████████████████████████▎ | 830M/890M [00:08<00:00, 114MiB/s]\n 95%|█████████████████████████████████████▊ | 841M/890M [00:08<00:00, 111MiB/s]\n 96%|██████████████████████████████████████▍ | 854M/890M [00:08<00:00, 119MiB/s]\n 97%|██████████████████████████████████████▉ | 866M/890M [00:08<00:00, 120MiB/s]\n 99%|███████████████████████████████████████▍| 878M/890M [00:08<00:00, 120MiB/s]\n100%|███████████████████████████████████████▉| 890M/890M [00:08<00:00, 121MiB/s]\n100%|████████████████████████████████████████| 890M/890M [00:08<00:00, 110MiB/s]\ncreating upsample model... [22/12 16:16:28]\ndownloading base checkpoint... [22/12 16:16:33]\n 0%| | 0.00/161M [00:00<?, ?iB/s]\n 6%|▌ | 9.18M/161M [00:00<00:01, 90.8MiB/s]\n 11%|█▏ | 18.3M/161M [00:00<00:01, 74.8MiB/s]\n 16%|█▌ | 26.2M/161M [00:00<00:01, 76.4MiB/s]\n 21%|██ | 34.0M/161M [00:00<00:01, 76.3MiB/s]\n 26%|██▌ | 42.3M/161M [00:00<00:01, 78.6MiB/s]\n 31%|███ | 50.3M/161M [00:00<00:01, 78.7MiB/s]\n 37%|███▋ | 59.1M/161M [00:00<00:01, 81.6MiB/s]\n 42%|████▏ | 67.4M/161M [00:00<00:01, 81.8MiB/s]\n 47%|████▋ | 76.0M/161M [00:00<00:01, 82.6MiB/s]\n 52%|█████▏ | 84.2M/161M [00:01<00:00, 80.5MiB/s]\n 57%|█████▋ | 92.3M/161M [00:01<00:00, 75.6MiB/s]\n 62%|██████▏ | 99.9M/161M [00:01<00:00, 73.4MiB/s]\n 68%|██████▊ | 109M/161M [00:01<00:00, 77.9MiB/s] \n 73%|███████▎ | 117M/161M [00:01<00:00, 78.7MiB/s]\n 78%|███████▊ | 126M/161M [00:01<00:00, 81.0MiB/s]\n 83%|████████▎ | 134M/161M [00:01<00:00, 73.2MiB/s]\n 88%|████████▊ | 141M/161M [00:01<00:00, 68.7MiB/s]\n 92%|█████████▏| 149M/161M [00:01<00:00, 70.8MiB/s]\n 97%|█████████▋| 157M/161M [00:02<00:00, 71.5MiB/s]\n100%|██████████| 161M/161M [00:02<00:00, 76.3MiB/s]\ndownloading upsampler checkpoint... [22/12 16:16:35]\n 0%| | 0.00/162M [00:00<?, ?iB/s]\n 6%|▌ | 8.98M/162M [00:00<00:01, 84.4MiB/s]\n 11%|█ | 17.7M/162M [00:00<00:01, 85.6MiB/s]\n 16%|█▌ | 26.3M/162M [00:00<00:01, 68.1MiB/s]\n 21%|██▏ | 34.6M/162M [00:00<00:01, 72.9MiB/s]\n 26%|██▋ | 42.8M/162M [00:00<00:01, 76.0MiB/s]\n 31%|███▏ | 50.7M/162M [00:00<00:01, 72.0MiB/s]\n 36%|███▋ | 58.7M/162M [00:00<00:01, 74.6MiB/s]\n 41%|████ | 66.3M/162M [00:00<00:01, 73.9MiB/s]\n 46%|████▋ | 75.0M/162M [00:00<00:01, 77.9MiB/s]\n 51%|█████ | 82.9M/162M [00:01<00:01, 76.4MiB/s]\n 56%|█████▋ | 91.5M/162M [00:01<00:00, 79.1MiB/s]\n 61%|██████▏ | 99.4M/162M [00:01<00:00, 76.0MiB/s]\n 66%|██████▌ | 107M/162M [00:01<00:00, 75.1MiB/s] \n 71%|███████ | 115M/162M [00:01<00:00, 72.0MiB/s]\n 75%|███████▌ | 122M/162M [00:01<00:00, 67.8MiB/s]\n 79%|███████▉ | 129M/162M [00:01<00:00, 65.5MiB/s]\n 84%|████████▎ | 136M/162M [00:01<00:00, 66.2MiB/s]\n 89%|████████▉ | 144M/162M [00:01<00:00, 70.9MiB/s]\n 94%|█████████▍| 153M/162M [00:02<00:00, 76.2MiB/s]\n 99%|█████████▉| 160M/162M [00:02<00:00, 62.2MiB/s]\n100%|██████████| 162M/162M [00:02<00:00, 71.7MiB/s]\n0it [00:00, ?it/s]\n1it [00:01, 1.13s/it]\n4it [00:01, 3.98it/s]\n7it [00:01, 7.11it/s]\n10it [00:01, 10.06it/s]\n13it [00:01, 12.68it/s]\n16it [00:01, 14.89it/s]\n19it [00:01, 16.66it/s]\n22it [00:02, 18.06it/s]\n25it [00:02, 19.11it/s]\n28it [00:02, 19.89it/s]\n31it [00:02, 20.46it/s]\n34it [00:02, 20.85it/s]\n37it [00:02, 21.15it/s]\n40it [00:02, 21.35it/s]\n43it [00:03, 21.48it/s]\n46it [00:03, 21.57it/s]\n49it [00:03, 21.63it/s]\n52it [00:03, 21.66it/s]\n55it [00:03, 21.69it/s]\n58it [00:03, 21.74it/s]\n61it [00:03, 21.78it/s]\n64it [00:04, 21.79it/s]\n67it [00:04, 16.75it/s]\n69it [00:04, 11.47it/s]\n71it [00:05, 9.06it/s]\n73it [00:05, 7.75it/s]\n74it [00:05, 7.28it/s]\n75it [00:05, 6.86it/s]\n76it [00:05, 6.51it/s]\n77it [00:06, 6.23it/s]\n78it [00:06, 6.03it/s]\n79it [00:06, 5.87it/s]\n80it [00:06, 5.76it/s]\n81it [00:06, 5.68it/s]\n82it [00:07, 5.62it/s]\n83it [00:07, 5.58it/s]\n84it [00:07, 5.54it/s]\n85it [00:07, 5.52it/s]\n86it [00:07, 5.50it/s]\n87it [00:07, 5.50it/s]\n88it [00:08, 5.49it/s]\n89it [00:08, 5.48it/s]\n90it [00:08, 5.48it/s]\n91it [00:08, 5.48it/s]\n92it [00:08, 5.47it/s]\n93it [00:09, 5.47it/s]\n94it [00:09, 5.47it/s]\n95it [00:09, 5.47it/s]\n96it [00:09, 5.46it/s]\n97it [00:09, 5.45it/s]\n98it [00:09, 5.45it/s]\n99it [00:10, 5.46it/s]\n100it [00:10, 5.46it/s]\n101it [00:10, 5.46it/s]\n102it [00:10, 5.45it/s]\n103it [00:10, 5.45it/s]\n104it [00:11, 5.42it/s]\n105it [00:11, 5.44it/s]\n106it [00:11, 5.45it/s]\n107it [00:11, 5.44it/s]\n108it [00:11, 5.44it/s]\n109it [00:11, 5.44it/s]\n110it [00:12, 5.43it/s]\n111it [00:12, 5.43it/s]\n112it [00:12, 5.43it/s]\n113it [00:12, 5.43it/s]\n114it [00:12, 5.43it/s]\n115it [00:13, 5.42it/s]\n116it [00:13, 5.42it/s]\n117it [00:13, 5.42it/s]\n118it [00:13, 5.42it/s]\n119it [00:13, 5.42it/s]\n120it [00:14, 5.42it/s]\n121it [00:14, 5.41it/s]\n122it [00:14, 5.42it/s]\n123it [00:14, 5.42it/s]\n124it [00:14, 5.42it/s]\n125it [00:14, 5.42it/s]\n126it [00:15, 5.42it/s]\n127it [00:15, 5.42it/s]\n128it [00:15, 5.42it/s]\n129it [00:15, 5.42it/s]\n130it [00:15, 8.29it/s]\nGenerating random point cloud (81920)... [22/12 16:16:53]\nNumber of points at initialisation : 81920 [22/12 16:16:54]\ntrain_process is in : ./output/Replicate/train_process/ [22/12 16:16:54]\n[INFO] loading stable diffusion... [22/12 16:16:57]\n[INFO] loaded stable diffusion! [22/12 16:16:59]\ntest views is in : ./output/Replicate/test_six_views/1_iteration [22/12 16:17:15]\n[ITER 1] Eval Done! [22/12 16:17:15]\nvideos is in : ./output/Replicate/videos/1_iteration [22/12 16:17:15]\nGenerating Video using 240 different view points[22/12 16:17:21]\n[ITER 1] Video Save Done! [22/12 16:17:24]\nTraining progress: 0%| | 0/1000 [00:00<?, ?it/s]\nTraining progress: 0%| | 0/1000 [00:32<?, ?it/s, Loss=1.0017186]\nTraining progress: 1%| | 10/1000 [00:32<53:16, 3.23s/it, Loss=1.0017186]\nTraining progress: 1%| | 10/1000 [00:40<53:16, 3.23s/it, Loss=1.0077757]\nTraining progress: 2%|▏ | 20/1000 [00:40<29:57, 1.83s/it, Loss=1.0077757]\nTraining progress: 2%|▏ | 20/1000 [00:49<29:57, 1.83s/it, Loss=1.0079711]\nTraining progress: 3%|▎ | 30/1000 [00:49<22:13, 1.37s/it, Loss=1.0079711]\nTraining progress: 3%|▎ | 30/1000 [00:57<22:13, 1.37s/it, Loss=1.0078438]\nTraining progress: 4%|▍ | 40/1000 [00:57<18:36, 1.16s/it, Loss=1.0078438]\nTraining progress: 4%|▍ | 40/1000 [01:05<18:36, 1.16s/it, Loss=1.0082182]\nTraining progress: 5%|▌ | 50/1000 [01:05<16:07, 1.02s/it, Loss=1.0082182]\nTraining progress: 5%|▌ | 50/1000 [01:13<16:07, 1.02s/it, Loss=1.0086312]\nTraining progress: 6%|▌ | 60/1000 [01:13<14:56, 1.05it/s, Loss=1.0086312]\nTraining progress: 6%|▌ | 60/1000 [01:21<14:56, 1.05it/s, Loss=1.0084402]\nTraining progress: 7%|▋ | 70/1000 [01:21<14:01, 1.11it/s, Loss=1.0084402]\nTraining progress: 7%|▋ | 70/1000 [01:29<14:01, 1.11it/s, Loss=1.0085526]\nTraining progress: 8%|▊ | 80/1000 [01:29<13:33, 1.13it/s, Loss=1.0085526]\nTraining progress: 8%|▊ | 80/1000 [01:38<13:33, 1.13it/s, Loss=1.0085533]\nTraining progress: 9%|▉ | 90/1000 [01:38<13:09, 1.15it/s, Loss=1.0085533]\nTraining progress: 9%|▉ | 90/1000 [01:48<13:09, 1.15it/s, Loss=1.0085533]\nTraining progress: 10%|█ | 100/1000 [01:48<13:34, 1.11it/s, Loss=1.0085533]\nTraining progress: 10%|█ | 100/1000 [01:56<13:34, 1.11it/s, Loss=1.0088473]\nTraining progress: 11%|█ | 110/1000 [01:56<12:57, 1.15it/s, Loss=1.0088473]\nTraining progress: 11%|█ | 110/1000 [02:04<12:57, 1.15it/s, Loss=1.0088198]\nTraining progress: 12%|█▏ | 120/1000 [02:04<12:33, 1.17it/s, Loss=1.0088198]\nTraining progress: 12%|█▏ | 120/1000 [02:12<12:33, 1.17it/s, Loss=1.0089299]\nTraining progress: 13%|█▎ | 130/1000 [02:12<12:04, 1.20it/s, Loss=1.0089299]\nTraining progress: 13%|█▎ | 130/1000 [02:20<12:04, 1.20it/s, Loss=1.0090425]\nTraining progress: 14%|█▍ | 140/1000 [02:20<11:48, 1.21it/s, Loss=1.0090425]\nTraining progress: 14%|█▍ | 140/1000 [02:28<11:48, 1.21it/s, Loss=1.0093045]\nTraining progress: 15%|█▌ | 150/1000 [02:28<11:36, 1.22it/s, Loss=1.0093045]\nTraining progress: 15%|█▌ | 150/1000 [02:36<11:36, 1.22it/s, Loss=1.0089162]\nTraining progress: 16%|█▌ | 160/1000 [02:36<11:19, 1.24it/s, Loss=1.0089162]\nTraining progress: 16%|█▌ | 160/1000 [02:44<11:19, 1.24it/s, Loss=1.0091812]\nTraining progress: 17%|█▋ | 170/1000 [02:44<11:13, 1.23it/s, Loss=1.0091812]\nTraining progress: 17%|█▋ | 170/1000 [02:52<11:13, 1.23it/s, Loss=1.0082853]\nTraining progress: 18%|█▊ | 180/1000 [02:52<11:06, 1.23it/s, Loss=1.0082853]\nTraining progress: 18%|█▊ | 180/1000 [03:00<11:06, 1.23it/s, Loss=1.0082300]\nTraining progress: 19%|█▉ | 190/1000 [03:00<10:48, 1.25it/s, Loss=1.0082300]\nTraining progress: 19%|█▉ | 190/1000 [03:09<10:48, 1.25it/s, Loss=1.0085656]\ntest views is in : ./output/Replicate/test_six_views/200_iteration[22/12 16:20:08]\n[ITER 200] Eval Done! [22/12 16:20:09]\nvideos is in : ./output/Replicate/videos/200_iteration[22/12 16:20:09]\nGenerating Video using 240 different view points[22/12 16:20:15]\n[ITER 200] Video Save Done! [22/12 16:20:17]\nTraining progress: 20%|██ | 200/1000 [03:09<11:08, 1.20it/s, Loss=1.0085656]\nTraining progress: 20%|██ | 200/1000 [03:27<11:08, 1.20it/s, Loss=1.0087679]\nTraining progress: 21%|██ | 210/1000 [03:27<14:44, 1.12s/it, Loss=1.0087679]\nTraining progress: 21%|██ | 210/1000 [03:35<14:44, 1.12s/it, Loss=1.0089540]\nTraining progress: 22%|██▏ | 220/1000 [03:35<13:32, 1.04s/it, Loss=1.0089540]\nTraining progress: 22%|██▏ | 220/1000 [03:44<13:32, 1.04s/it, Loss=1.0088401]\nTraining progress: 23%|██▎ | 230/1000 [03:44<12:39, 1.01it/s, Loss=1.0088401]\nTraining progress: 23%|██▎ | 230/1000 [03:52<12:39, 1.01it/s, Loss=1.0080839]\nTraining progress: 24%|██▍ | 240/1000 [03:52<12:04, 1.05it/s, Loss=1.0080839]\nTraining progress: 24%|██▍ | 240/1000 [04:01<12:04, 1.05it/s, Loss=1.0084546]\nTraining progress: 25%|██▌ | 250/1000 [04:01<11:26, 1.09it/s, Loss=1.0084546]\nTraining progress: 25%|██▌ | 250/1000 [04:09<11:26, 1.09it/s, Loss=1.0087927]\nTraining progress: 26%|██▌ | 260/1000 [04:09<10:56, 1.13it/s, Loss=1.0087927]\nTraining progress: 26%|██▌ | 260/1000 [04:17<10:56, 1.13it/s, Loss=1.0085855]\nTraining progress: 27%|██▋ | 270/1000 [04:17<10:30, 1.16it/s, Loss=1.0085855]\nTraining progress: 27%|██▋ | 270/1000 [04:26<10:30, 1.16it/s, Loss=1.0083972]\nTraining progress: 28%|██▊ | 280/1000 [04:26<10:20, 1.16it/s, Loss=1.0083972]\nTraining progress: 28%|██▊ | 280/1000 [04:34<10:20, 1.16it/s, Loss=1.0090715]\nTraining progress: 29%|██▉ | 290/1000 [04:34<10:08, 1.17it/s, Loss=1.0090715]\nTraining progress: 29%|██▉ | 290/1000 [04:44<10:08, 1.17it/s, Loss=1.0085778]\nTraining progress: 30%|███ | 300/1000 [04:44<10:18, 1.13it/s, Loss=1.0085778]\nTraining progress: 30%|███ | 300/1000 [04:52<10:18, 1.13it/s, Loss=1.0078171]\nTraining progress: 31%|███ | 310/1000 [04:52<09:56, 1.16it/s, Loss=1.0078171]\nTraining progress: 31%|███ | 310/1000 [05:01<09:56, 1.16it/s, Loss=1.0089422]\nTraining progress: 32%|███▏ | 320/1000 [05:01<10:04, 1.12it/s, Loss=1.0089422]\nTraining progress: 32%|███▏ | 320/1000 [05:10<10:04, 1.12it/s, Loss=1.0096785]\nTraining progress: 33%|███▎ | 330/1000 [05:10<09:47, 1.14it/s, Loss=1.0096785]\nTraining progress: 33%|███▎ | 330/1000 [05:18<09:47, 1.14it/s, Loss=1.0101533]\nTraining progress: 34%|███▍ | 340/1000 [05:18<09:31, 1.15it/s, Loss=1.0101533]\nTraining progress: 34%|███▍ | 340/1000 [05:26<09:31, 1.15it/s, Loss=1.0105944]\nTraining progress: 35%|███▌ | 350/1000 [05:26<09:15, 1.17it/s, Loss=1.0105944]\nTraining progress: 35%|███▌ | 350/1000 [05:35<09:15, 1.17it/s, Loss=1.0102142]\nTraining progress: 36%|███▌ | 360/1000 [05:35<09:04, 1.18it/s, Loss=1.0102142]\nTraining progress: 36%|███▌ | 360/1000 [05:44<09:04, 1.18it/s, Loss=1.0089403]\nTraining progress: 37%|███▋ | 370/1000 [05:44<08:59, 1.17it/s, Loss=1.0089403]\nTraining progress: 37%|███▋ | 370/1000 [05:52<08:59, 1.17it/s, Loss=1.0095749]\nTraining progress: 38%|███▊ | 380/1000 [05:52<08:44, 1.18it/s, Loss=1.0095749]\nTraining progress: 38%|███▊ | 380/1000 [06:00<08:44, 1.18it/s, Loss=1.0104323]\nTraining progress: 39%|███▉ | 390/1000 [06:00<08:28, 1.20it/s, Loss=1.0104323]\nTraining progress: 39%|███▉ | 390/1000 [06:09<08:28, 1.20it/s, Loss=1.0101397]\ntest views is in : ./output/Replicate/test_six_views/400_iteration [22/12 16:23:08]\n[ITER 400] Eval Done! [22/12 16:23:09]\nvideos is in : ./output/Replicate/videos/400_iteration [22/12 16:23:09]\nGenerating Video using 240 different view points[22/12 16:23:15]\n[ITER 400] Video Save Done! [22/12 16:23:18]\nTraining progress: 40%|████ | 400/1000 [06:09<08:33, 1.17it/s, Loss=1.0101397]\nTraining progress: 40%|████ | 400/1000 [06:27<08:33, 1.17it/s, Loss=1.0088887]\nTraining progress: 41%|████ | 410/1000 [06:27<11:11, 1.14s/it, Loss=1.0088887]\nTraining progress: 41%|████ | 410/1000 [06:36<11:11, 1.14s/it, Loss=1.0095410]\nTraining progress: 42%|████▏ | 420/1000 [06:36<10:23, 1.08s/it, Loss=1.0095410]\nTraining progress: 42%|████▏ | 420/1000 [06:45<10:23, 1.08s/it, Loss=1.0092835]\nTraining progress: 43%|████▎ | 430/1000 [06:45<09:41, 1.02s/it, Loss=1.0092835]\nTraining progress: 43%|████▎ | 430/1000 [06:54<09:41, 1.02s/it, Loss=1.0091632]\nTraining progress: 44%|████▍ | 440/1000 [06:54<09:09, 1.02it/s, Loss=1.0091632]\nTraining progress: 44%|████▍ | 440/1000 [07:03<09:09, 1.02it/s, Loss=1.0088365]\nTraining progress: 45%|████▌ | 450/1000 [07:03<08:45, 1.05it/s, Loss=1.0088365]\nTraining progress: 45%|████▌ | 450/1000 [07:11<08:45, 1.05it/s, Loss=1.0097462]\nTraining progress: 46%|████▌ | 460/1000 [07:11<08:13, 1.09it/s, Loss=1.0097462]\nTraining progress: 46%|████▌ | 460/1000 [07:19<08:13, 1.09it/s, Loss=1.0092854]\nTraining progress: 47%|████▋ | 470/1000 [07:19<07:49, 1.13it/s, Loss=1.0092854]\nTraining progress: 47%|████▋ | 470/1000 [07:28<07:49, 1.13it/s, Loss=1.0093460]\nTraining progress: 48%|████▊ | 480/1000 [07:28<07:39, 1.13it/s, Loss=1.0093460]\nTraining progress: 48%|████▊ | 480/1000 [07:37<07:39, 1.13it/s, Loss=1.0090952]\nscale up theta_range to: [60, 90] [22/12 16:24:43]\nscale up radius_range to: [4.9399999999999995, 5.225] [22/12 16:24:43]\nscale up phi_range to: [-180, 180] [22/12 16:24:43]\nscale up fovy_range to: [0.24, 0.6] [22/12 16:24:43]\nTraining progress: 49%|████▉ | 490/1000 [07:37<07:25, 1.14it/s, Loss=1.0090952]\nTraining progress: 49%|████▉ | 490/1000 [07:45<07:25, 1.14it/s, Loss=1.0091098]\n[ITER 500] Saving Gaussians [22/12 16:24:45]\nTraining progress: 50%|█████ | 500/1000 [07:45<07:20, 1.14it/s, Loss=1.0091098]\nTraining progress: 50%|█████ | 500/1000 [07:57<07:20, 1.14it/s, Loss=1.0093191]\nTraining progress: 51%|█████ | 510/1000 [07:57<07:47, 1.05it/s, Loss=1.0093191]\nTraining progress: 51%|█████ | 510/1000 [08:05<07:47, 1.05it/s, Loss=1.0097375]\nTraining progress: 52%|█████▏ | 520/1000 [08:05<07:20, 1.09it/s, Loss=1.0097375]\nTraining progress: 52%|█████▏ | 520/1000 [08:14<07:20, 1.09it/s, Loss=1.0100511]\nTraining progress: 53%|█████▎ | 530/1000 [08:14<07:02, 1.11it/s, Loss=1.0100511]\nTraining progress: 53%|█████▎ | 530/1000 [08:23<07:02, 1.11it/s, Loss=1.0102542]\nTraining progress: 54%|█████▍ | 540/1000 [08:23<06:58, 1.10it/s, Loss=1.0102542]\nTraining progress: 54%|█████▍ | 540/1000 [08:32<06:58, 1.10it/s, Loss=1.0098752]\nTraining progress: 55%|█████▌ | 550/1000 [08:32<06:42, 1.12it/s, Loss=1.0098752]\nTraining progress: 55%|█████▌ | 550/1000 [08:40<06:42, 1.12it/s, Loss=1.0098831]\nTraining progress: 56%|█████▌ | 560/1000 [08:40<06:26, 1.14it/s, Loss=1.0098831]\nTraining progress: 56%|█████▌ | 560/1000 [08:49<06:26, 1.14it/s, Loss=1.0099793]\nTraining progress: 57%|█████▋ | 570/1000 [08:49<06:14, 1.15it/s, Loss=1.0099793]\nTraining progress: 57%|█████▋ | 570/1000 [08:57<06:14, 1.15it/s, Loss=1.0098103]\nTraining progress: 58%|█████▊ | 580/1000 [08:57<06:02, 1.16it/s, Loss=1.0098103]\nTraining progress: 58%|█████▊ | 580/1000 [09:06<06:02, 1.16it/s, Loss=1.0090983]\nTraining progress: 59%|█████▉ | 590/1000 [09:06<05:56, 1.15it/s, Loss=1.0090983]\nTraining progress: 59%|█████▉ | 590/1000 [09:15<05:56, 1.15it/s, Loss=1.0095025]\ntest views is in : ./output/Replicate/test_six_views/600_iteration [22/12 16:26:14]\n[ITER 600] Eval Done! [22/12 16:26:15]\nvideos is in : ./output/Replicate/videos/600_iteration[22/12 16:26:15]\nGenerating Video using 240 different view points[22/12 16:26:21]\n[ITER 600] Video Save Done! [22/12 16:26:24]\nTraining progress: 60%|██████ | 600/1000 [09:15<05:55, 1.13it/s, Loss=1.0095025]\nTraining progress: 60%|██████ | 600/1000 [09:34<05:55, 1.13it/s, Loss=1.0120878]\nTraining progress: 61%|██████ | 610/1000 [09:34<07:41, 1.18s/it, Loss=1.0120878]\nTraining progress: 61%|██████ | 610/1000 [09:43<07:41, 1.18s/it, Loss=1.0099001]\nTraining progress: 62%|██████▏ | 620/1000 [09:43<06:56, 1.10s/it, Loss=1.0099001]\nTraining progress: 62%|██████▏ | 620/1000 [09:51<06:56, 1.10s/it, Loss=1.0100498]\nTraining progress: 63%|██████▎ | 630/1000 [09:51<06:19, 1.03s/it, Loss=1.0100498]\nTraining progress: 63%|██████▎ | 630/1000 [10:01<06:19, 1.03s/it, Loss=1.0104325]\nTraining progress: 64%|██████▍ | 640/1000 [10:01<06:01, 1.01s/it, Loss=1.0104325]\nTraining progress: 64%|██████▍ | 640/1000 [10:10<06:01, 1.01s/it, Loss=1.0113608]\nTraining progress: 65%|██████▌ | 650/1000 [10:10<05:38, 1.03it/s, Loss=1.0113608]\nTraining progress: 65%|██████▌ | 650/1000 [10:19<05:38, 1.03it/s, Loss=1.0094696]\nTraining progress: 66%|██████▌ | 660/1000 [10:19<05:19, 1.06it/s, Loss=1.0094696]\nTraining progress: 66%|██████▌ | 660/1000 [10:27<05:19, 1.06it/s, Loss=1.0095921]\nTraining progress: 67%|██████▋ | 670/1000 [10:27<05:04, 1.08it/s, Loss=1.0095921]\nTraining progress: 67%|██████▋ | 670/1000 [10:36<05:04, 1.08it/s, Loss=1.0090344]\nTraining progress: 68%|██████▊ | 680/1000 [10:36<04:49, 1.11it/s, Loss=1.0090344]\nTraining progress: 68%|██████▊ | 680/1000 [10:45<04:49, 1.11it/s, Loss=1.0103945]\nTraining progress: 69%|██████▉ | 690/1000 [10:45<04:35, 1.12it/s, Loss=1.0103945]\nTraining progress: 69%|██████▉ | 690/1000 [10:54<04:35, 1.12it/s, Loss=1.0091865]\nTraining progress: 70%|███████ | 700/1000 [10:54<04:32, 1.10it/s, Loss=1.0091865]\nTraining progress: 70%|███████ | 700/1000 [11:02<04:32, 1.10it/s, Loss=1.0109836]\nTraining progress: 71%|███████ | 710/1000 [11:02<04:17, 1.13it/s, Loss=1.0109836]\nTraining progress: 71%|███████ | 710/1000 [11:11<04:17, 1.13it/s, Loss=1.0101475]\nTraining progress: 72%|███████▏ | 720/1000 [11:11<04:08, 1.13it/s, Loss=1.0101475]\nTraining progress: 72%|███████▏ | 720/1000 [11:20<04:08, 1.13it/s, Loss=1.0097659]\nTraining progress: 73%|███████▎ | 730/1000 [11:20<04:01, 1.12it/s, Loss=1.0097659]\nTraining progress: 73%|███████▎ | 730/1000 [11:29<04:01, 1.12it/s, Loss=1.0101017]\nTraining progress: 74%|███████▍ | 740/1000 [11:29<03:51, 1.12it/s, Loss=1.0101017]\nTraining progress: 74%|███████▍ | 740/1000 [11:37<03:51, 1.12it/s, Loss=1.0095184]\nTraining progress: 75%|███████▌ | 750/1000 [11:37<03:37, 1.15it/s, Loss=1.0095184]\nTraining progress: 75%|███████▌ | 750/1000 [11:47<03:37, 1.15it/s, Loss=1.0111929]\nTraining progress: 76%|███████▌ | 760/1000 [11:47<03:33, 1.12it/s, Loss=1.0111929]\nTraining progress: 76%|███████▌ | 760/1000 [11:55<03:33, 1.12it/s, Loss=1.0105028]\nTraining progress: 77%|███████▋ | 770/1000 [11:55<03:21, 1.14it/s, Loss=1.0105028]\nTraining progress: 77%|███████▋ | 770/1000 [12:04<03:21, 1.14it/s, Loss=1.0102045]\nTraining progress: 78%|███████▊ | 780/1000 [12:04<03:10, 1.16it/s, Loss=1.0102045]\nTraining progress: 78%|███████▊ | 780/1000 [12:12<03:10, 1.16it/s, Loss=1.0098310]\nTraining progress: 79%|███████▉ | 790/1000 [12:12<03:01, 1.16it/s, Loss=1.0098310]\nTraining progress: 79%|███████▉ | 790/1000 [12:22<03:01, 1.16it/s, Loss=1.0101976]\ntest views is in : ./output/Replicate/test_six_views/800_iteration [22/12 16:29:21]\n[ITER 800] Eval Done! [22/12 16:29:22]\nvideos is in : ./output/Replicate/videos/800_iteration [22/12 16:29:22]\nGenerating Video using 240 different view points[22/12 16:29:28]\n[ITER 800] Video Save Done! [22/12 16:29:31]\nTraining progress: 80%|████████ | 800/1000 [12:22<02:57, 1.12it/s, Loss=1.0101976]\nTraining progress: 80%|████████ | 800/1000 [12:41<02:57, 1.12it/s, Loss=1.0115836]\nTraining progress: 81%|████████ | 810/1000 [12:41<03:45, 1.19s/it, Loss=1.0115836]\nTraining progress: 81%|████████ | 810/1000 [12:50<03:45, 1.19s/it, Loss=1.0098869]\nTraining progress: 82%|████████▏ | 820/1000 [12:50<03:18, 1.10s/it, Loss=1.0098869]\nTraining progress: 82%|████████▏ | 820/1000 [12:59<03:18, 1.10s/it, Loss=1.0102600]\nTraining progress: 83%|████████▎ | 830/1000 [12:59<02:57, 1.05s/it, Loss=1.0102600]\nTraining progress: 83%|████████▎ | 830/1000 [13:08<02:57, 1.05s/it, Loss=1.0097042]\nTraining progress: 84%|████████▍ | 840/1000 [13:08<02:39, 1.01it/s, Loss=1.0097042]\nTraining progress: 84%|████████▍ | 840/1000 [13:16<02:39, 1.01it/s, Loss=1.0103961]\nTraining progress: 85%|████████▌ | 850/1000 [13:16<02:24, 1.04it/s, Loss=1.0103961]\nTraining progress: 85%|████████▌ | 850/1000 [13:26<02:24, 1.04it/s, Loss=1.0108702]\nTraining progress: 86%|████████▌ | 860/1000 [13:26<02:13, 1.05it/s, Loss=1.0108702]\nTraining progress: 86%|████████▌ | 860/1000 [13:34<02:13, 1.05it/s, Loss=1.0092877]\nTraining progress: 87%|████████▋ | 870/1000 [13:34<02:00, 1.07it/s, Loss=1.0092877]\nTraining progress: 87%|████████▋ | 870/1000 [13:43<02:00, 1.07it/s, Loss=1.0103984]\nTraining progress: 88%|████████▊ | 880/1000 [13:43<01:49, 1.10it/s, Loss=1.0103984]\nTraining progress: 88%|████████▊ | 880/1000 [13:52<01:49, 1.10it/s, Loss=1.0098017]\nTraining progress: 89%|████████▉ | 890/1000 [13:52<01:39, 1.11it/s, Loss=1.0098017]\nTraining progress: 89%|████████▉ | 890/1000 [14:01<01:39, 1.11it/s, Loss=1.0112966]\nTraining progress: 90%|█████████ | 900/1000 [14:01<01:31, 1.09it/s, Loss=1.0112966]\nTraining progress: 90%|█████████ | 900/1000 [14:11<01:31, 1.09it/s, Loss=1.0114046]\nTraining progress: 91%|█████████ | 910/1000 [14:11<01:22, 1.09it/s, Loss=1.0114046]\nTraining progress: 91%|█████████ | 910/1000 [14:20<01:22, 1.09it/s, Loss=1.0115868]\nTraining progress: 92%|█████████▏| 920/1000 [14:20<01:12, 1.10it/s, Loss=1.0115868]\nTraining progress: 92%|█████████▏| 920/1000 [14:29<01:12, 1.10it/s, Loss=1.0097545]\nTraining progress: 93%|█████████▎| 930/1000 [14:29<01:03, 1.10it/s, Loss=1.0097545]\nTraining progress: 93%|█████████▎| 930/1000 [14:37<01:03, 1.10it/s, Loss=1.0098565]\nTraining progress: 94%|█████████▍| 940/1000 [14:37<00:53, 1.12it/s, Loss=1.0098565]\nTraining progress: 94%|█████████▍| 940/1000 [14:46<00:53, 1.12it/s, Loss=1.0107825]\nTraining progress: 95%|█████████▌| 950/1000 [14:46<00:43, 1.14it/s, Loss=1.0107825]\nTraining progress: 95%|█████████▌| 950/1000 [14:54<00:43, 1.14it/s, Loss=1.0096509]\nTraining progress: 96%|█████████▌| 960/1000 [14:54<00:34, 1.14it/s, Loss=1.0096509]\nTraining progress: 96%|█████████▌| 960/1000 [15:04<00:34, 1.14it/s, Loss=1.0093848]\nTraining progress: 97%|█████████▋| 970/1000 [15:04<00:26, 1.12it/s, Loss=1.0093848]\nTraining progress: 97%|█████████▋| 970/1000 [15:13<00:26, 1.12it/s, Loss=1.0099435]\nTraining progress: 98%|█████████▊| 980/1000 [15:13<00:17, 1.12it/s, Loss=1.0099435]\nTraining progress: 98%|█████████▊| 980/1000 [15:21<00:17, 1.12it/s, Loss=1.0103432]\nscale up theta_range to: [60, 90][22/12 16:32:28]\nscale up radius_range to: [4.693, 5.0] [22/12 16:32:28]\nscale up phi_range to: [-180, 180] [22/12 16:32:28]\nscale up fovy_range to: [0.18, 0.6] [22/12 16:32:28]\nTraining progress: 99%|█████████▉| 990/1000 [15:21<00:08, 1.13it/s, Loss=1.0103432]\nTraining progress: 99%|█████████▉| 990/1000 [15:31<00:08, 1.13it/s, Loss=1.0096740]\nTraining progress: 100%|██████████| 1000/1000 [15:31<00:00, 1.11it/s, Loss=1.0096740]\nTraining progress: 100%|██████████| 1000/1000 [15:31<00:00, 1.07it/s, Loss=1.0096740]\ntest views is in : ./output/Replicate/test_six_views/1000_iteration[22/12 16:32:30]\n[ITER 1000] Eval Done! [22/12 16:32:31]\nvideos is in : ./output/Replicate/videos/1000_iteration [22/12 16:32:31]\nGenerating Video using 240 different view points[22/12 16:32:37]\n[ITER 1000] Video Save Done! [22/12 16:32:42]\n[ITER 1000] Saving Gaussians [22/12 16:32:42]\nTraining complete.[22/12 16:32:52]", "metrics": { "predict_time": 1004.990021, "total_time": 1104.809692 }, "output": [ "https://replicate.delivery/pbxt/dGlbDMx6U2LGJxucqINW2G8IwyjmnsEEC2IJdwsVxbkNsNhE/video_rgb_1000.mp4", "https://replicate.delivery/pbxt/abd77ehLGfiKvENIKMkoPsKgLUEJwnW9MXY48MFhr6l3w2ESA/video_rgb.mp4" ], "started_at": "2023-12-22T16:16:10.497723Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/3atbyrtb3q54kierm4sx5u3bsa", "cancel": "https://api.replicate.com/v1/predictions/3atbyrtb3q54kierm4sx5u3bsa/cancel" }, "version": "fbf8e0dfef4ca0c0de45cf1afbf12c81667ee29fd79852852262aee4f167fbf5" }Generated inUsing seed: 2212729883 Test iter: [1, 200, 400, 600, 800, 1000] Save iter: [500, 1000] Optimizing Output folder: ./output/Replicate [22/12 16:16:11] Tensorboard not available: not logging progress [22/12 16:16:11] Reading Test Transforms [22/12 16:16:11] creating base model...[22/12 16:16:12] 0%| | 0.00/890M [00:00<?, ?iB/s] 1%|▍ | 10.9M/890M [00:00<00:08, 115MiB/s] 3%|▉ | 22.7M/890M [00:00<00:07, 120MiB/s] 4%|█▍ | 34.2M/890M [00:00<00:07, 114MiB/s] 5%|█▉ | 45.1M/890M [00:00<00:08, 106MiB/s] 6%|██▌ | 57.7M/890M [00:00<00:07, 115MiB/s] 8%|███ | 68.7M/890M [00:00<00:07, 111MiB/s] 9%|███▍ | 79.4M/890M [00:00<00:07, 111MiB/s] 10%|███▉ | 90.0M/890M [00:00<00:07, 110MiB/s] 12%|████▋ | 103M/890M [00:00<00:07, 118MiB/s] 13%|█████▏ | 115M/890M [00:01<00:06, 120MiB/s] 14%|█████▋ | 127M/890M [00:01<00:06, 123MiB/s] 16%|██████▎ | 140M/890M [00:01<00:06, 125MiB/s] 17%|██████▊ | 152M/890M [00:01<00:06, 114MiB/s] 18%|███████▎ | 163M/890M [00:01<00:07, 107MiB/s] 19%|███████▊ | 173M/890M [00:01<00:07, 106MiB/s] 21%|████████▎ | 184M/890M [00:01<00:06, 109MiB/s] 22%|████████▊ | 195M/890M [00:01<00:06, 109MiB/s] 23%|█████████▏ | 205M/890M [00:01<00:07, 100MiB/s] 24%|█████████▍ | 215M/890M [00:02<00:07, 97.7MiB/s] 25%|█████████▊ | 224M/890M [00:02<00:07, 97.0MiB/s] 27%|██████████▌ | 236M/890M [00:02<00:06, 104MiB/s] 28%|███████████ | 247M/890M [00:02<00:06, 105MiB/s] 29%|███████████▌ | 257M/890M [00:02<00:06, 101MiB/s] 30%|████████████ | 267M/890M [00:02<00:06, 104MiB/s] 31%|████████████▌ | 279M/890M [00:02<00:05, 109MiB/s] 33%|█████████████ | 290M/890M [00:02<00:05, 107MiB/s] 34%|█████████████▌ | 301M/890M [00:02<00:05, 109MiB/s] 35%|██████████████ | 312M/890M [00:02<00:05, 113MiB/s] 36%|██████████████▌ | 323M/890M [00:03<00:05, 108MiB/s] 38%|███████████████ | 334M/890M [00:03<00:05, 111MiB/s] 39%|███████████████▌ | 345M/890M [00:03<00:05, 107MiB/s] 40%|███████████████▉ | 356M/890M [00:03<00:05, 108MiB/s] 41%|████████████████▌ | 367M/890M [00:03<00:04, 112MiB/s] 42%|████████████████▉ | 378M/890M [00:03<00:04, 109MiB/s] 44%|█████████████████▍ | 388M/890M [00:03<00:04, 108MiB/s] 45%|██████████████████ | 400M/890M [00:03<00:04, 113MiB/s] 46%|██████████████████▌ | 412M/890M [00:03<00:04, 115MiB/s] 48%|███████████████████ | 424M/890M [00:04<00:04, 118MiB/s] 49%|███████████████████▌ | 435M/890M [00:04<00:04, 114MiB/s] 50%|████████████████████ | 447M/890M [00:04<00:04, 114MiB/s] 51%|████████████████████▌ | 458M/890M [00:04<00:04, 101MiB/s] 53%|█████████████████████ | 468M/890M [00:04<00:04, 100MiB/s] 54%|█████████████████████▍ | 478M/890M [00:04<00:04, 101MiB/s] 55%|█████████████████████▎ | 488M/890M [00:04<00:04, 93.0MiB/s] 56%|█████████████████████▊ | 498M/890M [00:04<00:04, 97.1MiB/s] 57%|██████████████████████▏ | 507M/890M [00:04<00:04, 94.1MiB/s] 58%|██████████████████████▋ | 516M/890M [00:05<00:04, 88.4MiB/s] 59%|███████████████████████ | 527M/890M [00:05<00:04, 93.4MiB/s] 60%|███████████████████████▌ | 537M/890M [00:05<00:03, 96.0MiB/s] 62%|████████████████████████▋ | 548M/890M [00:05<00:03, 102MiB/s] 63%|█████████████████████████▏ | 560M/890M [00:05<00:03, 111MiB/s] 64%|█████████████████████████▋ | 572M/890M [00:05<00:02, 115MiB/s] 66%|██████████████████████████▏ | 584M/890M [00:05<00:02, 116MiB/s] 67%|██████████████████████████▋ | 595M/890M [00:05<00:02, 111MiB/s] 68%|███████████████████████████▏ | 605M/890M [00:05<00:02, 109MiB/s] 69%|███████████████████████████▋ | 616M/890M [00:06<00:02, 108MiB/s] 70%|████████████████████████████▏ | 627M/890M [00:06<00:02, 110MiB/s] 72%|████████████████████████████▋ | 639M/890M [00:06<00:02, 113MiB/s] 73%|█████████████████████████████▏ | 650M/890M [00:06<00:02, 110MiB/s] 74%|█████████████████████████████▋ | 660M/890M [00:06<00:02, 110MiB/s] 75%|██████████████████████████████▏ | 671M/890M [00:06<00:02, 102MiB/s] 76%|█████████████████████████████▊ | 680M/890M [00:06<00:02, 99.7MiB/s] 78%|███████████████████████████████ | 691M/890M [00:06<00:02, 104MiB/s] 79%|███████████████████████████████▋ | 704M/890M [00:06<00:01, 112MiB/s] 81%|████████████████████████████████▎ | 718M/890M [00:06<00:01, 120MiB/s] 82%|████████████████████████████████▊ | 729M/890M [00:07<00:01, 117MiB/s] 83%|█████████████████████████████████▎ | 741M/890M [00:07<00:01, 118MiB/s] 85%|█████████████████████████████████▊ | 752M/890M [00:07<00:01, 118MiB/s] 86%|██████████████████████████████████▎ | 763M/890M [00:07<00:01, 116MiB/s] 87%|██████████████████████████████████▊ | 775M/890M [00:07<00:01, 118MiB/s] 88%|███████████████████████████████████▎ | 786M/890M [00:07<00:00, 111MiB/s] 90%|███████████████████████████████████▊ | 797M/890M [00:07<00:00, 110MiB/s] 91%|████████████████████████████████████▎ | 808M/890M [00:07<00:00, 112MiB/s] 92%|████████████████████████████████████▊ | 819M/890M [00:07<00:00, 112MiB/s] 93%|█████████████████████████████████████▎ | 830M/890M [00:08<00:00, 114MiB/s] 95%|█████████████████████████████████████▊ | 841M/890M [00:08<00:00, 111MiB/s] 96%|██████████████████████████████████████▍ | 854M/890M [00:08<00:00, 119MiB/s] 97%|██████████████████████████████████████▉ | 866M/890M [00:08<00:00, 120MiB/s] 99%|███████████████████████████████████████▍| 878M/890M [00:08<00:00, 120MiB/s] 100%|███████████████████████████████████████▉| 890M/890M [00:08<00:00, 121MiB/s] 100%|████████████████████████████████████████| 890M/890M [00:08<00:00, 110MiB/s] creating upsample model... [22/12 16:16:28] downloading base checkpoint... [22/12 16:16:33] 0%| | 0.00/161M [00:00<?, ?iB/s] 6%|▌ | 9.18M/161M [00:00<00:01, 90.8MiB/s] 11%|█▏ | 18.3M/161M [00:00<00:01, 74.8MiB/s] 16%|█▌ | 26.2M/161M [00:00<00:01, 76.4MiB/s] 21%|██ | 34.0M/161M [00:00<00:01, 76.3MiB/s] 26%|██▌ | 42.3M/161M [00:00<00:01, 78.6MiB/s] 31%|███ | 50.3M/161M [00:00<00:01, 78.7MiB/s] 37%|███▋ | 59.1M/161M [00:00<00:01, 81.6MiB/s] 42%|████▏ | 67.4M/161M [00:00<00:01, 81.8MiB/s] 47%|████▋ | 76.0M/161M [00:00<00:01, 82.6MiB/s] 52%|█████▏ | 84.2M/161M [00:01<00:00, 80.5MiB/s] 57%|█████▋ | 92.3M/161M [00:01<00:00, 75.6MiB/s] 62%|██████▏ | 99.9M/161M [00:01<00:00, 73.4MiB/s] 68%|██████▊ | 109M/161M [00:01<00:00, 77.9MiB/s] 73%|███████▎ | 117M/161M [00:01<00:00, 78.7MiB/s] 78%|███████▊ | 126M/161M [00:01<00:00, 81.0MiB/s] 83%|████████▎ | 134M/161M [00:01<00:00, 73.2MiB/s] 88%|████████▊ | 141M/161M [00:01<00:00, 68.7MiB/s] 92%|█████████▏| 149M/161M [00:01<00:00, 70.8MiB/s] 97%|█████████▋| 157M/161M [00:02<00:00, 71.5MiB/s] 100%|██████████| 161M/161M [00:02<00:00, 76.3MiB/s] downloading upsampler checkpoint... [22/12 16:16:35] 0%| | 0.00/162M [00:00<?, ?iB/s] 6%|▌ | 8.98M/162M [00:00<00:01, 84.4MiB/s] 11%|█ | 17.7M/162M [00:00<00:01, 85.6MiB/s] 16%|█▌ | 26.3M/162M [00:00<00:01, 68.1MiB/s] 21%|██▏ | 34.6M/162M [00:00<00:01, 72.9MiB/s] 26%|██▋ | 42.8M/162M [00:00<00:01, 76.0MiB/s] 31%|███▏ | 50.7M/162M [00:00<00:01, 72.0MiB/s] 36%|███▋ | 58.7M/162M [00:00<00:01, 74.6MiB/s] 41%|████ | 66.3M/162M [00:00<00:01, 73.9MiB/s] 46%|████▋ | 75.0M/162M [00:00<00:01, 77.9MiB/s] 51%|█████ | 82.9M/162M [00:01<00:01, 76.4MiB/s] 56%|█████▋ | 91.5M/162M [00:01<00:00, 79.1MiB/s] 61%|██████▏ | 99.4M/162M [00:01<00:00, 76.0MiB/s] 66%|██████▌ | 107M/162M [00:01<00:00, 75.1MiB/s] 71%|███████ | 115M/162M [00:01<00:00, 72.0MiB/s] 75%|███████▌ | 122M/162M [00:01<00:00, 67.8MiB/s] 79%|███████▉ | 129M/162M [00:01<00:00, 65.5MiB/s] 84%|████████▎ | 136M/162M [00:01<00:00, 66.2MiB/s] 89%|████████▉ | 144M/162M [00:01<00:00, 70.9MiB/s] 94%|█████████▍| 153M/162M [00:02<00:00, 76.2MiB/s] 99%|█████████▉| 160M/162M [00:02<00:00, 62.2MiB/s] 100%|██████████| 162M/162M [00:02<00:00, 71.7MiB/s] 0it [00:00, ?it/s] 1it [00:01, 1.13s/it] 4it [00:01, 3.98it/s] 7it [00:01, 7.11it/s] 10it [00:01, 10.06it/s] 13it [00:01, 12.68it/s] 16it [00:01, 14.89it/s] 19it [00:01, 16.66it/s] 22it [00:02, 18.06it/s] 25it [00:02, 19.11it/s] 28it [00:02, 19.89it/s] 31it [00:02, 20.46it/s] 34it [00:02, 20.85it/s] 37it [00:02, 21.15it/s] 40it [00:02, 21.35it/s] 43it [00:03, 21.48it/s] 46it [00:03, 21.57it/s] 49it [00:03, 21.63it/s] 52it [00:03, 21.66it/s] 55it [00:03, 21.69it/s] 58it [00:03, 21.74it/s] 61it [00:03, 21.78it/s] 64it [00:04, 21.79it/s] 67it [00:04, 16.75it/s] 69it [00:04, 11.47it/s] 71it [00:05, 9.06it/s] 73it [00:05, 7.75it/s] 74it [00:05, 7.28it/s] 75it [00:05, 6.86it/s] 76it [00:05, 6.51it/s] 77it [00:06, 6.23it/s] 78it [00:06, 6.03it/s] 79it [00:06, 5.87it/s] 80it [00:06, 5.76it/s] 81it [00:06, 5.68it/s] 82it [00:07, 5.62it/s] 83it [00:07, 5.58it/s] 84it [00:07, 5.54it/s] 85it [00:07, 5.52it/s] 86it [00:07, 5.50it/s] 87it [00:07, 5.50it/s] 88it [00:08, 5.49it/s] 89it [00:08, 5.48it/s] 90it [00:08, 5.48it/s] 91it [00:08, 5.48it/s] 92it [00:08, 5.47it/s] 93it [00:09, 5.47it/s] 94it [00:09, 5.47it/s] 95it [00:09, 5.47it/s] 96it [00:09, 5.46it/s] 97it [00:09, 5.45it/s] 98it [00:09, 5.45it/s] 99it [00:10, 5.46it/s] 100it [00:10, 5.46it/s] 101it [00:10, 5.46it/s] 102it [00:10, 5.45it/s] 103it [00:10, 5.45it/s] 104it [00:11, 5.42it/s] 105it [00:11, 5.44it/s] 106it [00:11, 5.45it/s] 107it [00:11, 5.44it/s] 108it [00:11, 5.44it/s] 109it [00:11, 5.44it/s] 110it [00:12, 5.43it/s] 111it [00:12, 5.43it/s] 112it [00:12, 5.43it/s] 113it [00:12, 5.43it/s] 114it [00:12, 5.43it/s] 115it [00:13, 5.42it/s] 116it [00:13, 5.42it/s] 117it [00:13, 5.42it/s] 118it [00:13, 5.42it/s] 119it [00:13, 5.42it/s] 120it [00:14, 5.42it/s] 121it [00:14, 5.41it/s] 122it [00:14, 5.42it/s] 123it [00:14, 5.42it/s] 124it [00:14, 5.42it/s] 125it [00:14, 5.42it/s] 126it [00:15, 5.42it/s] 127it [00:15, 5.42it/s] 128it [00:15, 5.42it/s] 129it [00:15, 5.42it/s] 130it [00:15, 8.29it/s] Generating random point cloud (81920)... [22/12 16:16:53] Number of points at initialisation : 81920 [22/12 16:16:54] train_process is in : ./output/Replicate/train_process/ [22/12 16:16:54] [INFO] loading stable diffusion... [22/12 16:16:57] [INFO] loaded stable diffusion! [22/12 16:16:59] test views is in : ./output/Replicate/test_six_views/1_iteration [22/12 16:17:15] [ITER 1] Eval Done! [22/12 16:17:15] videos is in : ./output/Replicate/videos/1_iteration [22/12 16:17:15] Generating Video using 240 different view points[22/12 16:17:21] [ITER 1] Video Save Done! [22/12 16:17:24] Training progress: 0%| | 0/1000 [00:00<?, ?it/s] Training progress: 0%| | 0/1000 [00:32<?, ?it/s, Loss=1.0017186] Training progress: 1%| | 10/1000 [00:32<53:16, 3.23s/it, Loss=1.0017186] Training progress: 1%| | 10/1000 [00:40<53:16, 3.23s/it, Loss=1.0077757] Training progress: 2%|▏ | 20/1000 [00:40<29:57, 1.83s/it, Loss=1.0077757] Training progress: 2%|▏ | 20/1000 [00:49<29:57, 1.83s/it, Loss=1.0079711] Training progress: 3%|▎ | 30/1000 [00:49<22:13, 1.37s/it, Loss=1.0079711] Training progress: 3%|▎ | 30/1000 [00:57<22:13, 1.37s/it, Loss=1.0078438] Training progress: 4%|▍ | 40/1000 [00:57<18:36, 1.16s/it, Loss=1.0078438] Training progress: 4%|▍ | 40/1000 [01:05<18:36, 1.16s/it, Loss=1.0082182] Training progress: 5%|▌ | 50/1000 [01:05<16:07, 1.02s/it, Loss=1.0082182] Training progress: 5%|▌ | 50/1000 [01:13<16:07, 1.02s/it, Loss=1.0086312] Training progress: 6%|▌ | 60/1000 [01:13<14:56, 1.05it/s, Loss=1.0086312] Training progress: 6%|▌ | 60/1000 [01:21<14:56, 1.05it/s, Loss=1.0084402] Training progress: 7%|▋ | 70/1000 [01:21<14:01, 1.11it/s, Loss=1.0084402] Training progress: 7%|▋ | 70/1000 [01:29<14:01, 1.11it/s, Loss=1.0085526] Training progress: 8%|▊ | 80/1000 [01:29<13:33, 1.13it/s, Loss=1.0085526] Training progress: 8%|▊ | 80/1000 [01:38<13:33, 1.13it/s, Loss=1.0085533] Training progress: 9%|▉ | 90/1000 [01:38<13:09, 1.15it/s, Loss=1.0085533] Training progress: 9%|▉ | 90/1000 [01:48<13:09, 1.15it/s, Loss=1.0085533] Training progress: 10%|█ | 100/1000 [01:48<13:34, 1.11it/s, Loss=1.0085533] Training progress: 10%|█ | 100/1000 [01:56<13:34, 1.11it/s, Loss=1.0088473] Training progress: 11%|█ | 110/1000 [01:56<12:57, 1.15it/s, Loss=1.0088473] Training progress: 11%|█ | 110/1000 [02:04<12:57, 1.15it/s, Loss=1.0088198] Training progress: 12%|█▏ | 120/1000 [02:04<12:33, 1.17it/s, Loss=1.0088198] Training progress: 12%|█▏ | 120/1000 [02:12<12:33, 1.17it/s, Loss=1.0089299] Training progress: 13%|█▎ | 130/1000 [02:12<12:04, 1.20it/s, Loss=1.0089299] Training progress: 13%|█▎ | 130/1000 [02:20<12:04, 1.20it/s, Loss=1.0090425] Training progress: 14%|█▍ | 140/1000 [02:20<11:48, 1.21it/s, Loss=1.0090425] Training progress: 14%|█▍ | 140/1000 [02:28<11:48, 1.21it/s, Loss=1.0093045] Training progress: 15%|█▌ | 150/1000 [02:28<11:36, 1.22it/s, Loss=1.0093045] Training progress: 15%|█▌ | 150/1000 [02:36<11:36, 1.22it/s, Loss=1.0089162] Training progress: 16%|█▌ | 160/1000 [02:36<11:19, 1.24it/s, Loss=1.0089162] Training progress: 16%|█▌ | 160/1000 [02:44<11:19, 1.24it/s, Loss=1.0091812] Training progress: 17%|█▋ | 170/1000 [02:44<11:13, 1.23it/s, Loss=1.0091812] Training progress: 17%|█▋ | 170/1000 [02:52<11:13, 1.23it/s, Loss=1.0082853] Training progress: 18%|█▊ | 180/1000 [02:52<11:06, 1.23it/s, Loss=1.0082853] Training progress: 18%|█▊ | 180/1000 [03:00<11:06, 1.23it/s, Loss=1.0082300] Training progress: 19%|█▉ | 190/1000 [03:00<10:48, 1.25it/s, Loss=1.0082300] Training progress: 19%|█▉ | 190/1000 [03:09<10:48, 1.25it/s, Loss=1.0085656] test views is in : ./output/Replicate/test_six_views/200_iteration[22/12 16:20:08] [ITER 200] Eval Done! [22/12 16:20:09] videos is in : ./output/Replicate/videos/200_iteration[22/12 16:20:09] Generating Video using 240 different view points[22/12 16:20:15] [ITER 200] Video Save Done! [22/12 16:20:17] Training progress: 20%|██ | 200/1000 [03:09<11:08, 1.20it/s, Loss=1.0085656] Training progress: 20%|██ | 200/1000 [03:27<11:08, 1.20it/s, Loss=1.0087679] Training progress: 21%|██ | 210/1000 [03:27<14:44, 1.12s/it, Loss=1.0087679] Training progress: 21%|██ | 210/1000 [03:35<14:44, 1.12s/it, Loss=1.0089540] Training progress: 22%|██▏ | 220/1000 [03:35<13:32, 1.04s/it, Loss=1.0089540] Training progress: 22%|██▏ | 220/1000 [03:44<13:32, 1.04s/it, Loss=1.0088401] Training progress: 23%|██▎ | 230/1000 [03:44<12:39, 1.01it/s, Loss=1.0088401] Training progress: 23%|██▎ | 230/1000 [03:52<12:39, 1.01it/s, Loss=1.0080839] Training progress: 24%|██▍ | 240/1000 [03:52<12:04, 1.05it/s, Loss=1.0080839] Training progress: 24%|██▍ | 240/1000 [04:01<12:04, 1.05it/s, Loss=1.0084546] Training progress: 25%|██▌ | 250/1000 [04:01<11:26, 1.09it/s, Loss=1.0084546] Training progress: 25%|██▌ | 250/1000 [04:09<11:26, 1.09it/s, Loss=1.0087927] Training progress: 26%|██▌ | 260/1000 [04:09<10:56, 1.13it/s, Loss=1.0087927] Training progress: 26%|██▌ | 260/1000 [04:17<10:56, 1.13it/s, Loss=1.0085855] Training progress: 27%|██▋ | 270/1000 [04:17<10:30, 1.16it/s, Loss=1.0085855] Training progress: 27%|██▋ | 270/1000 [04:26<10:30, 1.16it/s, Loss=1.0083972] Training progress: 28%|██▊ | 280/1000 [04:26<10:20, 1.16it/s, Loss=1.0083972] Training progress: 28%|██▊ | 280/1000 [04:34<10:20, 1.16it/s, Loss=1.0090715] Training progress: 29%|██▉ | 290/1000 [04:34<10:08, 1.17it/s, Loss=1.0090715] Training progress: 29%|██▉ | 290/1000 [04:44<10:08, 1.17it/s, Loss=1.0085778] Training progress: 30%|███ | 300/1000 [04:44<10:18, 1.13it/s, Loss=1.0085778] Training progress: 30%|███ | 300/1000 [04:52<10:18, 1.13it/s, Loss=1.0078171] Training progress: 31%|███ | 310/1000 [04:52<09:56, 1.16it/s, Loss=1.0078171] Training progress: 31%|███ | 310/1000 [05:01<09:56, 1.16it/s, Loss=1.0089422] Training progress: 32%|███▏ | 320/1000 [05:01<10:04, 1.12it/s, Loss=1.0089422] Training progress: 32%|███▏ | 320/1000 [05:10<10:04, 1.12it/s, Loss=1.0096785] Training progress: 33%|███▎ | 330/1000 [05:10<09:47, 1.14it/s, Loss=1.0096785] Training progress: 33%|███▎ | 330/1000 [05:18<09:47, 1.14it/s, Loss=1.0101533] Training progress: 34%|███▍ | 340/1000 [05:18<09:31, 1.15it/s, Loss=1.0101533] Training progress: 34%|███▍ | 340/1000 [05:26<09:31, 1.15it/s, Loss=1.0105944] Training progress: 35%|███▌ | 350/1000 [05:26<09:15, 1.17it/s, Loss=1.0105944] Training progress: 35%|███▌ | 350/1000 [05:35<09:15, 1.17it/s, Loss=1.0102142] Training progress: 36%|███▌ | 360/1000 [05:35<09:04, 1.18it/s, Loss=1.0102142] Training progress: 36%|███▌ | 360/1000 [05:44<09:04, 1.18it/s, Loss=1.0089403] Training progress: 37%|███▋ | 370/1000 [05:44<08:59, 1.17it/s, Loss=1.0089403] Training progress: 37%|███▋ | 370/1000 [05:52<08:59, 1.17it/s, Loss=1.0095749] Training progress: 38%|███▊ | 380/1000 [05:52<08:44, 1.18it/s, Loss=1.0095749] Training progress: 38%|███▊ | 380/1000 [06:00<08:44, 1.18it/s, Loss=1.0104323] Training progress: 39%|███▉ | 390/1000 [06:00<08:28, 1.20it/s, Loss=1.0104323] Training progress: 39%|███▉ | 390/1000 [06:09<08:28, 1.20it/s, Loss=1.0101397] test views is in : ./output/Replicate/test_six_views/400_iteration [22/12 16:23:08] [ITER 400] Eval Done! [22/12 16:23:09] videos is in : ./output/Replicate/videos/400_iteration [22/12 16:23:09] Generating Video using 240 different view points[22/12 16:23:15] [ITER 400] Video Save Done! [22/12 16:23:18] Training progress: 40%|████ | 400/1000 [06:09<08:33, 1.17it/s, Loss=1.0101397] Training progress: 40%|████ | 400/1000 [06:27<08:33, 1.17it/s, Loss=1.0088887] Training progress: 41%|████ | 410/1000 [06:27<11:11, 1.14s/it, Loss=1.0088887] Training progress: 41%|████ | 410/1000 [06:36<11:11, 1.14s/it, Loss=1.0095410] Training progress: 42%|████▏ | 420/1000 [06:36<10:23, 1.08s/it, Loss=1.0095410] Training progress: 42%|████▏ | 420/1000 [06:45<10:23, 1.08s/it, Loss=1.0092835] Training progress: 43%|████▎ | 430/1000 [06:45<09:41, 1.02s/it, Loss=1.0092835] Training progress: 43%|████▎ | 430/1000 [06:54<09:41, 1.02s/it, Loss=1.0091632] Training progress: 44%|████▍ | 440/1000 [06:54<09:09, 1.02it/s, Loss=1.0091632] Training progress: 44%|████▍ | 440/1000 [07:03<09:09, 1.02it/s, Loss=1.0088365] Training progress: 45%|████▌ | 450/1000 [07:03<08:45, 1.05it/s, Loss=1.0088365] Training progress: 45%|████▌ | 450/1000 [07:11<08:45, 1.05it/s, Loss=1.0097462] Training progress: 46%|████▌ | 460/1000 [07:11<08:13, 1.09it/s, Loss=1.0097462] Training progress: 46%|████▌ | 460/1000 [07:19<08:13, 1.09it/s, Loss=1.0092854] Training progress: 47%|████▋ | 470/1000 [07:19<07:49, 1.13it/s, Loss=1.0092854] Training progress: 47%|████▋ | 470/1000 [07:28<07:49, 1.13it/s, Loss=1.0093460] Training progress: 48%|████▊ | 480/1000 [07:28<07:39, 1.13it/s, Loss=1.0093460] Training progress: 48%|████▊ | 480/1000 [07:37<07:39, 1.13it/s, Loss=1.0090952] scale up theta_range to: [60, 90] [22/12 16:24:43] scale up radius_range to: [4.9399999999999995, 5.225] [22/12 16:24:43] scale up phi_range to: [-180, 180] [22/12 16:24:43] scale up fovy_range to: [0.24, 0.6] [22/12 16:24:43] Training progress: 49%|████▉ | 490/1000 [07:37<07:25, 1.14it/s, Loss=1.0090952] Training progress: 49%|████▉ | 490/1000 [07:45<07:25, 1.14it/s, Loss=1.0091098] [ITER 500] Saving Gaussians [22/12 16:24:45] Training progress: 50%|█████ | 500/1000 [07:45<07:20, 1.14it/s, Loss=1.0091098] Training progress: 50%|█████ | 500/1000 [07:57<07:20, 1.14it/s, Loss=1.0093191] Training progress: 51%|█████ | 510/1000 [07:57<07:47, 1.05it/s, Loss=1.0093191] Training progress: 51%|█████ | 510/1000 [08:05<07:47, 1.05it/s, Loss=1.0097375] Training progress: 52%|█████▏ | 520/1000 [08:05<07:20, 1.09it/s, Loss=1.0097375] Training progress: 52%|█████▏ | 520/1000 [08:14<07:20, 1.09it/s, Loss=1.0100511] Training progress: 53%|█████▎ | 530/1000 [08:14<07:02, 1.11it/s, Loss=1.0100511] Training progress: 53%|█████▎ | 530/1000 [08:23<07:02, 1.11it/s, Loss=1.0102542] Training progress: 54%|█████▍ | 540/1000 [08:23<06:58, 1.10it/s, Loss=1.0102542] Training progress: 54%|█████▍ | 540/1000 [08:32<06:58, 1.10it/s, Loss=1.0098752] Training progress: 55%|█████▌ | 550/1000 [08:32<06:42, 1.12it/s, Loss=1.0098752] Training progress: 55%|█████▌ | 550/1000 [08:40<06:42, 1.12it/s, Loss=1.0098831] Training progress: 56%|█████▌ | 560/1000 [08:40<06:26, 1.14it/s, Loss=1.0098831] Training progress: 56%|█████▌ | 560/1000 [08:49<06:26, 1.14it/s, Loss=1.0099793] Training progress: 57%|█████▋ | 570/1000 [08:49<06:14, 1.15it/s, Loss=1.0099793] Training progress: 57%|█████▋ | 570/1000 [08:57<06:14, 1.15it/s, Loss=1.0098103] Training progress: 58%|█████▊ | 580/1000 [08:57<06:02, 1.16it/s, Loss=1.0098103] Training progress: 58%|█████▊ | 580/1000 [09:06<06:02, 1.16it/s, Loss=1.0090983] Training progress: 59%|█████▉ | 590/1000 [09:06<05:56, 1.15it/s, Loss=1.0090983] Training progress: 59%|█████▉ | 590/1000 [09:15<05:56, 1.15it/s, Loss=1.0095025] test views is in : ./output/Replicate/test_six_views/600_iteration [22/12 16:26:14] [ITER 600] Eval Done! [22/12 16:26:15] videos is in : ./output/Replicate/videos/600_iteration[22/12 16:26:15] Generating Video using 240 different view points[22/12 16:26:21] [ITER 600] Video Save Done! [22/12 16:26:24] Training progress: 60%|██████ | 600/1000 [09:15<05:55, 1.13it/s, Loss=1.0095025] Training progress: 60%|██████ | 600/1000 [09:34<05:55, 1.13it/s, Loss=1.0120878] Training progress: 61%|██████ | 610/1000 [09:34<07:41, 1.18s/it, Loss=1.0120878] Training progress: 61%|██████ | 610/1000 [09:43<07:41, 1.18s/it, Loss=1.0099001] Training progress: 62%|██████▏ | 620/1000 [09:43<06:56, 1.10s/it, Loss=1.0099001] Training progress: 62%|██████▏ | 620/1000 [09:51<06:56, 1.10s/it, Loss=1.0100498] Training progress: 63%|██████▎ | 630/1000 [09:51<06:19, 1.03s/it, Loss=1.0100498] Training progress: 63%|██████▎ | 630/1000 [10:01<06:19, 1.03s/it, Loss=1.0104325] Training progress: 64%|██████▍ | 640/1000 [10:01<06:01, 1.01s/it, Loss=1.0104325] Training progress: 64%|██████▍ | 640/1000 [10:10<06:01, 1.01s/it, Loss=1.0113608] Training progress: 65%|██████▌ | 650/1000 [10:10<05:38, 1.03it/s, Loss=1.0113608] Training progress: 65%|██████▌ | 650/1000 [10:19<05:38, 1.03it/s, Loss=1.0094696] Training progress: 66%|██████▌ | 660/1000 [10:19<05:19, 1.06it/s, Loss=1.0094696] Training progress: 66%|██████▌ | 660/1000 [10:27<05:19, 1.06it/s, Loss=1.0095921] Training progress: 67%|██████▋ | 670/1000 [10:27<05:04, 1.08it/s, Loss=1.0095921] Training progress: 67%|██████▋ | 670/1000 [10:36<05:04, 1.08it/s, Loss=1.0090344] Training progress: 68%|██████▊ | 680/1000 [10:36<04:49, 1.11it/s, Loss=1.0090344] Training progress: 68%|██████▊ | 680/1000 [10:45<04:49, 1.11it/s, Loss=1.0103945] Training progress: 69%|██████▉ | 690/1000 [10:45<04:35, 1.12it/s, Loss=1.0103945] Training progress: 69%|██████▉ | 690/1000 [10:54<04:35, 1.12it/s, Loss=1.0091865] Training progress: 70%|███████ | 700/1000 [10:54<04:32, 1.10it/s, Loss=1.0091865] Training progress: 70%|███████ | 700/1000 [11:02<04:32, 1.10it/s, Loss=1.0109836] Training progress: 71%|███████ | 710/1000 [11:02<04:17, 1.13it/s, Loss=1.0109836] Training progress: 71%|███████ | 710/1000 [11:11<04:17, 1.13it/s, Loss=1.0101475] Training progress: 72%|███████▏ | 720/1000 [11:11<04:08, 1.13it/s, Loss=1.0101475] Training progress: 72%|███████▏ | 720/1000 [11:20<04:08, 1.13it/s, Loss=1.0097659] Training progress: 73%|███████▎ | 730/1000 [11:20<04:01, 1.12it/s, Loss=1.0097659] Training progress: 73%|███████▎ | 730/1000 [11:29<04:01, 1.12it/s, Loss=1.0101017] Training progress: 74%|███████▍ | 740/1000 [11:29<03:51, 1.12it/s, Loss=1.0101017] Training progress: 74%|███████▍ | 740/1000 [11:37<03:51, 1.12it/s, Loss=1.0095184] Training progress: 75%|███████▌ | 750/1000 [11:37<03:37, 1.15it/s, Loss=1.0095184] Training progress: 75%|███████▌ | 750/1000 [11:47<03:37, 1.15it/s, Loss=1.0111929] Training progress: 76%|███████▌ | 760/1000 [11:47<03:33, 1.12it/s, Loss=1.0111929] Training progress: 76%|███████▌ | 760/1000 [11:55<03:33, 1.12it/s, Loss=1.0105028] Training progress: 77%|███████▋ | 770/1000 [11:55<03:21, 1.14it/s, Loss=1.0105028] Training progress: 77%|███████▋ | 770/1000 [12:04<03:21, 1.14it/s, Loss=1.0102045] Training progress: 78%|███████▊ | 780/1000 [12:04<03:10, 1.16it/s, Loss=1.0102045] Training progress: 78%|███████▊ | 780/1000 [12:12<03:10, 1.16it/s, Loss=1.0098310] Training progress: 79%|███████▉ | 790/1000 [12:12<03:01, 1.16it/s, Loss=1.0098310] Training progress: 79%|███████▉ | 790/1000 [12:22<03:01, 1.16it/s, Loss=1.0101976] test views is in : ./output/Replicate/test_six_views/800_iteration [22/12 16:29:21] [ITER 800] Eval Done! [22/12 16:29:22] videos is in : ./output/Replicate/videos/800_iteration [22/12 16:29:22] Generating Video using 240 different view points[22/12 16:29:28] [ITER 800] Video Save Done! [22/12 16:29:31] Training progress: 80%|████████ | 800/1000 [12:22<02:57, 1.12it/s, Loss=1.0101976] Training progress: 80%|████████ | 800/1000 [12:41<02:57, 1.12it/s, Loss=1.0115836] Training progress: 81%|████████ | 810/1000 [12:41<03:45, 1.19s/it, Loss=1.0115836] Training progress: 81%|████████ | 810/1000 [12:50<03:45, 1.19s/it, Loss=1.0098869] Training progress: 82%|████████▏ | 820/1000 [12:50<03:18, 1.10s/it, Loss=1.0098869] Training progress: 82%|████████▏ | 820/1000 [12:59<03:18, 1.10s/it, Loss=1.0102600] Training progress: 83%|████████▎ | 830/1000 [12:59<02:57, 1.05s/it, Loss=1.0102600] Training progress: 83%|████████▎ | 830/1000 [13:08<02:57, 1.05s/it, Loss=1.0097042] Training progress: 84%|████████▍ | 840/1000 [13:08<02:39, 1.01it/s, Loss=1.0097042] Training progress: 84%|████████▍ | 840/1000 [13:16<02:39, 1.01it/s, Loss=1.0103961] Training progress: 85%|████████▌ | 850/1000 [13:16<02:24, 1.04it/s, Loss=1.0103961] Training progress: 85%|████████▌ | 850/1000 [13:26<02:24, 1.04it/s, Loss=1.0108702] Training progress: 86%|████████▌ | 860/1000 [13:26<02:13, 1.05it/s, Loss=1.0108702] Training progress: 86%|████████▌ | 860/1000 [13:34<02:13, 1.05it/s, Loss=1.0092877] Training progress: 87%|████████▋ | 870/1000 [13:34<02:00, 1.07it/s, Loss=1.0092877] Training progress: 87%|████████▋ | 870/1000 [13:43<02:00, 1.07it/s, Loss=1.0103984] Training progress: 88%|████████▊ | 880/1000 [13:43<01:49, 1.10it/s, Loss=1.0103984] Training progress: 88%|████████▊ | 880/1000 [13:52<01:49, 1.10it/s, Loss=1.0098017] Training progress: 89%|████████▉ | 890/1000 [13:52<01:39, 1.11it/s, Loss=1.0098017] Training progress: 89%|████████▉ | 890/1000 [14:01<01:39, 1.11it/s, Loss=1.0112966] Training progress: 90%|█████████ | 900/1000 [14:01<01:31, 1.09it/s, Loss=1.0112966] Training progress: 90%|█████████ | 900/1000 [14:11<01:31, 1.09it/s, Loss=1.0114046] Training progress: 91%|█████████ | 910/1000 [14:11<01:22, 1.09it/s, Loss=1.0114046] Training progress: 91%|█████████ | 910/1000 [14:20<01:22, 1.09it/s, Loss=1.0115868] Training progress: 92%|█████████▏| 920/1000 [14:20<01:12, 1.10it/s, Loss=1.0115868] Training progress: 92%|█████████▏| 920/1000 [14:29<01:12, 1.10it/s, Loss=1.0097545] Training progress: 93%|█████████▎| 930/1000 [14:29<01:03, 1.10it/s, Loss=1.0097545] Training progress: 93%|█████████▎| 930/1000 [14:37<01:03, 1.10it/s, Loss=1.0098565] Training progress: 94%|█████████▍| 940/1000 [14:37<00:53, 1.12it/s, Loss=1.0098565] Training progress: 94%|█████████▍| 940/1000 [14:46<00:53, 1.12it/s, Loss=1.0107825] Training progress: 95%|█████████▌| 950/1000 [14:46<00:43, 1.14it/s, Loss=1.0107825] Training progress: 95%|█████████▌| 950/1000 [14:54<00:43, 1.14it/s, Loss=1.0096509] Training progress: 96%|█████████▌| 960/1000 [14:54<00:34, 1.14it/s, Loss=1.0096509] Training progress: 96%|█████████▌| 960/1000 [15:04<00:34, 1.14it/s, Loss=1.0093848] Training progress: 97%|█████████▋| 970/1000 [15:04<00:26, 1.12it/s, Loss=1.0093848] Training progress: 97%|█████████▋| 970/1000 [15:13<00:26, 1.12it/s, Loss=1.0099435] Training progress: 98%|█████████▊| 980/1000 [15:13<00:17, 1.12it/s, Loss=1.0099435] Training progress: 98%|█████████▊| 980/1000 [15:21<00:17, 1.12it/s, Loss=1.0103432] scale up theta_range to: [60, 90][22/12 16:32:28] scale up radius_range to: [4.693, 5.0] [22/12 16:32:28] scale up phi_range to: [-180, 180] [22/12 16:32:28] scale up fovy_range to: [0.18, 0.6] [22/12 16:32:28] Training progress: 99%|█████████▉| 990/1000 [15:21<00:08, 1.13it/s, Loss=1.0103432] Training progress: 99%|█████████▉| 990/1000 [15:31<00:08, 1.13it/s, Loss=1.0096740] Training progress: 100%|██████████| 1000/1000 [15:31<00:00, 1.11it/s, Loss=1.0096740] Training progress: 100%|██████████| 1000/1000 [15:31<00:00, 1.07it/s, Loss=1.0096740] test views is in : ./output/Replicate/test_six_views/1000_iteration[22/12 16:32:30] [ITER 1000] Eval Done! [22/12 16:32:31] videos is in : ./output/Replicate/videos/1000_iteration [22/12 16:32:31] Generating Video using 240 different view points[22/12 16:32:37] [ITER 1000] Video Save Done! [22/12 16:32:42] [ITER 1000] Saving Gaussians [22/12 16:32:42] Training complete.[22/12 16:32:52]Prediction
jd7h/luciddreamer:fbf8e0dfef4ca0c0de45cf1afbf12c81667ee29fd79852852262aee4f167fbf5IDshgrpndbki7cyyurxrvyry374mStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- cfg
- 7.5
- prompt
- A christmas tree decorated with lights and ornaments
- iterations
- 1000
- neg_prompt
- unrealistic, blurry, low quality, out of focus, ugly, low contrast, dull, low resolution, distorted, boring
- init_prompt
- Fir tree
{ "cfg": 7.5, "prompt": "A christmas tree decorated with lights and ornaments", "iterations": 1000, "neg_prompt": "unrealistic, blurry, low quality, out of focus, ugly, low contrast, dull, low resolution, distorted, boring", "init_prompt": "Fir tree" }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 jd7h/luciddreamer using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "jd7h/luciddreamer:fbf8e0dfef4ca0c0de45cf1afbf12c81667ee29fd79852852262aee4f167fbf5", { input: { cfg: 7.5, prompt: "A christmas tree decorated with lights and ornaments", iterations: 1000, neg_prompt: "unrealistic, blurry, low quality, out of focus, ugly, low contrast, dull, low resolution, distorted, boring", init_prompt: "Fir tree" } } ); // To access the file URL: console.log(output[0].url()); //=> "http://example.com" // To write the file to disk: fs.writeFile("my-image.png", output[0]);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 jd7h/luciddreamer using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "jd7h/luciddreamer:fbf8e0dfef4ca0c0de45cf1afbf12c81667ee29fd79852852262aee4f167fbf5", input={ "cfg": 7.5, "prompt": "A christmas tree decorated with lights and ornaments", "iterations": 1000, "neg_prompt": "unrealistic, blurry, low quality, out of focus, ugly, low contrast, dull, low resolution, distorted, boring", "init_prompt": "Fir tree" } ) print(output)To learn more, take a look at the guide on getting started with Python.
Run jd7h/luciddreamer 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": "jd7h/luciddreamer:fbf8e0dfef4ca0c0de45cf1afbf12c81667ee29fd79852852262aee4f167fbf5", "input": { "cfg": 7.5, "prompt": "A christmas tree decorated with lights and ornaments", "iterations": 1000, "neg_prompt": "unrealistic, blurry, low quality, out of focus, ugly, low contrast, dull, low resolution, distorted, boring", "init_prompt": "Fir tree" } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2023-12-22T16:36:36.197903Z", "created_at": "2023-12-22T16:16:26.452145Z", "data_removed": false, "error": null, "id": "shgrpndbki7cyyurxrvyry374m", "input": { "cfg": 7.5, "prompt": "A christmas tree decorated with lights and ornaments", "iterations": 1000, "neg_prompt": "unrealistic, blurry, low quality, out of focus, ugly, low contrast, dull, low resolution, distorted, boring", "init_prompt": "Fir tree" }, "logs": "Using seed: 1156556824\nTest iter: [1, 200, 400, 600, 800, 1000]\nSave iter: [500, 1000]\nOptimizing\nOutput folder: ./output/Replicate[22/12 16:19:13]\nTensorboard not available: not logging progress [22/12 16:19:13]\nReading Test Transforms [22/12 16:19:13]\ncreating base model... [22/12 16:19:13]\n 0%| | 0.00/890M [00:00<?, ?iB/s]\n 0%|▏ | 3.88M/890M [00:00<00:23, 40.4MiB/s]\n 1%|▎ | 7.73M/890M [00:00<00:24, 37.4MiB/s]\n 1%|▌ | 12.8M/890M [00:00<00:21, 43.7MiB/s]\n 2%|▋ | 17.0M/890M [00:00<00:21, 43.1MiB/s]\n 2%|▉ | 22.0M/890M [00:00<00:21, 42.4MiB/s]\n 3%|█▏ | 26.5M/890M [00:00<00:20, 43.7MiB/s]\n 3%|█▎ | 30.7M/890M [00:00<00:21, 42.2MiB/s]\n 4%|█▌ | 35.7M/890M [00:00<00:19, 45.1MiB/s]\n 5%|█▋ | 40.4M/890M [00:00<00:19, 46.3MiB/s]\n 5%|█▉ | 45.4M/890M [00:01<00:18, 48.1MiB/s]\n 6%|██▏ | 50.0M/890M [00:01<00:18, 48.0MiB/s]\n 6%|██▎ | 54.6M/890M [00:01<00:19, 46.1MiB/s]\n 7%|██▌ | 59.5M/890M [00:01<00:18, 47.5MiB/s]\n 7%|██▋ | 64.0M/890M [00:01<00:19, 45.4MiB/s]\n 8%|██▉ | 69.9M/890M [00:01<00:17, 50.0MiB/s]\n 8%|███▏ | 74.7M/890M [00:01<00:17, 47.6MiB/s]\n 9%|███▍ | 80.0M/890M [00:01<00:17, 49.4MiB/s]\n 10%|███▋ | 85.0M/890M [00:01<00:16, 50.0MiB/s]\n 10%|███▊ | 90.1M/890M [00:02<00:16, 50.8MiB/s]\n 11%|████ | 95.0M/890M [00:02<00:16, 49.7MiB/s]\n 11%|████▍ | 100M/890M [00:02<00:16, 49.2MiB/s]\n 12%|████▌ | 105M/890M [00:02<00:18, 45.7MiB/s]\n 12%|████▊ | 110M/890M [00:02<00:17, 47.7MiB/s]\n 13%|█████ | 115M/890M [00:02<00:16, 49.2MiB/s]\n 13%|█████▎ | 120M/890M [00:02<00:16, 49.5MiB/s]\n 14%|█████▍ | 125M/890M [00:02<00:15, 50.8MiB/s]\n 15%|█████▋ | 130M/890M [00:02<00:16, 47.9MiB/s]\n 15%|█████▉ | 135M/890M [00:02<00:16, 47.4MiB/s]\n 16%|██████▏ | 140M/890M [00:03<00:15, 50.1MiB/s]\n 16%|██████▎ | 145M/890M [00:03<00:15, 50.5MiB/s]\n 17%|██████▌ | 150M/890M [00:03<00:16, 47.5MiB/s]\n 17%|██████▊ | 154M/890M [00:03<00:16, 45.4MiB/s]\n 18%|██████▉ | 159M/890M [00:03<00:16, 46.0MiB/s]\n 18%|███████▏ | 164M/890M [00:03<00:15, 48.7MiB/s]\n 19%|███████▍ | 170M/890M [00:03<00:14, 51.1MiB/s]\n 20%|███████▋ | 176M/890M [00:03<00:13, 53.6MiB/s]\n 20%|███████▉ | 181M/890M [00:03<00:14, 52.0MiB/s]\n 21%|████████▏ | 186M/890M [00:04<00:14, 52.4MiB/s]\n 21%|████████▎ | 191M/890M [00:04<00:14, 52.2MiB/s]\n 22%|████████▌ | 196M/890M [00:04<00:13, 52.6MiB/s]\n 23%|████████▊ | 201M/890M [00:04<00:13, 53.3MiB/s]\n 23%|█████████ | 207M/890M [00:04<00:13, 54.7MiB/s]\n 24%|█████████▎ | 212M/890M [00:04<00:13, 52.0MiB/s]\n 24%|█████████▌ | 217M/890M [00:04<00:13, 51.0MiB/s]\n 25%|█████████▋ | 222M/890M [00:04<00:13, 51.3MiB/s]\n 26%|█████████▉ | 227M/890M [00:04<00:13, 51.9MiB/s]\n 26%|██████████▏ | 232M/890M [00:05<00:15, 45.7MiB/s]\n 27%|██████████▍ | 237M/890M [00:05<00:14, 47.0MiB/s]\n 27%|██████████▌ | 242M/890M [00:05<00:14, 45.4MiB/s]\n 28%|██████████▊ | 247M/890M [00:05<00:14, 47.7MiB/s]\n 28%|███████████ | 252M/890M [00:05<00:13, 49.7MiB/s]\n 29%|███████████▍ | 260M/890M [00:05<00:11, 58.7MiB/s]\n 30%|███████████▋ | 268M/890M [00:05<00:10, 64.6MiB/s]\n 31%|████████████ | 274M/890M [00:05<00:10, 60.3MiB/s]\n 31%|████████████▎ | 280M/890M [00:05<00:12, 51.5MiB/s]\n 32%|████████████▍ | 285M/890M [00:06<00:12, 49.7MiB/s]\n 33%|████████████▋ | 290M/890M [00:06<00:14, 42.0MiB/s]\n 33%|████████████▉ | 294M/890M [00:06<00:15, 39.3MiB/s]\n 34%|█████████████ | 298M/890M [00:06<00:15, 40.8MiB/s]\n 34%|█████████████▎ | 303M/890M [00:06<00:14, 41.4MiB/s]\n 35%|█████████████▌ | 308M/890M [00:06<00:13, 45.5MiB/s]\n 35%|█████████████▋ | 313M/890M [00:06<00:12, 48.0MiB/s]\n 36%|█████████████▉ | 319M/890M [00:06<00:12, 49.4MiB/s]\n 36%|██████████████▏ | 323M/890M [00:06<00:11, 49.7MiB/s]\n 37%|██████████████▍ | 329M/890M [00:07<00:11, 51.8MiB/s]\n 38%|██████████████▋ | 334M/890M [00:07<00:10, 53.0MiB/s]\n 38%|██████████████▉ | 339M/890M [00:07<00:10, 52.6MiB/s]\n 39%|███████████████ | 344M/890M [00:07<00:10, 52.4MiB/s]\n 39%|███████████████▎ | 350M/890M [00:07<00:10, 53.8MiB/s]\n 40%|███████████████▌ | 355M/890M [00:07<00:10, 52.2MiB/s]\n 40%|███████████████▊ | 360M/890M [00:07<00:11, 48.6MiB/s]\n 41%|████████████████ | 365M/890M [00:07<00:10, 50.2MiB/s]\n 42%|████████████████▏ | 370M/890M [00:07<00:10, 51.0MiB/s]\n 42%|████████████████▍ | 375M/890M [00:08<00:10, 49.1MiB/s]\n 43%|████████████████▋ | 380M/890M [00:08<00:14, 37.9MiB/s]\n 43%|████████████████▉ | 385M/890M [00:08<00:12, 41.6MiB/s]\n 44%|█████████████████ | 390M/890M [00:08<00:11, 44.2MiB/s]\n 44%|█████████████████▎ | 395M/890M [00:08<00:11, 43.8MiB/s]\n 45%|█████████████████▌ | 400M/890M [00:08<00:11, 46.5MiB/s]\n 46%|█████████████████▊ | 405M/890M [00:08<00:10, 49.1MiB/s]\n 46%|█████████████████▉ | 410M/890M [00:08<00:10, 50.0MiB/s]\n 47%|██████████████████▏ | 415M/890M [00:08<00:10, 49.7MiB/s]\n 47%|██████████████████▍ | 420M/890M [00:09<00:09, 50.0MiB/s]\n 48%|██████████████████▋ | 425M/890M [00:09<00:14, 34.2MiB/s]\n 48%|██████████████████▊ | 430M/890M [00:09<00:12, 37.9MiB/s]\n 49%|███████████████████ | 434M/890M [00:09<00:12, 39.4MiB/s]\n 49%|███████████████████▏ | 438M/890M [00:09<00:11, 40.6MiB/s]\n 50%|███████████████████▍ | 443M/890M [00:09<00:11, 41.6MiB/s]\n 50%|███████████████████▌ | 448M/890M [00:09<00:10, 44.2MiB/s]\n 51%|███████████████████▊ | 453M/890M [00:09<00:09, 46.8MiB/s]\n 51%|████████████████████ | 458M/890M [00:10<00:09, 48.3MiB/s]\n 52%|████████████████████▎ | 463M/890M [00:10<00:08, 51.3MiB/s]\n 53%|████████████████████▌ | 468M/890M [00:10<00:08, 50.2MiB/s]\n 53%|████████████████████▋ | 473M/890M [00:10<00:08, 50.5MiB/s]\n 54%|████████████████████▉ | 478M/890M [00:10<00:08, 51.6MiB/s]\n 54%|█████████████████████▏ | 484M/890M [00:10<00:08, 53.0MiB/s]\n 55%|█████████████████████▍ | 489M/890M [00:10<00:07, 53.7MiB/s]\n 56%|█████████████████████▋ | 495M/890M [00:10<00:07, 54.2MiB/s]\n 56%|█████████████████████▉ | 500M/890M [00:10<00:08, 50.2MiB/s]\n 57%|██████████████████████ | 505M/890M [00:10<00:08, 49.8MiB/s]\n 57%|██████████████████████▎ | 510M/890M [00:11<00:07, 51.0MiB/s]\n 58%|██████████████████████▌ | 515M/890M [00:11<00:07, 50.3MiB/s]\n 58%|██████████████████████▊ | 520M/890M [00:11<00:07, 51.0MiB/s]\n 59%|███████████████████████ | 525M/890M [00:11<00:07, 51.2MiB/s]\n 60%|███████████████████████▏ | 530M/890M [00:11<00:07, 51.3MiB/s]\n 60%|███████████████████████▍ | 535M/890M [00:11<00:07, 51.3MiB/s]\n 61%|███████████████████████▋ | 540M/890M [00:11<00:07, 51.4MiB/s]\n 61%|███████████████████████▉ | 545M/890M [00:11<00:06, 51.9MiB/s]\n 62%|████████████████████████ | 550M/890M [00:11<00:06, 51.7MiB/s]\n 63%|████████████████████████▍ | 559M/890M [00:12<00:05, 64.6MiB/s]\n 63%|████████████████████████▊ | 565M/890M [00:12<00:05, 64.1MiB/s]\n 64%|█████████████████████████ | 571M/890M [00:12<00:05, 60.6MiB/s]\n 65%|█████████████████████████▎ | 577M/890M [00:12<00:05, 55.2MiB/s]\n 65%|█████████████████████████▌ | 582M/890M [00:12<00:05, 54.2MiB/s]\n 66%|█████████████████████████▊ | 587M/890M [00:12<00:05, 53.9MiB/s]\n 67%|█████████████████████████▉ | 593M/890M [00:12<00:05, 53.3MiB/s]\n 67%|██████████████████████████▏ | 598M/890M [00:12<00:06, 49.6MiB/s]\n 68%|██████████████████████████▍ | 603M/890M [00:12<00:05, 50.4MiB/s]\n 68%|██████████████████████████▋ | 608M/890M [00:13<00:05, 50.0MiB/s]\n 69%|██████████████████████████▊ | 612M/890M [00:13<00:06, 47.4MiB/s]\n 69%|███████████████████████████ | 617M/890M [00:13<00:06, 47.3MiB/s]\n 70%|███████████████████████████▏ | 622M/890M [00:13<00:05, 46.9MiB/s]\n 70%|███████████████████████████▍ | 626M/890M [00:13<00:05, 46.4MiB/s]\n 71%|███████████████████████████▋ | 631M/890M [00:13<00:05, 46.9MiB/s]\n 71%|███████████████████████████▊ | 635M/890M [00:13<00:05, 46.8MiB/s]\n 72%|████████████████████████████ | 640M/890M [00:13<00:05, 49.0MiB/s]\n 73%|████████████████████████████▎ | 645M/890M [00:13<00:05, 49.6MiB/s]\n 73%|████████████████████████████▌ | 650M/890M [00:13<00:05, 49.7MiB/s]\n 74%|████████████████████████████▋ | 655M/890M [00:14<00:05, 47.8MiB/s]\n 74%|████████████████████████████▉ | 660M/890M [00:14<00:04, 49.7MiB/s]\n 75%|█████████████████████████████▏ | 665M/890M [00:14<00:04, 49.7MiB/s]\n 75%|█████████████████████████████▎ | 670M/890M [00:14<00:04, 49.3MiB/s]\n 76%|█████████████████████████████▌ | 674M/890M [00:14<00:04, 49.2MiB/s]\n 76%|█████████████████████████████▊ | 679M/890M [00:14<00:04, 48.9MiB/s]\n 77%|█████████████████████████████▉ | 684M/890M [00:14<00:04, 47.9MiB/s]\n 77%|██████████████████████████████▏ | 688M/890M [00:14<00:04, 45.7MiB/s]\n 78%|██████████████████████████████▍ | 693M/890M [00:14<00:04, 47.4MiB/s]\n 78%|██████████████████████████████▌ | 698M/890M [00:14<00:04, 46.5MiB/s]\n 79%|██████████████████████████████▊ | 703M/890M [00:15<00:04, 48.4MiB/s]\n 80%|███████████████████████████████ | 708M/890M [00:15<00:03, 49.4MiB/s]\n 80%|███████████████████████████████▏ | 713M/890M [00:15<00:03, 49.7MiB/s]\n 81%|███████████████████████████████▍ | 717M/890M [00:15<00:03, 49.6MiB/s]\n 81%|███████████████████████████████▋ | 723M/890M [00:15<00:03, 50.9MiB/s]\n 82%|███████████████████████████████▉ | 728M/890M [00:15<00:03, 51.0MiB/s]\n 82%|████████████████████████████████ | 733M/890M [00:15<00:03, 51.6MiB/s]\n 83%|████████████████████████████████▎ | 738M/890M [00:15<00:02, 53.2MiB/s]\n 84%|████████████████████████████████▌ | 743M/890M [00:15<00:02, 53.4MiB/s]\n 84%|████████████████████████████████▊ | 748M/890M [00:16<00:02, 51.8MiB/s]\n 85%|█████████████████████████████████ | 753M/890M [00:16<00:02, 48.7MiB/s]\n 85%|█████████████████████████████████▏ | 758M/890M [00:16<00:02, 47.3MiB/s]\n 86%|█████████████████████████████████▍ | 763M/890M [00:16<00:02, 47.1MiB/s]\n 86%|█████████████████████████████████▋ | 767M/890M [00:16<00:02, 45.9MiB/s]\n 87%|█████████████████████████████████▊ | 772M/890M [00:16<00:02, 47.0MiB/s]\n 87%|██████████████████████████████████ | 777M/890M [00:16<00:02, 47.8MiB/s]\n 88%|██████████████████████████████████▎ | 782M/890M [00:16<00:02, 48.5MiB/s]\n 88%|██████████████████████████████████▍ | 787M/890M [00:16<00:02, 49.5MiB/s]\n 89%|██████████████████████████████████▋ | 791M/890M [00:16<00:02, 49.4MiB/s]\n 89%|██████████████████████████████████▉ | 796M/890M [00:17<00:02, 48.4MiB/s]\n 90%|███████████████████████████████████ | 801M/890M [00:17<00:01, 49.7MiB/s]\n 91%|███████████████████████████████████▎ | 806M/890M [00:17<00:01, 49.3MiB/s]\n 91%|███████████████████████████████████▌ | 811M/890M [00:17<00:01, 51.4MiB/s]\n 92%|███████████████████████████████████▊ | 816M/890M [00:17<00:01, 50.2MiB/s]\n 92%|████████████████████████████████████ | 822M/890M [00:17<00:01, 51.8MiB/s]\n 93%|████████████████████████████████████▎ | 827M/890M [00:17<00:01, 52.9MiB/s]\n 94%|████████████████████████████████████▍ | 832M/890M [00:17<00:01, 52.8MiB/s]\n 94%|████████████████████████████████████▋ | 838M/890M [00:17<00:01, 54.0MiB/s]\n 95%|████████████████████████████████████▉ | 843M/890M [00:17<00:00, 54.4MiB/s]\n 95%|█████████████████████████████████████▏ | 848M/890M [00:18<00:00, 53.9MiB/s]\n 96%|█████████████████████████████████████▍ | 854M/890M [00:18<00:00, 54.7MiB/s]\n 97%|█████████████████████████████████████▋ | 859M/890M [00:18<00:00, 54.5MiB/s]\n 97%|█████████████████████████████████████▉ | 864M/890M [00:18<00:00, 51.7MiB/s]\n 98%|██████████████████████████████████████ | 869M/890M [00:18<00:00, 48.0MiB/s]\n 98%|██████████████████████████████████████▎| 874M/890M [00:18<00:00, 46.8MiB/s]\n 99%|██████████████████████████████████████▌| 879M/890M [00:18<00:00, 48.1MiB/s]\n 99%|██████████████████████████████████████▋| 883M/890M [00:18<00:00, 46.6MiB/s]\n100%|██████████████████████████████████████▉| 888M/890M [00:18<00:00, 48.9MiB/s]\n100%|███████████████████████████████████████| 890M/890M [00:18<00:00, 49.1MiB/s]\ncreating upsample model... [22/12 16:19:40]\ndownloading base checkpoint... [22/12 16:19:45]\n 0%| | 0.00/161M [00:00<?, ?iB/s]\n 0%| | 393k/161M [00:00<00:47, 3.37MiB/s]\n 1%| | 1.18M/161M [00:00<00:29, 5.38MiB/s]\n 2%|▏ | 2.49M/161M [00:00<00:19, 8.07MiB/s]\n 3%|▎ | 4.19M/161M [00:00<00:15, 10.4MiB/s]\n 4%|▍ | 7.21M/161M [00:00<00:09, 16.0MiB/s]\n 5%|▌ | 8.81M/161M [00:00<00:11, 13.7MiB/s]\n 7%|▋ | 11.5M/161M [00:00<00:08, 17.1MiB/s]\n 9%|▉ | 15.2M/161M [00:00<00:06, 22.6MiB/s]\n 12%|█▏ | 19.3M/161M [00:01<00:05, 27.5MiB/s]\n 15%|█▍ | 23.9M/161M [00:01<00:04, 32.6MiB/s]\n 18%|█▊ | 28.4M/161M [00:01<00:03, 36.3MiB/s]\n 20%|██ | 33.0M/161M [00:01<00:03, 39.0MiB/s]\n 23%|██▎ | 37.5M/161M [00:01<00:03, 40.6MiB/s]\n 26%|██▌ | 41.9M/161M [00:01<00:05, 21.3MiB/s]\n 28%|██▊ | 45.1M/161M [00:02<00:07, 15.2MiB/s]\n 30%|██▉ | 47.6M/161M [00:02<00:07, 15.3MiB/s]\n 32%|███▏ | 50.9M/161M [00:02<00:06, 17.9MiB/s]\n 33%|███▎ | 53.6M/161M [00:02<00:05, 19.2MiB/s]\n 35%|███▍ | 56.1M/161M [00:02<00:05, 18.8MiB/s]\n 36%|███▋ | 58.7M/161M [00:03<00:08, 12.4MiB/s]\n 37%|███▋ | 60.5M/161M [00:03<00:10, 9.94MiB/s]\n 38%|███▊ | 61.9M/161M [00:03<00:09, 10.3MiB/s]\n 39%|███▉ | 63.3M/161M [00:03<00:09, 10.5MiB/s]\n 41%|████ | 65.5M/161M [00:03<00:07, 12.6MiB/s]\n 42%|████▏ | 67.1M/161M [00:04<00:11, 8.38MiB/s]\n 42%|████▏ | 68.3M/161M [00:04<00:14, 6.43MiB/s]\n 43%|████▎ | 69.2M/161M [00:04<00:15, 6.06MiB/s]\n 43%|████▎ | 70.0M/161M [00:04<00:15, 5.87MiB/s]\n 44%|████▍ | 70.8M/161M [00:05<00:15, 5.93MiB/s]\n 44%|████▍ | 71.5M/161M [00:05<00:17, 5.19MiB/s]\n 45%|████▍ | 72.1M/161M [00:05<00:16, 5.26MiB/s]\n 45%|████▌ | 72.7M/161M [00:05<00:17, 5.16MiB/s]\n 45%|████▌ | 73.3M/161M [00:05<00:17, 5.17MiB/s]\n 46%|████▌ | 73.8M/161M [00:05<00:17, 5.06MiB/s]\n 46%|████▌ | 74.5M/161M [00:05<00:16, 5.18MiB/s]\n 47%|████▋ | 75.1M/161M [00:05<00:16, 5.31MiB/s]\n 48%|████▊ | 77.9M/161M [00:06<00:07, 11.0MiB/s]\n 51%|█████ | 82.2M/161M [00:06<00:04, 19.5MiB/s]\n 52%|█████▏ | 84.3M/161M [00:06<00:08, 9.24MiB/s]\n 53%|█████▎ | 85.9M/161M [00:06<00:08, 8.88MiB/s]\n 54%|█████▍ | 87.4M/161M [00:06<00:07, 9.71MiB/s]\n 56%|█████▌ | 89.9M/161M [00:07<00:05, 12.0MiB/s]\n 58%|█████▊ | 93.7M/161M [00:07<00:03, 17.3MiB/s]\n 60%|██████ | 97.3M/161M [00:07<00:03, 21.2MiB/s]\n 62%|██████▏ | 101M/161M [00:07<00:04, 13.8MiB/s] \n 64%|██████▎ | 103M/161M [00:08<00:05, 10.7MiB/s]\n 65%|██████▍ | 104M/161M [00:08<00:05, 11.4MiB/s]\n 66%|██████▌ | 107M/161M [00:08<00:04, 13.4MiB/s]\n 68%|██████▊ | 109M/161M [00:08<00:05, 9.43MiB/s]\n 68%|██████▊ | 110M/161M [00:08<00:06, 7.76MiB/s]\n 69%|██████▉ | 112M/161M [00:09<00:05, 8.53MiB/s]\n 71%|███████ | 114M/161M [00:09<00:04, 10.4MiB/s]\n 73%|███████▎ | 117M/161M [00:09<00:04, 9.08MiB/s]\n 74%|███████▎ | 119M/161M [00:09<00:05, 8.02MiB/s]\n 74%|███████▍ | 120M/161M [00:09<00:04, 8.36MiB/s]\n 75%|███████▌ | 122M/161M [00:10<00:04, 9.73MiB/s]\n 77%|███████▋ | 124M/161M [00:10<00:02, 12.7MiB/s]\n 80%|███████▉ | 128M/161M [00:10<00:01, 18.5MiB/s]\n 83%|████████▎ | 133M/161M [00:10<00:01, 25.0MiB/s]\n 84%|████████▍ | 136M/161M [00:11<00:02, 10.9MiB/s]\n 86%|████████▌ | 138M/161M [00:11<00:01, 11.6MiB/s]\n 87%|████████▋ | 140M/161M [00:11<00:01, 12.4MiB/s]\n 89%|████████▉ | 144M/161M [00:11<00:01, 15.6MiB/s]\n 92%|█████████▏| 148M/161M [00:11<00:00, 20.8MiB/s]\n 94%|█████████▎| 151M/161M [00:11<00:00, 21.2MiB/s]\n 96%|█████████▌| 155M/161M [00:11<00:00, 24.6MiB/s]\n 98%|█████████▊| 158M/161M [00:11<00:00, 27.8MiB/s]\n100%|██████████| 161M/161M [00:12<00:00, 13.4MiB/s]\ndownloading upsampler checkpoint... [22/12 16:19:58]\n 0%| | 0.00/162M [00:00<?, ?iB/s]\n 6%|▋ | 10.3M/162M [00:00<00:01, 103MiB/s]\n 15%|█▌ | 24.6M/162M [00:00<00:01, 127MiB/s]\n 23%|██▎ | 37.3M/162M [00:00<00:01, 111MiB/s]\n 31%|███▏ | 50.7M/162M [00:00<00:00, 119MiB/s]\n 39%|███▉ | 62.9M/162M [00:00<00:00, 120MiB/s]\n 47%|████▋ | 76.2M/162M [00:00<00:00, 124MiB/s]\n 55%|█████▌ | 89.7M/162M [00:00<00:00, 128MiB/s]\n 63%|██████▎ | 103M/162M [00:00<00:00, 119MiB/s] \n 71%|███████ | 115M/162M [00:00<00:00, 109MiB/s]\n 78%|███████▊ | 127M/162M [00:01<00:00, 112MiB/s]\n 87%|████████▋ | 141M/162M [00:01<00:00, 121MiB/s]\n 95%|█████████▍| 154M/162M [00:01<00:00, 117MiB/s]\n100%|██████████| 162M/162M [00:01<00:00, 118MiB/s]\n0it [00:00, ?it/s]\n1it [00:01, 1.23s/it]\n4it [00:01, 3.70it/s]\n7it [00:01, 6.67it/s]\n10it [00:01, 9.55it/s]\n13it [00:01, 12.16it/s]\n16it [00:01, 14.39it/s]\n19it [00:02, 16.24it/s]\n22it [00:02, 17.70it/s]\n25it [00:02, 18.81it/s]\n28it [00:02, 19.63it/s]\n31it [00:02, 20.23it/s]\n34it [00:02, 20.66it/s]\n37it [00:02, 20.98it/s]\n40it [00:03, 21.20it/s]\n43it [00:03, 21.36it/s]\n46it [00:03, 21.47it/s]\n49it [00:03, 21.53it/s]\n52it [00:03, 21.56it/s]\n55it [00:03, 21.60it/s]\n58it [00:03, 21.59it/s]\n61it [00:03, 21.61it/s]\n64it [00:04, 21.62it/s]\n67it [00:04, 16.65it/s]\n69it [00:04, 11.39it/s]\n71it [00:05, 8.99it/s]\n73it [00:05, 7.69it/s]\n74it [00:05, 7.23it/s]\n75it [00:05, 6.82it/s]\n76it [00:06, 6.47it/s]\n77it [00:06, 6.19it/s]\n78it [00:06, 5.99it/s]\n79it [00:06, 5.84it/s]\n80it [00:06, 5.73it/s]\n81it [00:06, 5.65it/s]\n82it [00:07, 5.59it/s]\n83it [00:07, 5.55it/s]\n84it [00:07, 5.53it/s]\n85it [00:07, 5.50it/s]\n86it [00:07, 5.48it/s]\n87it [00:08, 5.47it/s]\n88it [00:08, 5.46it/s]\n89it [00:08, 5.46it/s]\n90it [00:08, 5.46it/s]\n91it [00:08, 5.46it/s]\n92it [00:09, 5.45it/s]\n93it [00:09, 5.45it/s]\n94it [00:09, 5.45it/s]\n95it [00:09, 5.45it/s]\n96it [00:09, 5.45it/s]\n97it [00:09, 5.45it/s]\n98it [00:10, 5.44it/s]\n99it [00:10, 5.44it/s]\n100it [00:10, 5.44it/s]\n101it [00:10, 5.44it/s]\n102it [00:10, 5.44it/s]\n103it [00:11, 5.44it/s]\n104it [00:11, 5.44it/s]\n105it [00:11, 5.44it/s]\n106it [00:11, 5.43it/s]\n107it [00:11, 5.43it/s]\n108it [00:11, 5.42it/s]\n109it [00:12, 5.41it/s]\n110it [00:12, 5.41it/s]\n111it [00:12, 5.42it/s]\n112it [00:12, 5.41it/s]\n113it [00:12, 5.42it/s]\n114it [00:13, 5.42it/s]\n115it [00:13, 5.42it/s]\n116it [00:13, 5.40it/s]\n117it [00:13, 5.40it/s]\n118it [00:13, 5.40it/s]\n119it [00:13, 5.40it/s]\n120it [00:14, 5.39it/s]\n121it [00:14, 5.40it/s]\n122it [00:14, 5.40it/s]\n123it [00:14, 5.40it/s]\n124it [00:14, 5.41it/s]\n125it [00:15, 5.40it/s]\n126it [00:15, 5.40it/s]\n127it [00:15, 5.40it/s]\n128it [00:15, 5.40it/s]\n129it [00:15, 5.41it/s]\n130it [00:15, 8.21it/s]\nGenerating random point cloud (81920)...[22/12 16:20:16]\nNumber of points at initialisation : 81920 [22/12 16:20:16]\ntrain_process is in : ./output/Replicate/train_process/ [22/12 16:20:16]\n[INFO] loading stable diffusion... [22/12 16:20:19]\n[INFO] loaded stable diffusion! [22/12 16:20:21]\ntest views is in : ./output/Replicate/test_six_views/1_iteration [22/12 16:20:37]\n[ITER 1] Eval Done! [22/12 16:20:38]\nvideos is in : ./output/Replicate/videos/1_iteration[22/12 16:20:38]\nGenerating Video using 240 different view points[22/12 16:20:44]\n[ITER 1] Video Save Done! [22/12 16:20:46]\nTraining progress: 0%| | 0/1000 [00:00<?, ?it/s]\nTraining progress: 0%| | 0/1000 [00:32<?, ?it/s, Loss=1.0007480]\nTraining progress: 1%| | 10/1000 [00:32<54:10, 3.28s/it, Loss=1.0007480]\nTraining progress: 1%| | 10/1000 [00:41<54:10, 3.28s/it, Loss=1.0067991]\nTraining progress: 2%|▏ | 20/1000 [00:41<30:05, 1.84s/it, Loss=1.0067991]\nTraining progress: 2%|▏ | 20/1000 [00:49<30:05, 1.84s/it, Loss=1.0068357]\nTraining progress: 3%|▎ | 30/1000 [00:49<22:18, 1.38s/it, Loss=1.0068357]\nTraining progress: 3%|▎ | 30/1000 [00:58<22:18, 1.38s/it, Loss=1.0068359]\nTraining progress: 4%|▍ | 40/1000 [00:58<18:56, 1.18s/it, Loss=1.0068359]\nTraining progress: 4%|▍ | 40/1000 [01:06<18:56, 1.18s/it, Loss=1.0068359]\nTraining progress: 5%|▌ | 50/1000 [01:06<16:35, 1.05s/it, Loss=1.0068359]\nTraining progress: 5%|▌ | 50/1000 [01:15<16:35, 1.05s/it, Loss=1.0068359]\nTraining progress: 6%|▌ | 60/1000 [01:15<15:31, 1.01it/s, Loss=1.0068359]\nTraining progress: 6%|▌ | 60/1000 [01:23<15:31, 1.01it/s, Loss=1.0070703]\nTraining progress: 7%|▋ | 70/1000 [01:23<14:21, 1.08it/s, Loss=1.0070703]\nTraining progress: 7%|▋ | 70/1000 [01:31<14:21, 1.08it/s, Loss=1.0069780]\nTraining progress: 8%|▊ | 80/1000 [01:31<13:56, 1.10it/s, Loss=1.0069780]\nTraining progress: 8%|▊ | 80/1000 [01:39<13:56, 1.10it/s, Loss=1.0069023]\nTraining progress: 9%|▉ | 90/1000 [01:39<13:20, 1.14it/s, Loss=1.0069023]\nTraining progress: 9%|▉ | 90/1000 [01:48<13:20, 1.14it/s, Loss=1.0072865]\nTraining progress: 10%|█ | 100/1000 [01:48<13:16, 1.13it/s, Loss=1.0072865]\nTraining progress: 10%|█ | 100/1000 [01:56<13:16, 1.13it/s, Loss=1.0071143]\nTraining progress: 11%|█ | 110/1000 [01:56<12:43, 1.17it/s, Loss=1.0071143]\nTraining progress: 11%|█ | 110/1000 [02:05<12:43, 1.17it/s, Loss=1.0075922]\nTraining progress: 12%|█▏ | 120/1000 [02:05<12:31, 1.17it/s, Loss=1.0075922]\nTraining progress: 12%|█▏ | 120/1000 [02:13<12:31, 1.17it/s, Loss=1.0075768]\nTraining progress: 13%|█▎ | 130/1000 [02:13<12:18, 1.18it/s, Loss=1.0075768]\nTraining progress: 13%|█▎ | 130/1000 [02:22<12:18, 1.18it/s, Loss=1.0073698]\nTraining progress: 14%|█▍ | 140/1000 [02:22<12:06, 1.18it/s, Loss=1.0073698]\nTraining progress: 14%|█▍ | 140/1000 [02:30<12:06, 1.18it/s, Loss=1.0078098]\nTraining progress: 15%|█▌ | 150/1000 [02:30<11:52, 1.19it/s, Loss=1.0078098]\nTraining progress: 15%|█▌ | 150/1000 [02:38<11:52, 1.19it/s, Loss=1.0077821]\nTraining progress: 16%|█▌ | 160/1000 [02:38<11:28, 1.22it/s, Loss=1.0077821]\nTraining progress: 16%|█▌ | 160/1000 [02:46<11:28, 1.22it/s, Loss=1.0078123]\nTraining progress: 17%|█▋ | 170/1000 [02:46<11:28, 1.21it/s, Loss=1.0078123]\nTraining progress: 17%|█▋ | 170/1000 [02:55<11:28, 1.21it/s, Loss=1.0078125]\nTraining progress: 18%|█▊ | 180/1000 [02:55<11:43, 1.17it/s, Loss=1.0078125]\nTraining progress: 18%|█▊ | 180/1000 [03:03<11:43, 1.17it/s, Loss=1.0078086]\nTraining progress: 19%|█▉ | 190/1000 [03:03<11:18, 1.19it/s, Loss=1.0078086]\nTraining progress: 19%|█▉ | 190/1000 [03:12<11:18, 1.19it/s, Loss=1.0078125]\ntest views is in : ./output/Replicate/test_six_views/200_iteration [22/12 16:23:34]\n[ITER 200] Eval Done! [22/12 16:23:35]\nvideos is in : ./output/Replicate/videos/200_iteration [22/12 16:23:35]\nGenerating Video using 240 different view points [22/12 16:23:40]\n[ITER 200] Video Save Done! [22/12 16:23:43]\nTraining progress: 20%|██ | 200/1000 [03:12<11:30, 1.16it/s, Loss=1.0078125]\nTraining progress: 20%|██ | 200/1000 [03:30<11:30, 1.16it/s, Loss=1.0080375]\nTraining progress: 21%|██ | 210/1000 [03:30<14:45, 1.12s/it, Loss=1.0080375]\nTraining progress: 21%|██ | 210/1000 [03:38<14:45, 1.12s/it, Loss=1.0080179]\nTraining progress: 22%|██▏ | 220/1000 [03:38<13:33, 1.04s/it, Loss=1.0080179]\nTraining progress: 22%|██▏ | 220/1000 [03:47<13:33, 1.04s/it, Loss=1.0082394]\nTraining progress: 23%|██▎ | 230/1000 [03:47<12:37, 1.02it/s, Loss=1.0082394]\nTraining progress: 23%|██▎ | 230/1000 [03:55<12:37, 1.02it/s, Loss=1.0084688]\nTraining progress: 24%|██▍ | 240/1000 [03:55<11:56, 1.06it/s, Loss=1.0084688]\nTraining progress: 24%|██▍ | 240/1000 [04:03<11:56, 1.06it/s, Loss=1.0078165]\nTraining progress: 25%|██▌ | 250/1000 [04:03<11:20, 1.10it/s, Loss=1.0078165]\nTraining progress: 25%|██▌ | 250/1000 [04:12<11:20, 1.10it/s, Loss=1.0083477]\nTraining progress: 26%|██▌ | 260/1000 [04:12<10:56, 1.13it/s, Loss=1.0083477]\nTraining progress: 26%|██▌ | 260/1000 [04:20<10:56, 1.13it/s, Loss=1.0079507]\nTraining progress: 27%|██▋ | 270/1000 [04:20<10:38, 1.14it/s, Loss=1.0079507]\nTraining progress: 27%|██▋ | 270/1000 [04:30<10:38, 1.14it/s, Loss=1.0079588]\nTraining progress: 28%|██▊ | 280/1000 [04:30<10:47, 1.11it/s, Loss=1.0079588]\nTraining progress: 28%|██▊ | 280/1000 [04:39<10:47, 1.11it/s, Loss=1.0084979]\nTraining progress: 29%|██▉ | 290/1000 [04:39<10:34, 1.12it/s, Loss=1.0084979]\nTraining progress: 29%|██▉ | 290/1000 [04:48<10:34, 1.12it/s, Loss=1.0079069]\nTraining progress: 30%|███ | 300/1000 [04:48<10:29, 1.11it/s, Loss=1.0079069]\nTraining progress: 30%|███ | 300/1000 [04:56<10:29, 1.11it/s, Loss=1.0096953]\nTraining progress: 31%|███ | 310/1000 [04:56<10:10, 1.13it/s, Loss=1.0096953]\nTraining progress: 31%|███ | 310/1000 [05:05<10:10, 1.13it/s, Loss=1.0105446]\nTraining progress: 32%|███▏ | 320/1000 [05:05<09:58, 1.14it/s, Loss=1.0105446]\nTraining progress: 32%|███▏ | 320/1000 [05:14<09:58, 1.14it/s, Loss=1.0109520]\nTraining progress: 33%|███▎ | 330/1000 [05:14<09:44, 1.15it/s, Loss=1.0109520]\nTraining progress: 33%|███▎ | 330/1000 [05:22<09:44, 1.15it/s, Loss=1.0107435]\nTraining progress: 34%|███▍ | 340/1000 [05:22<09:28, 1.16it/s, Loss=1.0107435]\nTraining progress: 34%|███▍ | 340/1000 [05:30<09:28, 1.16it/s, Loss=1.0114516]\nTraining progress: 35%|███▌ | 350/1000 [05:30<09:14, 1.17it/s, Loss=1.0114516]\nTraining progress: 35%|███▌ | 350/1000 [05:39<09:14, 1.17it/s, Loss=1.0105843]\nTraining progress: 36%|███▌ | 360/1000 [05:39<09:06, 1.17it/s, Loss=1.0105843]\nTraining progress: 36%|███▌ | 360/1000 [05:48<09:06, 1.17it/s, Loss=1.0101097]\nTraining progress: 37%|███▋ | 370/1000 [05:48<09:00, 1.17it/s, Loss=1.0101097]\nTraining progress: 37%|███▋ | 370/1000 [05:56<09:00, 1.17it/s, Loss=1.0092723]\nTraining progress: 38%|███▊ | 380/1000 [05:56<08:46, 1.18it/s, Loss=1.0092723]\nTraining progress: 38%|███▊ | 380/1000 [06:04<08:46, 1.18it/s, Loss=1.0114264]\nTraining progress: 39%|███▉ | 390/1000 [06:04<08:27, 1.20it/s, Loss=1.0114264]\nTraining progress: 39%|███▉ | 390/1000 [06:14<08:27, 1.20it/s, Loss=1.0102742]\ntest views is in : ./output/Replicate/test_six_views/400_iteration [22/12 16:26:35]\n[ITER 400] Eval Done! [22/12 16:26:36]\nvideos is in : ./output/Replicate/videos/400_iteration [22/12 16:26:36]\nGenerating Video using 240 different view points [22/12 16:26:42]\n[ITER 400] Video Save Done! [22/12 16:26:45]\nTraining progress: 40%|████ | 400/1000 [06:14<08:52, 1.13it/s, Loss=1.0102742]\nTraining progress: 40%|████ | 400/1000 [06:32<08:52, 1.13it/s, Loss=1.0089330]\nTraining progress: 41%|████ | 410/1000 [06:32<11:19, 1.15s/it, Loss=1.0089330]\nTraining progress: 41%|████ | 410/1000 [06:41<11:19, 1.15s/it, Loss=1.0094149]\nTraining progress: 42%|████▏ | 420/1000 [06:41<10:27, 1.08s/it, Loss=1.0094149]\nTraining progress: 42%|████▏ | 420/1000 [06:49<10:27, 1.08s/it, Loss=1.0089874]\nTraining progress: 43%|████▎ | 430/1000 [06:49<09:38, 1.02s/it, Loss=1.0089874]\nTraining progress: 43%|████▎ | 430/1000 [06:58<09:38, 1.02s/it, Loss=1.0094367]\nTraining progress: 44%|████▍ | 440/1000 [06:58<09:06, 1.02it/s, Loss=1.0094367]\nTraining progress: 44%|████▍ | 440/1000 [07:06<09:06, 1.02it/s, Loss=1.0085691]\nTraining progress: 45%|████▌ | 450/1000 [07:06<08:32, 1.07it/s, Loss=1.0085691]\nTraining progress: 45%|████▌ | 450/1000 [07:15<08:32, 1.07it/s, Loss=1.0100140]\nTraining progress: 46%|████▌ | 460/1000 [07:15<08:07, 1.11it/s, Loss=1.0100140]\nTraining progress: 46%|████▌ | 460/1000 [07:23<08:07, 1.11it/s, Loss=1.0095660]\nTraining progress: 47%|████▋ | 470/1000 [07:23<07:44, 1.14it/s, Loss=1.0095660]\nTraining progress: 47%|████▋ | 470/1000 [07:31<07:44, 1.14it/s, Loss=1.0088043]\nTraining progress: 48%|████▊ | 480/1000 [07:31<07:27, 1.16it/s, Loss=1.0088043]\nTraining progress: 48%|████▊ | 480/1000 [07:40<07:27, 1.16it/s, Loss=1.0089837]\nscale up theta_range to: [60, 90] [22/12 16:28:09]\nscale up radius_range to: [4.9399999999999995, 5.225] [22/12 16:28:09]\nscale up phi_range to: [-180, 180] [22/12 16:28:09]\nscale up fovy_range to: [0.24, 0.6] [22/12 16:28:09]\nTraining progress: 49%|████▉ | 490/1000 [07:40<07:22, 1.15it/s, Loss=1.0089837]\nTraining progress: 49%|████▉ | 490/1000 [07:51<07:22, 1.15it/s, Loss=1.0090351]\n[ITER 500] Saving Gaussians [22/12 16:28:12]\nTraining progress: 50%|█████ | 500/1000 [07:51<07:40, 1.09it/s, Loss=1.0090351]\nTraining progress: 50%|█████ | 500/1000 [08:02<07:40, 1.09it/s, Loss=1.0090662]\nTraining progress: 51%|█████ | 510/1000 [08:02<08:10, 1.00s/it, Loss=1.0090662]\nTraining progress: 51%|█████ | 510/1000 [08:11<08:10, 1.00s/it, Loss=1.0097691]\nTraining progress: 52%|█████▏ | 520/1000 [08:11<07:40, 1.04it/s, Loss=1.0097691]\nTraining progress: 52%|█████▏ | 520/1000 [08:20<07:40, 1.04it/s, Loss=1.0095495]\nTraining progress: 53%|█████▎ | 530/1000 [08:20<07:18, 1.07it/s, Loss=1.0095495]\nTraining progress: 53%|█████▎ | 530/1000 [08:28<07:18, 1.07it/s, Loss=1.0098791]\nTraining progress: 54%|█████▍ | 540/1000 [08:28<07:00, 1.09it/s, Loss=1.0098791]\nTraining progress: 54%|█████▍ | 540/1000 [08:37<07:00, 1.09it/s, Loss=1.0095788]\nTraining progress: 55%|█████▌ | 550/1000 [08:37<06:41, 1.12it/s, Loss=1.0095788]\nTraining progress: 55%|█████▌ | 550/1000 [08:46<06:41, 1.12it/s, Loss=1.0097192]\nTraining progress: 56%|█████▌ | 560/1000 [08:46<06:36, 1.11it/s, Loss=1.0097192]\nTraining progress: 56%|█████▌ | 560/1000 [08:55<06:36, 1.11it/s, Loss=1.0096953]\nTraining progress: 57%|█████▋ | 570/1000 [08:55<06:30, 1.10it/s, Loss=1.0096953]\nTraining progress: 57%|█████▋ | 570/1000 [09:04<06:30, 1.10it/s, Loss=1.0092266]\nTraining progress: 58%|█████▊ | 580/1000 [09:04<06:12, 1.13it/s, Loss=1.0092266]\nTraining progress: 58%|█████▊ | 580/1000 [09:12<06:12, 1.13it/s, Loss=1.0090673]\nTraining progress: 59%|█████▉ | 590/1000 [09:12<06:02, 1.13it/s, Loss=1.0090673]\nTraining progress: 59%|█████▉ | 590/1000 [09:22<06:02, 1.13it/s, Loss=1.0089094]\ntest views is in : ./output/Replicate/test_six_views/600_iteration[22/12 16:29:43]\n[ITER 600] Eval Done! [22/12 16:29:44]\nvideos is in : ./output/Replicate/videos/600_iteration [22/12 16:29:44]\nGenerating Video using 240 different view points[22/12 16:29:50]\n[ITER 600] Video Save Done! [22/12 16:29:54]\nTraining progress: 60%|██████ | 600/1000 [09:22<06:03, 1.10it/s, Loss=1.0089094]\nTraining progress: 60%|██████ | 600/1000 [09:41<06:03, 1.10it/s, Loss=1.0130514]\nTraining progress: 61%|██████ | 610/1000 [09:41<07:52, 1.21s/it, Loss=1.0130514]\nTraining progress: 61%|██████ | 610/1000 [09:50<07:52, 1.21s/it, Loss=1.0110758]\nTraining progress: 62%|██████▏ | 620/1000 [09:50<07:05, 1.12s/it, Loss=1.0110758]\nTraining progress: 62%|██████▏ | 620/1000 [09:59<07:05, 1.12s/it, Loss=1.0103461]\nTraining progress: 63%|██████▎ | 630/1000 [09:59<06:29, 1.05s/it, Loss=1.0103461]\nTraining progress: 63%|██████▎ | 630/1000 [10:08<06:29, 1.05s/it, Loss=1.0108610]\nTraining progress: 64%|██████▍ | 640/1000 [10:08<05:58, 1.01it/s, Loss=1.0108610]\nTraining progress: 64%|██████▍ | 640/1000 [10:16<05:58, 1.01it/s, Loss=1.0109771]\nTraining progress: 65%|██████▌ | 650/1000 [10:16<05:33, 1.05it/s, Loss=1.0109771]\nTraining progress: 65%|██████▌ | 650/1000 [10:25<05:33, 1.05it/s, Loss=1.0098803]\nTraining progress: 66%|██████▌ | 660/1000 [10:25<05:14, 1.08it/s, Loss=1.0098803]\nTraining progress: 66%|██████▌ | 660/1000 [10:34<05:14, 1.08it/s, Loss=1.0106163]\nTraining progress: 67%|██████▋ | 670/1000 [10:34<04:57, 1.11it/s, Loss=1.0106163]\nTraining progress: 67%|██████▋ | 670/1000 [10:43<04:57, 1.11it/s, Loss=1.0092700]\nTraining progress: 68%|██████▊ | 680/1000 [10:43<04:50, 1.10it/s, Loss=1.0092700]\nTraining progress: 68%|██████▊ | 680/1000 [10:51<04:50, 1.10it/s, Loss=1.0107625]\nTraining progress: 69%|██████▉ | 690/1000 [10:51<04:38, 1.11it/s, Loss=1.0107625]\nTraining progress: 69%|██████▉ | 690/1000 [11:01<04:38, 1.11it/s, Loss=1.0095968]\nTraining progress: 70%|███████ | 700/1000 [11:01<04:35, 1.09it/s, Loss=1.0095968]\nTraining progress: 70%|███████ | 700/1000 [11:10<04:35, 1.09it/s, Loss=1.0102746]\nTraining progress: 71%|███████ | 710/1000 [11:10<04:27, 1.09it/s, Loss=1.0102746]\nTraining progress: 71%|███████ | 710/1000 [11:19<04:27, 1.09it/s, Loss=1.0102181]\nTraining progress: 72%|███████▏ | 720/1000 [11:19<04:16, 1.09it/s, Loss=1.0102181]\nTraining progress: 72%|███████▏ | 720/1000 [11:28<04:16, 1.09it/s, Loss=1.0097177]\nTraining progress: 73%|███████▎ | 730/1000 [11:28<04:03, 1.11it/s, Loss=1.0097177]\nTraining progress: 73%|███████▎ | 730/1000 [11:37<04:03, 1.11it/s, Loss=1.0097081]\nTraining progress: 74%|███████▍ | 740/1000 [11:37<03:50, 1.13it/s, Loss=1.0097081]\nTraining progress: 74%|███████▍ | 740/1000 [11:45<03:50, 1.13it/s, Loss=1.0099252]\nTraining progress: 75%|███████▌ | 750/1000 [11:45<03:41, 1.13it/s, Loss=1.0099252]\nTraining progress: 75%|███████▌ | 750/1000 [11:54<03:41, 1.13it/s, Loss=1.0111279]\nTraining progress: 76%|███████▌ | 760/1000 [11:54<03:30, 1.14it/s, Loss=1.0111279]\nTraining progress: 76%|███████▌ | 760/1000 [12:03<03:30, 1.14it/s, Loss=1.0101377]\nTraining progress: 77%|███████▋ | 770/1000 [12:03<03:19, 1.15it/s, Loss=1.0101377]\nTraining progress: 77%|███████▋ | 770/1000 [12:11<03:19, 1.15it/s, Loss=1.0106392]\nTraining progress: 78%|███████▊ | 780/1000 [12:11<03:07, 1.17it/s, Loss=1.0106392]\nTraining progress: 78%|███████▊ | 780/1000 [12:19<03:07, 1.17it/s, Loss=1.0102619]\nTraining progress: 79%|███████▉ | 790/1000 [12:19<02:58, 1.17it/s, Loss=1.0102619]\nTraining progress: 79%|███████▉ | 790/1000 [12:29<02:58, 1.17it/s, Loss=1.0111697]\ntest views is in : ./output/Replicate/test_six_views/800_iteration [22/12 16:32:50]\n[ITER 800] Eval Done! [22/12 16:32:51]\nvideos is in : ./output/Replicate/videos/800_iteration[22/12 16:32:51]\nGenerating Video using 240 different view points [22/12 16:32:57]\n[ITER 800] Video Save Done! [22/12 16:33:01]\nTraining progress: 80%|████████ | 800/1000 [12:29<02:55, 1.14it/s, Loss=1.0111697]\nTraining progress: 80%|████████ | 800/1000 [12:48<02:55, 1.14it/s, Loss=1.0114215]\nTraining progress: 81%|████████ | 810/1000 [12:48<03:46, 1.19s/it, Loss=1.0114215]\nTraining progress: 81%|████████ | 810/1000 [12:57<03:46, 1.19s/it, Loss=1.0098516]\nTraining progress: 82%|████████▏ | 820/1000 [12:57<03:21, 1.12s/it, Loss=1.0098516]\nTraining progress: 82%|████████▏ | 820/1000 [13:06<03:21, 1.12s/it, Loss=1.0106504]\nTraining progress: 83%|████████▎ | 830/1000 [13:06<02:56, 1.04s/it, Loss=1.0106504]\nTraining progress: 83%|████████▎ | 830/1000 [13:15<02:56, 1.04s/it, Loss=1.0098756]\nTraining progress: 84%|████████▍ | 840/1000 [13:15<02:39, 1.01it/s, Loss=1.0098756]\nTraining progress: 84%|████████▍ | 840/1000 [13:23<02:39, 1.01it/s, Loss=1.0107513]\nTraining progress: 85%|████████▌ | 850/1000 [13:23<02:22, 1.05it/s, Loss=1.0107513]\nTraining progress: 85%|████████▌ | 850/1000 [13:32<02:22, 1.05it/s, Loss=1.0114682]\nTraining progress: 86%|████████▌ | 860/1000 [13:32<02:09, 1.08it/s, Loss=1.0114682]\nTraining progress: 86%|████████▌ | 860/1000 [13:41<02:09, 1.08it/s, Loss=1.0098460]\nTraining progress: 87%|████████▋ | 870/1000 [13:41<01:57, 1.10it/s, Loss=1.0098460]\nTraining progress: 87%|████████▋ | 870/1000 [13:49<01:57, 1.10it/s, Loss=1.0104150]\nTraining progress: 88%|████████▊ | 880/1000 [13:49<01:45, 1.14it/s, Loss=1.0104150]\nTraining progress: 88%|████████▊ | 880/1000 [13:57<01:45, 1.14it/s, Loss=1.0103430]\nTraining progress: 89%|████████▉ | 890/1000 [13:57<01:35, 1.15it/s, Loss=1.0103430]\nTraining progress: 89%|████████▉ | 890/1000 [14:07<01:35, 1.15it/s, Loss=1.0112264]\nTraining progress: 90%|█████████ | 900/1000 [14:07<01:28, 1.13it/s, Loss=1.0112264]\nTraining progress: 90%|█████████ | 900/1000 [14:16<01:28, 1.13it/s, Loss=1.0153764]\nTraining progress: 91%|█████████ | 910/1000 [14:16<01:21, 1.11it/s, Loss=1.0153764]\nTraining progress: 91%|█████████ | 910/1000 [14:25<01:21, 1.11it/s, Loss=1.0135635]\nTraining progress: 92%|█████████▏| 920/1000 [14:25<01:11, 1.11it/s, Loss=1.0135635]\nTraining progress: 92%|█████████▏| 920/1000 [14:34<01:11, 1.11it/s, Loss=1.0099341]\nTraining progress: 93%|█████████▎| 930/1000 [14:34<01:04, 1.09it/s, Loss=1.0099341]\nTraining progress: 93%|█████████▎| 930/1000 [14:43<01:04, 1.09it/s, Loss=1.0107898]\nTraining progress: 94%|█████████▍| 940/1000 [14:43<00:54, 1.10it/s, Loss=1.0107898]\nTraining progress: 94%|█████████▍| 940/1000 [14:52<00:54, 1.10it/s, Loss=1.0116342]\nTraining progress: 95%|█████████▌| 950/1000 [14:52<00:44, 1.11it/s, Loss=1.0116342]\nTraining progress: 95%|█████████▌| 950/1000 [15:01<00:44, 1.11it/s, Loss=1.0102147]\nTraining progress: 96%|█████████▌| 960/1000 [15:01<00:35, 1.12it/s, Loss=1.0102147]\nTraining progress: 96%|█████████▌| 960/1000 [15:10<00:35, 1.12it/s, Loss=1.0102574]\nTraining progress: 97%|█████████▋| 970/1000 [15:10<00:26, 1.13it/s, Loss=1.0102574]\nTraining progress: 97%|█████████▋| 970/1000 [15:18<00:26, 1.13it/s, Loss=1.0106889]\nTraining progress: 98%|█████████▊| 980/1000 [15:18<00:17, 1.15it/s, Loss=1.0106889]\nTraining progress: 98%|█████████▊| 980/1000 [15:27<00:17, 1.15it/s, Loss=1.0106823]\nscale up theta_range to: [60, 90][22/12 16:35:56]\nscale up radius_range to: [4.693, 5.0] [22/12 16:35:56]\nscale up phi_range to: [-180, 180] [22/12 16:35:56]\nscale up fovy_range to: [0.18, 0.6] [22/12 16:35:56]\nTraining progress: 99%|█████████▉| 990/1000 [15:27<00:08, 1.15it/s, Loss=1.0106823]\nTraining progress: 99%|█████████▉| 990/1000 [15:36<00:08, 1.15it/s, Loss=1.0103620]\nTraining progress: 100%|██████████| 1000/1000 [15:36<00:00, 1.12it/s, Loss=1.0103620]\nTraining progress: 100%|██████████| 1000/1000 [15:36<00:00, 1.07it/s, Loss=1.0103620]\ntest views is in : ./output/Replicate/test_six_views/1000_iteration[22/12 16:35:57]\n[ITER 1000] Eval Done! [22/12 16:35:58]\nvideos is in : ./output/Replicate/videos/1000_iteration[22/12 16:35:58]\nGenerating Video using 240 different view points[22/12 16:36:04]\n[ITER 1000] Video Save Done! [22/12 16:36:09]\n[ITER 1000] Saving Gaussians [22/12 16:36:09]\nTraining complete. [22/12 16:36:23]", "metrics": { "predict_time": 1044.437889, "total_time": 1209.745758 }, "output": [ "https://replicate.delivery/pbxt/A69Rs2vU8yLVA9fQG4MPqkAAiu3swCeJT1N5oOUeIqETotJkA/video_rgb_1000.mp4", "https://replicate.delivery/pbxt/ZLOstxKEQXrqIp40NregSrrG4dzF9usYlUU9uZhrqQrJabCJA/video_rgb.mp4" ], "started_at": "2023-12-22T16:19:11.760014Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/shgrpndbki7cyyurxrvyry374m", "cancel": "https://api.replicate.com/v1/predictions/shgrpndbki7cyyurxrvyry374m/cancel" }, "version": "fbf8e0dfef4ca0c0de45cf1afbf12c81667ee29fd79852852262aee4f167fbf5" }Generated inUsing seed: 1156556824 Test iter: [1, 200, 400, 600, 800, 1000] Save iter: [500, 1000] Optimizing Output folder: ./output/Replicate[22/12 16:19:13] Tensorboard not available: not logging progress [22/12 16:19:13] Reading Test Transforms [22/12 16:19:13] creating base model... [22/12 16:19:13] 0%| | 0.00/890M [00:00<?, ?iB/s] 0%|▏ | 3.88M/890M [00:00<00:23, 40.4MiB/s] 1%|▎ | 7.73M/890M [00:00<00:24, 37.4MiB/s] 1%|▌ | 12.8M/890M [00:00<00:21, 43.7MiB/s] 2%|▋ | 17.0M/890M [00:00<00:21, 43.1MiB/s] 2%|▉ | 22.0M/890M [00:00<00:21, 42.4MiB/s] 3%|█▏ | 26.5M/890M [00:00<00:20, 43.7MiB/s] 3%|█▎ | 30.7M/890M [00:00<00:21, 42.2MiB/s] 4%|█▌ | 35.7M/890M [00:00<00:19, 45.1MiB/s] 5%|█▋ | 40.4M/890M [00:00<00:19, 46.3MiB/s] 5%|█▉ | 45.4M/890M [00:01<00:18, 48.1MiB/s] 6%|██▏ | 50.0M/890M [00:01<00:18, 48.0MiB/s] 6%|██▎ | 54.6M/890M [00:01<00:19, 46.1MiB/s] 7%|██▌ | 59.5M/890M [00:01<00:18, 47.5MiB/s] 7%|██▋ | 64.0M/890M [00:01<00:19, 45.4MiB/s] 8%|██▉ | 69.9M/890M [00:01<00:17, 50.0MiB/s] 8%|███▏ | 74.7M/890M [00:01<00:17, 47.6MiB/s] 9%|███▍ | 80.0M/890M [00:01<00:17, 49.4MiB/s] 10%|███▋ | 85.0M/890M [00:01<00:16, 50.0MiB/s] 10%|███▊ | 90.1M/890M [00:02<00:16, 50.8MiB/s] 11%|████ | 95.0M/890M [00:02<00:16, 49.7MiB/s] 11%|████▍ | 100M/890M [00:02<00:16, 49.2MiB/s] 12%|████▌ | 105M/890M [00:02<00:18, 45.7MiB/s] 12%|████▊ | 110M/890M [00:02<00:17, 47.7MiB/s] 13%|█████ | 115M/890M [00:02<00:16, 49.2MiB/s] 13%|█████▎ | 120M/890M [00:02<00:16, 49.5MiB/s] 14%|█████▍ | 125M/890M [00:02<00:15, 50.8MiB/s] 15%|█████▋ | 130M/890M [00:02<00:16, 47.9MiB/s] 15%|█████▉ | 135M/890M [00:02<00:16, 47.4MiB/s] 16%|██████▏ | 140M/890M [00:03<00:15, 50.1MiB/s] 16%|██████▎ | 145M/890M [00:03<00:15, 50.5MiB/s] 17%|██████▌ | 150M/890M [00:03<00:16, 47.5MiB/s] 17%|██████▊ | 154M/890M [00:03<00:16, 45.4MiB/s] 18%|██████▉ | 159M/890M [00:03<00:16, 46.0MiB/s] 18%|███████▏ | 164M/890M [00:03<00:15, 48.7MiB/s] 19%|███████▍ | 170M/890M [00:03<00:14, 51.1MiB/s] 20%|███████▋ | 176M/890M [00:03<00:13, 53.6MiB/s] 20%|███████▉ | 181M/890M [00:03<00:14, 52.0MiB/s] 21%|████████▏ | 186M/890M [00:04<00:14, 52.4MiB/s] 21%|████████▎ | 191M/890M [00:04<00:14, 52.2MiB/s] 22%|████████▌ | 196M/890M [00:04<00:13, 52.6MiB/s] 23%|████████▊ | 201M/890M [00:04<00:13, 53.3MiB/s] 23%|█████████ | 207M/890M [00:04<00:13, 54.7MiB/s] 24%|█████████▎ | 212M/890M [00:04<00:13, 52.0MiB/s] 24%|█████████▌ | 217M/890M [00:04<00:13, 51.0MiB/s] 25%|█████████▋ | 222M/890M [00:04<00:13, 51.3MiB/s] 26%|█████████▉ | 227M/890M [00:04<00:13, 51.9MiB/s] 26%|██████████▏ | 232M/890M [00:05<00:15, 45.7MiB/s] 27%|██████████▍ | 237M/890M [00:05<00:14, 47.0MiB/s] 27%|██████████▌ | 242M/890M [00:05<00:14, 45.4MiB/s] 28%|██████████▊ | 247M/890M [00:05<00:14, 47.7MiB/s] 28%|███████████ | 252M/890M [00:05<00:13, 49.7MiB/s] 29%|███████████▍ | 260M/890M [00:05<00:11, 58.7MiB/s] 30%|███████████▋ | 268M/890M [00:05<00:10, 64.6MiB/s] 31%|████████████ | 274M/890M [00:05<00:10, 60.3MiB/s] 31%|████████████▎ | 280M/890M [00:05<00:12, 51.5MiB/s] 32%|████████████▍ | 285M/890M [00:06<00:12, 49.7MiB/s] 33%|████████████▋ | 290M/890M [00:06<00:14, 42.0MiB/s] 33%|████████████▉ | 294M/890M [00:06<00:15, 39.3MiB/s] 34%|█████████████ | 298M/890M [00:06<00:15, 40.8MiB/s] 34%|█████████████▎ | 303M/890M [00:06<00:14, 41.4MiB/s] 35%|█████████████▌ | 308M/890M [00:06<00:13, 45.5MiB/s] 35%|█████████████▋ | 313M/890M [00:06<00:12, 48.0MiB/s] 36%|█████████████▉ | 319M/890M [00:06<00:12, 49.4MiB/s] 36%|██████████████▏ | 323M/890M [00:06<00:11, 49.7MiB/s] 37%|██████████████▍ | 329M/890M [00:07<00:11, 51.8MiB/s] 38%|██████████████▋ | 334M/890M [00:07<00:10, 53.0MiB/s] 38%|██████████████▉ | 339M/890M [00:07<00:10, 52.6MiB/s] 39%|███████████████ | 344M/890M [00:07<00:10, 52.4MiB/s] 39%|███████████████▎ | 350M/890M [00:07<00:10, 53.8MiB/s] 40%|███████████████▌ | 355M/890M [00:07<00:10, 52.2MiB/s] 40%|███████████████▊ | 360M/890M [00:07<00:11, 48.6MiB/s] 41%|████████████████ | 365M/890M [00:07<00:10, 50.2MiB/s] 42%|████████████████▏ | 370M/890M [00:07<00:10, 51.0MiB/s] 42%|████████████████▍ | 375M/890M [00:08<00:10, 49.1MiB/s] 43%|████████████████▋ | 380M/890M [00:08<00:14, 37.9MiB/s] 43%|████████████████▉ | 385M/890M [00:08<00:12, 41.6MiB/s] 44%|█████████████████ | 390M/890M [00:08<00:11, 44.2MiB/s] 44%|█████████████████▎ | 395M/890M [00:08<00:11, 43.8MiB/s] 45%|█████████████████▌ | 400M/890M [00:08<00:11, 46.5MiB/s] 46%|█████████████████▊ | 405M/890M [00:08<00:10, 49.1MiB/s] 46%|█████████████████▉ | 410M/890M [00:08<00:10, 50.0MiB/s] 47%|██████████████████▏ | 415M/890M [00:08<00:10, 49.7MiB/s] 47%|██████████████████▍ | 420M/890M [00:09<00:09, 50.0MiB/s] 48%|██████████████████▋ | 425M/890M [00:09<00:14, 34.2MiB/s] 48%|██████████████████▊ | 430M/890M [00:09<00:12, 37.9MiB/s] 49%|███████████████████ | 434M/890M [00:09<00:12, 39.4MiB/s] 49%|███████████████████▏ | 438M/890M [00:09<00:11, 40.6MiB/s] 50%|███████████████████▍ | 443M/890M [00:09<00:11, 41.6MiB/s] 50%|███████████████████▌ | 448M/890M [00:09<00:10, 44.2MiB/s] 51%|███████████████████▊ | 453M/890M [00:09<00:09, 46.8MiB/s] 51%|████████████████████ | 458M/890M [00:10<00:09, 48.3MiB/s] 52%|████████████████████▎ | 463M/890M [00:10<00:08, 51.3MiB/s] 53%|████████████████████▌ | 468M/890M [00:10<00:08, 50.2MiB/s] 53%|████████████████████▋ | 473M/890M [00:10<00:08, 50.5MiB/s] 54%|████████████████████▉ | 478M/890M [00:10<00:08, 51.6MiB/s] 54%|█████████████████████▏ | 484M/890M [00:10<00:08, 53.0MiB/s] 55%|█████████████████████▍ | 489M/890M [00:10<00:07, 53.7MiB/s] 56%|█████████████████████▋ | 495M/890M [00:10<00:07, 54.2MiB/s] 56%|█████████████████████▉ | 500M/890M [00:10<00:08, 50.2MiB/s] 57%|██████████████████████ | 505M/890M [00:10<00:08, 49.8MiB/s] 57%|██████████████████████▎ | 510M/890M [00:11<00:07, 51.0MiB/s] 58%|██████████████████████▌ | 515M/890M [00:11<00:07, 50.3MiB/s] 58%|██████████████████████▊ | 520M/890M [00:11<00:07, 51.0MiB/s] 59%|███████████████████████ | 525M/890M [00:11<00:07, 51.2MiB/s] 60%|███████████████████████▏ | 530M/890M [00:11<00:07, 51.3MiB/s] 60%|███████████████████████▍ | 535M/890M [00:11<00:07, 51.3MiB/s] 61%|███████████████████████▋ | 540M/890M [00:11<00:07, 51.4MiB/s] 61%|███████████████████████▉ | 545M/890M [00:11<00:06, 51.9MiB/s] 62%|████████████████████████ | 550M/890M [00:11<00:06, 51.7MiB/s] 63%|████████████████████████▍ | 559M/890M [00:12<00:05, 64.6MiB/s] 63%|████████████████████████▊ | 565M/890M [00:12<00:05, 64.1MiB/s] 64%|█████████████████████████ | 571M/890M [00:12<00:05, 60.6MiB/s] 65%|█████████████████████████▎ | 577M/890M [00:12<00:05, 55.2MiB/s] 65%|█████████████████████████▌ | 582M/890M [00:12<00:05, 54.2MiB/s] 66%|█████████████████████████▊ | 587M/890M [00:12<00:05, 53.9MiB/s] 67%|█████████████████████████▉ | 593M/890M [00:12<00:05, 53.3MiB/s] 67%|██████████████████████████▏ | 598M/890M [00:12<00:06, 49.6MiB/s] 68%|██████████████████████████▍ | 603M/890M [00:12<00:05, 50.4MiB/s] 68%|██████████████████████████▋ | 608M/890M [00:13<00:05, 50.0MiB/s] 69%|██████████████████████████▊ | 612M/890M [00:13<00:06, 47.4MiB/s] 69%|███████████████████████████ | 617M/890M [00:13<00:06, 47.3MiB/s] 70%|███████████████████████████▏ | 622M/890M [00:13<00:05, 46.9MiB/s] 70%|███████████████████████████▍ | 626M/890M [00:13<00:05, 46.4MiB/s] 71%|███████████████████████████▋ | 631M/890M [00:13<00:05, 46.9MiB/s] 71%|███████████████████████████▊ | 635M/890M [00:13<00:05, 46.8MiB/s] 72%|████████████████████████████ | 640M/890M [00:13<00:05, 49.0MiB/s] 73%|████████████████████████████▎ | 645M/890M [00:13<00:05, 49.6MiB/s] 73%|████████████████████████████▌ | 650M/890M [00:13<00:05, 49.7MiB/s] 74%|████████████████████████████▋ | 655M/890M [00:14<00:05, 47.8MiB/s] 74%|████████████████████████████▉ | 660M/890M [00:14<00:04, 49.7MiB/s] 75%|█████████████████████████████▏ | 665M/890M [00:14<00:04, 49.7MiB/s] 75%|█████████████████████████████▎ | 670M/890M [00:14<00:04, 49.3MiB/s] 76%|█████████████████████████████▌ | 674M/890M [00:14<00:04, 49.2MiB/s] 76%|█████████████████████████████▊ | 679M/890M [00:14<00:04, 48.9MiB/s] 77%|█████████████████████████████▉ | 684M/890M [00:14<00:04, 47.9MiB/s] 77%|██████████████████████████████▏ | 688M/890M [00:14<00:04, 45.7MiB/s] 78%|██████████████████████████████▍ | 693M/890M [00:14<00:04, 47.4MiB/s] 78%|██████████████████████████████▌ | 698M/890M [00:14<00:04, 46.5MiB/s] 79%|██████████████████████████████▊ | 703M/890M [00:15<00:04, 48.4MiB/s] 80%|███████████████████████████████ | 708M/890M [00:15<00:03, 49.4MiB/s] 80%|███████████████████████████████▏ | 713M/890M [00:15<00:03, 49.7MiB/s] 81%|███████████████████████████████▍ | 717M/890M [00:15<00:03, 49.6MiB/s] 81%|███████████████████████████████▋ | 723M/890M [00:15<00:03, 50.9MiB/s] 82%|███████████████████████████████▉ | 728M/890M [00:15<00:03, 51.0MiB/s] 82%|████████████████████████████████ | 733M/890M [00:15<00:03, 51.6MiB/s] 83%|████████████████████████████████▎ | 738M/890M [00:15<00:02, 53.2MiB/s] 84%|████████████████████████████████▌ | 743M/890M [00:15<00:02, 53.4MiB/s] 84%|████████████████████████████████▊ | 748M/890M [00:16<00:02, 51.8MiB/s] 85%|█████████████████████████████████ | 753M/890M [00:16<00:02, 48.7MiB/s] 85%|█████████████████████████████████▏ | 758M/890M [00:16<00:02, 47.3MiB/s] 86%|█████████████████████████████████▍ | 763M/890M [00:16<00:02, 47.1MiB/s] 86%|█████████████████████████████████▋ | 767M/890M [00:16<00:02, 45.9MiB/s] 87%|█████████████████████████████████▊ | 772M/890M [00:16<00:02, 47.0MiB/s] 87%|██████████████████████████████████ | 777M/890M [00:16<00:02, 47.8MiB/s] 88%|██████████████████████████████████▎ | 782M/890M [00:16<00:02, 48.5MiB/s] 88%|██████████████████████████████████▍ | 787M/890M [00:16<00:02, 49.5MiB/s] 89%|██████████████████████████████████▋ | 791M/890M [00:16<00:02, 49.4MiB/s] 89%|██████████████████████████████████▉ | 796M/890M [00:17<00:02, 48.4MiB/s] 90%|███████████████████████████████████ | 801M/890M [00:17<00:01, 49.7MiB/s] 91%|███████████████████████████████████▎ | 806M/890M [00:17<00:01, 49.3MiB/s] 91%|███████████████████████████████████▌ | 811M/890M [00:17<00:01, 51.4MiB/s] 92%|███████████████████████████████████▊ | 816M/890M [00:17<00:01, 50.2MiB/s] 92%|████████████████████████████████████ | 822M/890M [00:17<00:01, 51.8MiB/s] 93%|████████████████████████████████████▎ | 827M/890M [00:17<00:01, 52.9MiB/s] 94%|████████████████████████████████████▍ | 832M/890M [00:17<00:01, 52.8MiB/s] 94%|████████████████████████████████████▋ | 838M/890M [00:17<00:01, 54.0MiB/s] 95%|████████████████████████████████████▉ | 843M/890M [00:17<00:00, 54.4MiB/s] 95%|█████████████████████████████████████▏ | 848M/890M [00:18<00:00, 53.9MiB/s] 96%|█████████████████████████████████████▍ | 854M/890M [00:18<00:00, 54.7MiB/s] 97%|█████████████████████████████████████▋ | 859M/890M [00:18<00:00, 54.5MiB/s] 97%|█████████████████████████████████████▉ | 864M/890M [00:18<00:00, 51.7MiB/s] 98%|██████████████████████████████████████ | 869M/890M [00:18<00:00, 48.0MiB/s] 98%|██████████████████████████████████████▎| 874M/890M [00:18<00:00, 46.8MiB/s] 99%|██████████████████████████████████████▌| 879M/890M [00:18<00:00, 48.1MiB/s] 99%|██████████████████████████████████████▋| 883M/890M [00:18<00:00, 46.6MiB/s] 100%|██████████████████████████████████████▉| 888M/890M [00:18<00:00, 48.9MiB/s] 100%|███████████████████████████████████████| 890M/890M [00:18<00:00, 49.1MiB/s] creating upsample model... [22/12 16:19:40] downloading base checkpoint... [22/12 16:19:45] 0%| | 0.00/161M [00:00<?, ?iB/s] 0%| | 393k/161M [00:00<00:47, 3.37MiB/s] 1%| | 1.18M/161M [00:00<00:29, 5.38MiB/s] 2%|▏ | 2.49M/161M [00:00<00:19, 8.07MiB/s] 3%|▎ | 4.19M/161M [00:00<00:15, 10.4MiB/s] 4%|▍ | 7.21M/161M [00:00<00:09, 16.0MiB/s] 5%|▌ | 8.81M/161M [00:00<00:11, 13.7MiB/s] 7%|▋ | 11.5M/161M [00:00<00:08, 17.1MiB/s] 9%|▉ | 15.2M/161M [00:00<00:06, 22.6MiB/s] 12%|█▏ | 19.3M/161M [00:01<00:05, 27.5MiB/s] 15%|█▍ | 23.9M/161M [00:01<00:04, 32.6MiB/s] 18%|█▊ | 28.4M/161M [00:01<00:03, 36.3MiB/s] 20%|██ | 33.0M/161M [00:01<00:03, 39.0MiB/s] 23%|██▎ | 37.5M/161M [00:01<00:03, 40.6MiB/s] 26%|██▌ | 41.9M/161M [00:01<00:05, 21.3MiB/s] 28%|██▊ | 45.1M/161M [00:02<00:07, 15.2MiB/s] 30%|██▉ | 47.6M/161M [00:02<00:07, 15.3MiB/s] 32%|███▏ | 50.9M/161M [00:02<00:06, 17.9MiB/s] 33%|███▎ | 53.6M/161M [00:02<00:05, 19.2MiB/s] 35%|███▍ | 56.1M/161M [00:02<00:05, 18.8MiB/s] 36%|███▋ | 58.7M/161M [00:03<00:08, 12.4MiB/s] 37%|███▋ | 60.5M/161M [00:03<00:10, 9.94MiB/s] 38%|███▊ | 61.9M/161M [00:03<00:09, 10.3MiB/s] 39%|███▉ | 63.3M/161M [00:03<00:09, 10.5MiB/s] 41%|████ | 65.5M/161M [00:03<00:07, 12.6MiB/s] 42%|████▏ | 67.1M/161M [00:04<00:11, 8.38MiB/s] 42%|████▏ | 68.3M/161M [00:04<00:14, 6.43MiB/s] 43%|████▎ | 69.2M/161M [00:04<00:15, 6.06MiB/s] 43%|████▎ | 70.0M/161M [00:04<00:15, 5.87MiB/s] 44%|████▍ | 70.8M/161M [00:05<00:15, 5.93MiB/s] 44%|████▍ | 71.5M/161M [00:05<00:17, 5.19MiB/s] 45%|████▍ | 72.1M/161M [00:05<00:16, 5.26MiB/s] 45%|████▌ | 72.7M/161M [00:05<00:17, 5.16MiB/s] 45%|████▌ | 73.3M/161M [00:05<00:17, 5.17MiB/s] 46%|████▌ | 73.8M/161M [00:05<00:17, 5.06MiB/s] 46%|████▌ | 74.5M/161M [00:05<00:16, 5.18MiB/s] 47%|████▋ | 75.1M/161M [00:05<00:16, 5.31MiB/s] 48%|████▊ | 77.9M/161M [00:06<00:07, 11.0MiB/s] 51%|█████ | 82.2M/161M [00:06<00:04, 19.5MiB/s] 52%|█████▏ | 84.3M/161M [00:06<00:08, 9.24MiB/s] 53%|█████▎ | 85.9M/161M [00:06<00:08, 8.88MiB/s] 54%|█████▍ | 87.4M/161M [00:06<00:07, 9.71MiB/s] 56%|█████▌ | 89.9M/161M [00:07<00:05, 12.0MiB/s] 58%|█████▊ | 93.7M/161M [00:07<00:03, 17.3MiB/s] 60%|██████ | 97.3M/161M [00:07<00:03, 21.2MiB/s] 62%|██████▏ | 101M/161M [00:07<00:04, 13.8MiB/s] 64%|██████▎ | 103M/161M [00:08<00:05, 10.7MiB/s] 65%|██████▍ | 104M/161M [00:08<00:05, 11.4MiB/s] 66%|██████▌ | 107M/161M [00:08<00:04, 13.4MiB/s] 68%|██████▊ | 109M/161M [00:08<00:05, 9.43MiB/s] 68%|██████▊ | 110M/161M [00:08<00:06, 7.76MiB/s] 69%|██████▉ | 112M/161M [00:09<00:05, 8.53MiB/s] 71%|███████ | 114M/161M [00:09<00:04, 10.4MiB/s] 73%|███████▎ | 117M/161M [00:09<00:04, 9.08MiB/s] 74%|███████▎ | 119M/161M [00:09<00:05, 8.02MiB/s] 74%|███████▍ | 120M/161M [00:09<00:04, 8.36MiB/s] 75%|███████▌ | 122M/161M [00:10<00:04, 9.73MiB/s] 77%|███████▋ | 124M/161M [00:10<00:02, 12.7MiB/s] 80%|███████▉ | 128M/161M [00:10<00:01, 18.5MiB/s] 83%|████████▎ | 133M/161M [00:10<00:01, 25.0MiB/s] 84%|████████▍ | 136M/161M [00:11<00:02, 10.9MiB/s] 86%|████████▌ | 138M/161M [00:11<00:01, 11.6MiB/s] 87%|████████▋ | 140M/161M [00:11<00:01, 12.4MiB/s] 89%|████████▉ | 144M/161M [00:11<00:01, 15.6MiB/s] 92%|█████████▏| 148M/161M [00:11<00:00, 20.8MiB/s] 94%|█████████▎| 151M/161M [00:11<00:00, 21.2MiB/s] 96%|█████████▌| 155M/161M [00:11<00:00, 24.6MiB/s] 98%|█████████▊| 158M/161M [00:11<00:00, 27.8MiB/s] 100%|██████████| 161M/161M [00:12<00:00, 13.4MiB/s] downloading upsampler checkpoint... [22/12 16:19:58] 0%| | 0.00/162M [00:00<?, ?iB/s] 6%|▋ | 10.3M/162M [00:00<00:01, 103MiB/s] 15%|█▌ | 24.6M/162M [00:00<00:01, 127MiB/s] 23%|██▎ | 37.3M/162M [00:00<00:01, 111MiB/s] 31%|███▏ | 50.7M/162M [00:00<00:00, 119MiB/s] 39%|███▉ | 62.9M/162M [00:00<00:00, 120MiB/s] 47%|████▋ | 76.2M/162M [00:00<00:00, 124MiB/s] 55%|█████▌ | 89.7M/162M [00:00<00:00, 128MiB/s] 63%|██████▎ | 103M/162M [00:00<00:00, 119MiB/s] 71%|███████ | 115M/162M [00:00<00:00, 109MiB/s] 78%|███████▊ | 127M/162M [00:01<00:00, 112MiB/s] 87%|████████▋ | 141M/162M [00:01<00:00, 121MiB/s] 95%|█████████▍| 154M/162M [00:01<00:00, 117MiB/s] 100%|██████████| 162M/162M [00:01<00:00, 118MiB/s] 0it [00:00, ?it/s] 1it [00:01, 1.23s/it] 4it [00:01, 3.70it/s] 7it [00:01, 6.67it/s] 10it [00:01, 9.55it/s] 13it [00:01, 12.16it/s] 16it [00:01, 14.39it/s] 19it [00:02, 16.24it/s] 22it [00:02, 17.70it/s] 25it [00:02, 18.81it/s] 28it [00:02, 19.63it/s] 31it [00:02, 20.23it/s] 34it [00:02, 20.66it/s] 37it [00:02, 20.98it/s] 40it [00:03, 21.20it/s] 43it [00:03, 21.36it/s] 46it [00:03, 21.47it/s] 49it [00:03, 21.53it/s] 52it [00:03, 21.56it/s] 55it [00:03, 21.60it/s] 58it [00:03, 21.59it/s] 61it [00:03, 21.61it/s] 64it [00:04, 21.62it/s] 67it [00:04, 16.65it/s] 69it [00:04, 11.39it/s] 71it [00:05, 8.99it/s] 73it [00:05, 7.69it/s] 74it [00:05, 7.23it/s] 75it [00:05, 6.82it/s] 76it [00:06, 6.47it/s] 77it [00:06, 6.19it/s] 78it [00:06, 5.99it/s] 79it [00:06, 5.84it/s] 80it [00:06, 5.73it/s] 81it [00:06, 5.65it/s] 82it [00:07, 5.59it/s] 83it [00:07, 5.55it/s] 84it [00:07, 5.53it/s] 85it [00:07, 5.50it/s] 86it [00:07, 5.48it/s] 87it [00:08, 5.47it/s] 88it [00:08, 5.46it/s] 89it [00:08, 5.46it/s] 90it [00:08, 5.46it/s] 91it [00:08, 5.46it/s] 92it [00:09, 5.45it/s] 93it [00:09, 5.45it/s] 94it [00:09, 5.45it/s] 95it [00:09, 5.45it/s] 96it [00:09, 5.45it/s] 97it [00:09, 5.45it/s] 98it [00:10, 5.44it/s] 99it [00:10, 5.44it/s] 100it [00:10, 5.44it/s] 101it [00:10, 5.44it/s] 102it [00:10, 5.44it/s] 103it [00:11, 5.44it/s] 104it [00:11, 5.44it/s] 105it [00:11, 5.44it/s] 106it [00:11, 5.43it/s] 107it [00:11, 5.43it/s] 108it [00:11, 5.42it/s] 109it [00:12, 5.41it/s] 110it [00:12, 5.41it/s] 111it [00:12, 5.42it/s] 112it [00:12, 5.41it/s] 113it [00:12, 5.42it/s] 114it [00:13, 5.42it/s] 115it [00:13, 5.42it/s] 116it [00:13, 5.40it/s] 117it [00:13, 5.40it/s] 118it [00:13, 5.40it/s] 119it [00:13, 5.40it/s] 120it [00:14, 5.39it/s] 121it [00:14, 5.40it/s] 122it [00:14, 5.40it/s] 123it [00:14, 5.40it/s] 124it [00:14, 5.41it/s] 125it [00:15, 5.40it/s] 126it [00:15, 5.40it/s] 127it [00:15, 5.40it/s] 128it [00:15, 5.40it/s] 129it [00:15, 5.41it/s] 130it [00:15, 8.21it/s] Generating random point cloud (81920)...[22/12 16:20:16] Number of points at initialisation : 81920 [22/12 16:20:16] train_process is in : ./output/Replicate/train_process/ [22/12 16:20:16] [INFO] loading stable diffusion... [22/12 16:20:19] [INFO] loaded stable diffusion! [22/12 16:20:21] test views is in : ./output/Replicate/test_six_views/1_iteration [22/12 16:20:37] [ITER 1] Eval Done! [22/12 16:20:38] videos is in : ./output/Replicate/videos/1_iteration[22/12 16:20:38] Generating Video using 240 different view points[22/12 16:20:44] [ITER 1] Video Save Done! [22/12 16:20:46] Training progress: 0%| | 0/1000 [00:00<?, ?it/s] Training progress: 0%| | 0/1000 [00:32<?, ?it/s, Loss=1.0007480] Training progress: 1%| | 10/1000 [00:32<54:10, 3.28s/it, Loss=1.0007480] Training progress: 1%| | 10/1000 [00:41<54:10, 3.28s/it, Loss=1.0067991] Training progress: 2%|▏ | 20/1000 [00:41<30:05, 1.84s/it, Loss=1.0067991] Training progress: 2%|▏ | 20/1000 [00:49<30:05, 1.84s/it, Loss=1.0068357] Training progress: 3%|▎ | 30/1000 [00:49<22:18, 1.38s/it, Loss=1.0068357] Training progress: 3%|▎ | 30/1000 [00:58<22:18, 1.38s/it, Loss=1.0068359] Training progress: 4%|▍ | 40/1000 [00:58<18:56, 1.18s/it, Loss=1.0068359] Training progress: 4%|▍ | 40/1000 [01:06<18:56, 1.18s/it, Loss=1.0068359] Training progress: 5%|▌ | 50/1000 [01:06<16:35, 1.05s/it, Loss=1.0068359] Training progress: 5%|▌ | 50/1000 [01:15<16:35, 1.05s/it, Loss=1.0068359] Training progress: 6%|▌ | 60/1000 [01:15<15:31, 1.01it/s, Loss=1.0068359] Training progress: 6%|▌ | 60/1000 [01:23<15:31, 1.01it/s, Loss=1.0070703] Training progress: 7%|▋ | 70/1000 [01:23<14:21, 1.08it/s, Loss=1.0070703] Training progress: 7%|▋ | 70/1000 [01:31<14:21, 1.08it/s, Loss=1.0069780] Training progress: 8%|▊ | 80/1000 [01:31<13:56, 1.10it/s, Loss=1.0069780] Training progress: 8%|▊ | 80/1000 [01:39<13:56, 1.10it/s, Loss=1.0069023] Training progress: 9%|▉ | 90/1000 [01:39<13:20, 1.14it/s, Loss=1.0069023] Training progress: 9%|▉ | 90/1000 [01:48<13:20, 1.14it/s, Loss=1.0072865] Training progress: 10%|█ | 100/1000 [01:48<13:16, 1.13it/s, Loss=1.0072865] Training progress: 10%|█ | 100/1000 [01:56<13:16, 1.13it/s, Loss=1.0071143] Training progress: 11%|█ | 110/1000 [01:56<12:43, 1.17it/s, Loss=1.0071143] Training progress: 11%|█ | 110/1000 [02:05<12:43, 1.17it/s, Loss=1.0075922] Training progress: 12%|█▏ | 120/1000 [02:05<12:31, 1.17it/s, Loss=1.0075922] Training progress: 12%|█▏ | 120/1000 [02:13<12:31, 1.17it/s, Loss=1.0075768] Training progress: 13%|█▎ | 130/1000 [02:13<12:18, 1.18it/s, Loss=1.0075768] Training progress: 13%|█▎ | 130/1000 [02:22<12:18, 1.18it/s, Loss=1.0073698] Training progress: 14%|█▍ | 140/1000 [02:22<12:06, 1.18it/s, Loss=1.0073698] Training progress: 14%|█▍ | 140/1000 [02:30<12:06, 1.18it/s, Loss=1.0078098] Training progress: 15%|█▌ | 150/1000 [02:30<11:52, 1.19it/s, Loss=1.0078098] Training progress: 15%|█▌ | 150/1000 [02:38<11:52, 1.19it/s, Loss=1.0077821] Training progress: 16%|█▌ | 160/1000 [02:38<11:28, 1.22it/s, Loss=1.0077821] Training progress: 16%|█▌ | 160/1000 [02:46<11:28, 1.22it/s, Loss=1.0078123] Training progress: 17%|█▋ | 170/1000 [02:46<11:28, 1.21it/s, Loss=1.0078123] Training progress: 17%|█▋ | 170/1000 [02:55<11:28, 1.21it/s, Loss=1.0078125] Training progress: 18%|█▊ | 180/1000 [02:55<11:43, 1.17it/s, Loss=1.0078125] Training progress: 18%|█▊ | 180/1000 [03:03<11:43, 1.17it/s, Loss=1.0078086] Training progress: 19%|█▉ | 190/1000 [03:03<11:18, 1.19it/s, Loss=1.0078086] Training progress: 19%|█▉ | 190/1000 [03:12<11:18, 1.19it/s, Loss=1.0078125] test views is in : ./output/Replicate/test_six_views/200_iteration [22/12 16:23:34] [ITER 200] Eval Done! [22/12 16:23:35] videos is in : ./output/Replicate/videos/200_iteration [22/12 16:23:35] Generating Video using 240 different view points [22/12 16:23:40] [ITER 200] Video Save Done! [22/12 16:23:43] Training progress: 20%|██ | 200/1000 [03:12<11:30, 1.16it/s, Loss=1.0078125] Training progress: 20%|██ | 200/1000 [03:30<11:30, 1.16it/s, Loss=1.0080375] Training progress: 21%|██ | 210/1000 [03:30<14:45, 1.12s/it, Loss=1.0080375] Training progress: 21%|██ | 210/1000 [03:38<14:45, 1.12s/it, Loss=1.0080179] Training progress: 22%|██▏ | 220/1000 [03:38<13:33, 1.04s/it, Loss=1.0080179] Training progress: 22%|██▏ | 220/1000 [03:47<13:33, 1.04s/it, Loss=1.0082394] Training progress: 23%|██▎ | 230/1000 [03:47<12:37, 1.02it/s, Loss=1.0082394] Training progress: 23%|██▎ | 230/1000 [03:55<12:37, 1.02it/s, Loss=1.0084688] Training progress: 24%|██▍ | 240/1000 [03:55<11:56, 1.06it/s, Loss=1.0084688] Training progress: 24%|██▍ | 240/1000 [04:03<11:56, 1.06it/s, Loss=1.0078165] Training progress: 25%|██▌ | 250/1000 [04:03<11:20, 1.10it/s, Loss=1.0078165] Training progress: 25%|██▌ | 250/1000 [04:12<11:20, 1.10it/s, Loss=1.0083477] Training progress: 26%|██▌ | 260/1000 [04:12<10:56, 1.13it/s, Loss=1.0083477] Training progress: 26%|██▌ | 260/1000 [04:20<10:56, 1.13it/s, Loss=1.0079507] Training progress: 27%|██▋ | 270/1000 [04:20<10:38, 1.14it/s, Loss=1.0079507] Training progress: 27%|██▋ | 270/1000 [04:30<10:38, 1.14it/s, Loss=1.0079588] Training progress: 28%|██▊ | 280/1000 [04:30<10:47, 1.11it/s, Loss=1.0079588] Training progress: 28%|██▊ | 280/1000 [04:39<10:47, 1.11it/s, Loss=1.0084979] Training progress: 29%|██▉ | 290/1000 [04:39<10:34, 1.12it/s, Loss=1.0084979] Training progress: 29%|██▉ | 290/1000 [04:48<10:34, 1.12it/s, Loss=1.0079069] Training progress: 30%|███ | 300/1000 [04:48<10:29, 1.11it/s, Loss=1.0079069] Training progress: 30%|███ | 300/1000 [04:56<10:29, 1.11it/s, Loss=1.0096953] Training progress: 31%|███ | 310/1000 [04:56<10:10, 1.13it/s, Loss=1.0096953] Training progress: 31%|███ | 310/1000 [05:05<10:10, 1.13it/s, Loss=1.0105446] Training progress: 32%|███▏ | 320/1000 [05:05<09:58, 1.14it/s, Loss=1.0105446] Training progress: 32%|███▏ | 320/1000 [05:14<09:58, 1.14it/s, Loss=1.0109520] Training progress: 33%|███▎ | 330/1000 [05:14<09:44, 1.15it/s, Loss=1.0109520] Training progress: 33%|███▎ | 330/1000 [05:22<09:44, 1.15it/s, Loss=1.0107435] Training progress: 34%|███▍ | 340/1000 [05:22<09:28, 1.16it/s, Loss=1.0107435] Training progress: 34%|███▍ | 340/1000 [05:30<09:28, 1.16it/s, Loss=1.0114516] Training progress: 35%|███▌ | 350/1000 [05:30<09:14, 1.17it/s, Loss=1.0114516] Training progress: 35%|███▌ | 350/1000 [05:39<09:14, 1.17it/s, Loss=1.0105843] Training progress: 36%|███▌ | 360/1000 [05:39<09:06, 1.17it/s, Loss=1.0105843] Training progress: 36%|███▌ | 360/1000 [05:48<09:06, 1.17it/s, Loss=1.0101097] Training progress: 37%|███▋ | 370/1000 [05:48<09:00, 1.17it/s, Loss=1.0101097] Training progress: 37%|███▋ | 370/1000 [05:56<09:00, 1.17it/s, Loss=1.0092723] Training progress: 38%|███▊ | 380/1000 [05:56<08:46, 1.18it/s, Loss=1.0092723] Training progress: 38%|███▊ | 380/1000 [06:04<08:46, 1.18it/s, Loss=1.0114264] Training progress: 39%|███▉ | 390/1000 [06:04<08:27, 1.20it/s, Loss=1.0114264] Training progress: 39%|███▉ | 390/1000 [06:14<08:27, 1.20it/s, Loss=1.0102742] test views is in : ./output/Replicate/test_six_views/400_iteration [22/12 16:26:35] [ITER 400] Eval Done! [22/12 16:26:36] videos is in : ./output/Replicate/videos/400_iteration [22/12 16:26:36] Generating Video using 240 different view points [22/12 16:26:42] [ITER 400] Video Save Done! [22/12 16:26:45] Training progress: 40%|████ | 400/1000 [06:14<08:52, 1.13it/s, Loss=1.0102742] Training progress: 40%|████ | 400/1000 [06:32<08:52, 1.13it/s, Loss=1.0089330] Training progress: 41%|████ | 410/1000 [06:32<11:19, 1.15s/it, Loss=1.0089330] Training progress: 41%|████ | 410/1000 [06:41<11:19, 1.15s/it, Loss=1.0094149] Training progress: 42%|████▏ | 420/1000 [06:41<10:27, 1.08s/it, Loss=1.0094149] Training progress: 42%|████▏ | 420/1000 [06:49<10:27, 1.08s/it, Loss=1.0089874] Training progress: 43%|████▎ | 430/1000 [06:49<09:38, 1.02s/it, Loss=1.0089874] Training progress: 43%|████▎ | 430/1000 [06:58<09:38, 1.02s/it, Loss=1.0094367] Training progress: 44%|████▍ | 440/1000 [06:58<09:06, 1.02it/s, Loss=1.0094367] Training progress: 44%|████▍ | 440/1000 [07:06<09:06, 1.02it/s, Loss=1.0085691] Training progress: 45%|████▌ | 450/1000 [07:06<08:32, 1.07it/s, Loss=1.0085691] Training progress: 45%|████▌ | 450/1000 [07:15<08:32, 1.07it/s, Loss=1.0100140] Training progress: 46%|████▌ | 460/1000 [07:15<08:07, 1.11it/s, Loss=1.0100140] Training progress: 46%|████▌ | 460/1000 [07:23<08:07, 1.11it/s, Loss=1.0095660] Training progress: 47%|████▋ | 470/1000 [07:23<07:44, 1.14it/s, Loss=1.0095660] Training progress: 47%|████▋ | 470/1000 [07:31<07:44, 1.14it/s, Loss=1.0088043] Training progress: 48%|████▊ | 480/1000 [07:31<07:27, 1.16it/s, Loss=1.0088043] Training progress: 48%|████▊ | 480/1000 [07:40<07:27, 1.16it/s, Loss=1.0089837] scale up theta_range to: [60, 90] [22/12 16:28:09] scale up radius_range to: [4.9399999999999995, 5.225] [22/12 16:28:09] scale up phi_range to: [-180, 180] [22/12 16:28:09] scale up fovy_range to: [0.24, 0.6] [22/12 16:28:09] Training progress: 49%|████▉ | 490/1000 [07:40<07:22, 1.15it/s, Loss=1.0089837] Training progress: 49%|████▉ | 490/1000 [07:51<07:22, 1.15it/s, Loss=1.0090351] [ITER 500] Saving Gaussians [22/12 16:28:12] Training progress: 50%|█████ | 500/1000 [07:51<07:40, 1.09it/s, Loss=1.0090351] Training progress: 50%|█████ | 500/1000 [08:02<07:40, 1.09it/s, Loss=1.0090662] Training progress: 51%|█████ | 510/1000 [08:02<08:10, 1.00s/it, Loss=1.0090662] Training progress: 51%|█████ | 510/1000 [08:11<08:10, 1.00s/it, Loss=1.0097691] Training progress: 52%|█████▏ | 520/1000 [08:11<07:40, 1.04it/s, Loss=1.0097691] Training progress: 52%|█████▏ | 520/1000 [08:20<07:40, 1.04it/s, Loss=1.0095495] Training progress: 53%|█████▎ | 530/1000 [08:20<07:18, 1.07it/s, Loss=1.0095495] Training progress: 53%|█████▎ | 530/1000 [08:28<07:18, 1.07it/s, Loss=1.0098791] Training progress: 54%|█████▍ | 540/1000 [08:28<07:00, 1.09it/s, Loss=1.0098791] Training progress: 54%|█████▍ | 540/1000 [08:37<07:00, 1.09it/s, Loss=1.0095788] Training progress: 55%|█████▌ | 550/1000 [08:37<06:41, 1.12it/s, Loss=1.0095788] Training progress: 55%|█████▌ | 550/1000 [08:46<06:41, 1.12it/s, Loss=1.0097192] Training progress: 56%|█████▌ | 560/1000 [08:46<06:36, 1.11it/s, Loss=1.0097192] Training progress: 56%|█████▌ | 560/1000 [08:55<06:36, 1.11it/s, Loss=1.0096953] Training progress: 57%|█████▋ | 570/1000 [08:55<06:30, 1.10it/s, Loss=1.0096953] Training progress: 57%|█████▋ | 570/1000 [09:04<06:30, 1.10it/s, Loss=1.0092266] Training progress: 58%|█████▊ | 580/1000 [09:04<06:12, 1.13it/s, Loss=1.0092266] Training progress: 58%|█████▊ | 580/1000 [09:12<06:12, 1.13it/s, Loss=1.0090673] Training progress: 59%|█████▉ | 590/1000 [09:12<06:02, 1.13it/s, Loss=1.0090673] Training progress: 59%|█████▉ | 590/1000 [09:22<06:02, 1.13it/s, Loss=1.0089094] test views is in : ./output/Replicate/test_six_views/600_iteration[22/12 16:29:43] [ITER 600] Eval Done! [22/12 16:29:44] videos is in : ./output/Replicate/videos/600_iteration [22/12 16:29:44] Generating Video using 240 different view points[22/12 16:29:50] [ITER 600] Video Save Done! [22/12 16:29:54] Training progress: 60%|██████ | 600/1000 [09:22<06:03, 1.10it/s, Loss=1.0089094] Training progress: 60%|██████ | 600/1000 [09:41<06:03, 1.10it/s, Loss=1.0130514] Training progress: 61%|██████ | 610/1000 [09:41<07:52, 1.21s/it, Loss=1.0130514] Training progress: 61%|██████ | 610/1000 [09:50<07:52, 1.21s/it, Loss=1.0110758] Training progress: 62%|██████▏ | 620/1000 [09:50<07:05, 1.12s/it, Loss=1.0110758] Training progress: 62%|██████▏ | 620/1000 [09:59<07:05, 1.12s/it, Loss=1.0103461] Training progress: 63%|██████▎ | 630/1000 [09:59<06:29, 1.05s/it, Loss=1.0103461] Training progress: 63%|██████▎ | 630/1000 [10:08<06:29, 1.05s/it, Loss=1.0108610] Training progress: 64%|██████▍ | 640/1000 [10:08<05:58, 1.01it/s, Loss=1.0108610] Training progress: 64%|██████▍ | 640/1000 [10:16<05:58, 1.01it/s, Loss=1.0109771] Training progress: 65%|██████▌ | 650/1000 [10:16<05:33, 1.05it/s, Loss=1.0109771] Training progress: 65%|██████▌ | 650/1000 [10:25<05:33, 1.05it/s, Loss=1.0098803] Training progress: 66%|██████▌ | 660/1000 [10:25<05:14, 1.08it/s, Loss=1.0098803] Training progress: 66%|██████▌ | 660/1000 [10:34<05:14, 1.08it/s, Loss=1.0106163] Training progress: 67%|██████▋ | 670/1000 [10:34<04:57, 1.11it/s, Loss=1.0106163] Training progress: 67%|██████▋ | 670/1000 [10:43<04:57, 1.11it/s, Loss=1.0092700] Training progress: 68%|██████▊ | 680/1000 [10:43<04:50, 1.10it/s, Loss=1.0092700] Training progress: 68%|██████▊ | 680/1000 [10:51<04:50, 1.10it/s, Loss=1.0107625] Training progress: 69%|██████▉ | 690/1000 [10:51<04:38, 1.11it/s, Loss=1.0107625] Training progress: 69%|██████▉ | 690/1000 [11:01<04:38, 1.11it/s, Loss=1.0095968] Training progress: 70%|███████ | 700/1000 [11:01<04:35, 1.09it/s, Loss=1.0095968] Training progress: 70%|███████ | 700/1000 [11:10<04:35, 1.09it/s, Loss=1.0102746] Training progress: 71%|███████ | 710/1000 [11:10<04:27, 1.09it/s, Loss=1.0102746] Training progress: 71%|███████ | 710/1000 [11:19<04:27, 1.09it/s, Loss=1.0102181] Training progress: 72%|███████▏ | 720/1000 [11:19<04:16, 1.09it/s, Loss=1.0102181] Training progress: 72%|███████▏ | 720/1000 [11:28<04:16, 1.09it/s, Loss=1.0097177] Training progress: 73%|███████▎ | 730/1000 [11:28<04:03, 1.11it/s, Loss=1.0097177] Training progress: 73%|███████▎ | 730/1000 [11:37<04:03, 1.11it/s, Loss=1.0097081] Training progress: 74%|███████▍ | 740/1000 [11:37<03:50, 1.13it/s, Loss=1.0097081] Training progress: 74%|███████▍ | 740/1000 [11:45<03:50, 1.13it/s, Loss=1.0099252] Training progress: 75%|███████▌ | 750/1000 [11:45<03:41, 1.13it/s, Loss=1.0099252] Training progress: 75%|███████▌ | 750/1000 [11:54<03:41, 1.13it/s, Loss=1.0111279] Training progress: 76%|███████▌ | 760/1000 [11:54<03:30, 1.14it/s, Loss=1.0111279] Training progress: 76%|███████▌ | 760/1000 [12:03<03:30, 1.14it/s, Loss=1.0101377] Training progress: 77%|███████▋ | 770/1000 [12:03<03:19, 1.15it/s, Loss=1.0101377] Training progress: 77%|███████▋ | 770/1000 [12:11<03:19, 1.15it/s, Loss=1.0106392] Training progress: 78%|███████▊ | 780/1000 [12:11<03:07, 1.17it/s, Loss=1.0106392] Training progress: 78%|███████▊ | 780/1000 [12:19<03:07, 1.17it/s, Loss=1.0102619] Training progress: 79%|███████▉ | 790/1000 [12:19<02:58, 1.17it/s, Loss=1.0102619] Training progress: 79%|███████▉ | 790/1000 [12:29<02:58, 1.17it/s, Loss=1.0111697] test views is in : ./output/Replicate/test_six_views/800_iteration [22/12 16:32:50] [ITER 800] Eval Done! [22/12 16:32:51] videos is in : ./output/Replicate/videos/800_iteration[22/12 16:32:51] Generating Video using 240 different view points [22/12 16:32:57] [ITER 800] Video Save Done! [22/12 16:33:01] Training progress: 80%|████████ | 800/1000 [12:29<02:55, 1.14it/s, Loss=1.0111697] Training progress: 80%|████████ | 800/1000 [12:48<02:55, 1.14it/s, Loss=1.0114215] Training progress: 81%|████████ | 810/1000 [12:48<03:46, 1.19s/it, Loss=1.0114215] Training progress: 81%|████████ | 810/1000 [12:57<03:46, 1.19s/it, Loss=1.0098516] Training progress: 82%|████████▏ | 820/1000 [12:57<03:21, 1.12s/it, Loss=1.0098516] Training progress: 82%|████████▏ | 820/1000 [13:06<03:21, 1.12s/it, Loss=1.0106504] Training progress: 83%|████████▎ | 830/1000 [13:06<02:56, 1.04s/it, Loss=1.0106504] Training progress: 83%|████████▎ | 830/1000 [13:15<02:56, 1.04s/it, Loss=1.0098756] Training progress: 84%|████████▍ | 840/1000 [13:15<02:39, 1.01it/s, Loss=1.0098756] Training progress: 84%|████████▍ | 840/1000 [13:23<02:39, 1.01it/s, Loss=1.0107513] Training progress: 85%|████████▌ | 850/1000 [13:23<02:22, 1.05it/s, Loss=1.0107513] Training progress: 85%|████████▌ | 850/1000 [13:32<02:22, 1.05it/s, Loss=1.0114682] Training progress: 86%|████████▌ | 860/1000 [13:32<02:09, 1.08it/s, Loss=1.0114682] Training progress: 86%|████████▌ | 860/1000 [13:41<02:09, 1.08it/s, Loss=1.0098460] Training progress: 87%|████████▋ | 870/1000 [13:41<01:57, 1.10it/s, Loss=1.0098460] Training progress: 87%|████████▋ | 870/1000 [13:49<01:57, 1.10it/s, Loss=1.0104150] Training progress: 88%|████████▊ | 880/1000 [13:49<01:45, 1.14it/s, Loss=1.0104150] Training progress: 88%|████████▊ | 880/1000 [13:57<01:45, 1.14it/s, Loss=1.0103430] Training progress: 89%|████████▉ | 890/1000 [13:57<01:35, 1.15it/s, Loss=1.0103430] Training progress: 89%|████████▉ | 890/1000 [14:07<01:35, 1.15it/s, Loss=1.0112264] Training progress: 90%|█████████ | 900/1000 [14:07<01:28, 1.13it/s, Loss=1.0112264] Training progress: 90%|█████████ | 900/1000 [14:16<01:28, 1.13it/s, Loss=1.0153764] Training progress: 91%|█████████ | 910/1000 [14:16<01:21, 1.11it/s, Loss=1.0153764] Training progress: 91%|█████████ | 910/1000 [14:25<01:21, 1.11it/s, Loss=1.0135635] Training progress: 92%|█████████▏| 920/1000 [14:25<01:11, 1.11it/s, Loss=1.0135635] Training progress: 92%|█████████▏| 920/1000 [14:34<01:11, 1.11it/s, Loss=1.0099341] Training progress: 93%|█████████▎| 930/1000 [14:34<01:04, 1.09it/s, Loss=1.0099341] Training progress: 93%|█████████▎| 930/1000 [14:43<01:04, 1.09it/s, Loss=1.0107898] Training progress: 94%|█████████▍| 940/1000 [14:43<00:54, 1.10it/s, Loss=1.0107898] Training progress: 94%|█████████▍| 940/1000 [14:52<00:54, 1.10it/s, Loss=1.0116342] Training progress: 95%|█████████▌| 950/1000 [14:52<00:44, 1.11it/s, Loss=1.0116342] Training progress: 95%|█████████▌| 950/1000 [15:01<00:44, 1.11it/s, Loss=1.0102147] Training progress: 96%|█████████▌| 960/1000 [15:01<00:35, 1.12it/s, Loss=1.0102147] Training progress: 96%|█████████▌| 960/1000 [15:10<00:35, 1.12it/s, Loss=1.0102574] Training progress: 97%|█████████▋| 970/1000 [15:10<00:26, 1.13it/s, Loss=1.0102574] Training progress: 97%|█████████▋| 970/1000 [15:18<00:26, 1.13it/s, Loss=1.0106889] Training progress: 98%|█████████▊| 980/1000 [15:18<00:17, 1.15it/s, Loss=1.0106889] Training progress: 98%|█████████▊| 980/1000 [15:27<00:17, 1.15it/s, Loss=1.0106823] scale up theta_range to: [60, 90][22/12 16:35:56] scale up radius_range to: [4.693, 5.0] [22/12 16:35:56] scale up phi_range to: [-180, 180] [22/12 16:35:56] scale up fovy_range to: [0.18, 0.6] [22/12 16:35:56] Training progress: 99%|█████████▉| 990/1000 [15:27<00:08, 1.15it/s, Loss=1.0106823] Training progress: 99%|█████████▉| 990/1000 [15:36<00:08, 1.15it/s, Loss=1.0103620] Training progress: 100%|██████████| 1000/1000 [15:36<00:00, 1.12it/s, Loss=1.0103620] Training progress: 100%|██████████| 1000/1000 [15:36<00:00, 1.07it/s, Loss=1.0103620] test views is in : ./output/Replicate/test_six_views/1000_iteration[22/12 16:35:57] [ITER 1000] Eval Done! [22/12 16:35:58] videos is in : ./output/Replicate/videos/1000_iteration[22/12 16:35:58] Generating Video using 240 different view points[22/12 16:36:04] [ITER 1000] Video Save Done! [22/12 16:36:09] [ITER 1000] Saving Gaussians [22/12 16:36:09] Training complete. [22/12 16:36:23]
Want to make some of these yourself?
Run this model
