{
  "completed_at": "2021-09-09T21:45:36.439293Z",
  "created_at": "2021-09-09T21:42:04.043670Z",
  "data_removed": false,
  "error": null,
  "id": "yt34tm4zi5arvj4bpfjp3apwqa",
  "input": {
    "aspect": "widescreen",
    "prompts": "sunset river snow mountain",
    "quality": "draft"
  },
  "logs": "Working with z of shape (1, 256, 16, 16) = 65536 dimensions.\nDownloading: \"https://download.pytorch.org/models/vgg16-397923af.pth\" to /root/.cache/torch/hub/checkpoints/vgg16-397923af.pth\n\n  0%|          | 0.00/528M [00:00<?, ?B/s]\n\n  1%|          | 3.15M/528M [00:00<00:16, 33.0MB/s]\n\n  1%|1         | 5.95M/528M [00:00<00:17, 31.8MB/s]\n\n  4%|4         | 22.4M/528M [00:00<00:12, 42.1MB/s]\n\n  9%|8         | 44.9M/528M [00:00<00:09, 55.9MB/s]\n\n 13%|#3        | 69.2M/528M [00:00<00:06, 73.0MB/s]\n\n 17%|#7        | 91.7M/528M [00:00<00:04, 92.1MB/s]\n\n 21%|##        | 109M/528M [00:00<00:04, 103MB/s]\n\n 25%|##4       | 130M/528M [00:00<00:03, 123MB/s]\n\n 29%|##8       | 152M/528M [00:00<00:02, 143MB/s]\n\n 34%|###3      | 177M/528M [00:01<00:02, 165MB/s]\n\n 38%|###8      | 203M/528M [00:01<00:01, 187MB/s]\n\n 43%|####3     | 228M/528M [00:01<00:01, 204MB/s]\n\n 48%|####7     | 252M/528M [00:01<00:01, 217MB/s]\n\n 52%|#####2    | 275M/528M [00:01<00:01, 215MB/s]\n\n 57%|#####6    | 299M/528M [00:01<00:01, 225MB/s]\n\n 61%|######1   | 322M/528M [00:01<00:00, 228MB/s]\n\n 65%|######5   | 345M/528M [00:01<00:00, 215MB/s]\n\n 70%|######9   | 369M/528M [00:01<00:00, 225MB/s]\n\n 74%|#######4  | 391M/528M [00:02<00:00, 202MB/s]\n\n 78%|#######7  | 412M/528M [00:02<00:00, 157MB/s]\n\n 83%|########2 | 437M/528M [00:02<00:00, 179MB/s]\n\n 88%|########7 | 463M/528M [00:02<00:00, 200MB/s]\n\n 93%|#########2| 490M/528M [00:02<00:00, 218MB/s]\n\n 97%|#########7| 513M/528M [00:02<00:00, 219MB/s]\n\n100%|##########| 528M/528M [00:02<00:00, 205MB/s]\nloaded pretrained LPIPS loss from taming/modules/autoencoder/lpips/vgg.pth\nVQLPIPSWithDiscriminator running with hinge loss.\nRestored from models/vqgan_imagenet_f16_16384.ckpt\n\n  0%|                                               | 0.00/338M [00:00<?, ?iB/s]\n\n  0%|1                                     | 1.12M/338M [00:00<00:30, 11.6MiB/s]\n\n  5%|#7                                    | 15.7M/338M [00:00<00:21, 16.0MiB/s]\n\n 12%|####4                                 | 39.6M/338M [00:00<00:14, 22.3MiB/s]\n\n 19%|#######                               | 62.8M/338M [00:00<00:09, 30.6MiB/s]\n\n 23%|########8                             | 79.0M/338M [00:00<00:06, 40.6MiB/s]\n\n 30%|###########2                          | 99.8M/338M [00:00<00:04, 53.7MiB/s]\n\n 36%|##############1                        | 122M/338M [00:00<00:03, 69.8MiB/s]\n\n 43%|################6                      | 144M/338M [00:00<00:02, 88.2MiB/s]\n\n 48%|###################3                    | 164M/338M [00:00<00:01, 107MiB/s]\n\n 54%|#####################6                  | 183M/338M [00:01<00:01, 123MiB/s]\n\n 60%|########################1               | 204M/338M [00:01<00:00, 142MiB/s]\n\n 68%|###########################             | 228M/338M [00:01<00:00, 164MiB/s]\n\n 74%|#############################7          | 251M/338M [00:01<00:00, 180MiB/s]\n\n 81%|################################2       | 272M/338M [00:01<00:00, 190MiB/s]\n\n 87%|##################################7     | 294M/338M [00:01<00:00, 185MiB/s]\n\n 93%|#####################################3  | 315M/338M [00:01<00:00, 196MiB/s]\n\n100%|#######################################8| 336M/338M [00:01<00:00, 203MiB/s]\n\n100%|########################################| 338M/338M [00:01<00:00, 203MiB/s]\nUsing device:\ncuda:0\nOptimising using:\nAdam\nUsing text prompts:\n['sunset river snow mountain']\nUsing seed:\n14723532543356836858\n\n0it [00:00, ?it/s]\n/root/.pyenv/versions/3.8.12/lib/python3.8/site-packages/torch/nn/functional.py:3451: UserWarning: Default upsampling behavior when mode=bilinear is changed to align_corners=False since 0.4.0. Please specify align_corners=True if the old behavior is desired. See the documentation of nn.Upsample for details.\n  warnings.warn(\niter: 0, loss: 0.952009, losses: 0.952009\n\n0it [00:00, ?it/s]\n\n1it [00:00,  3.26it/s]\n\n2it [00:00,  3.60it/s]\n\n3it [00:00,  3.89it/s]\n\n4it [00:00,  4.11it/s]\n\n5it [00:01,  4.31it/s]\n\n6it [00:01,  4.45it/s]\n\n7it [00:01,  4.57it/s]\n\n8it [00:01,  4.65it/s]\n\n9it [00:01,  4.73it/s]\n\n10it [00:02,  4.78it/s]\niter: 10, loss: 0.872961, losses: 0.872961\n\n10it [00:02,  4.78it/s]\n\n11it [00:02,  4.13it/s]\n\n12it [00:02,  4.35it/s]\n\n13it [00:02,  4.50it/s]\n\n14it [00:03,  4.62it/s]\n\n15it [00:03,  4.66it/s]\n\n16it [00:03,  4.71it/s]\n\n17it [00:03,  4.76it/s]\n\n18it [00:03,  4.81it/s]\n\n19it [00:04,  4.78it/s]\n\n20it [00:04,  4.83it/s]\niter: 20, loss: 0.816933, losses: 0.816933\n\n20it [00:04,  4.83it/s]\n\n21it [00:05,  2.72it/s]\n\n22it [00:05,  3.13it/s]\n\n23it [00:05,  3.52it/s]\n\n24it [00:05,  3.82it/s]\n\n25it [00:05,  4.06it/s]\n\n26it [00:06,  4.29it/s]\n\n27it [00:06,  4.49it/s]\n\n28it [00:06,  4.58it/s]\n\n29it [00:06,  4.67it/s]\n\n30it [00:06,  4.76it/s]\niter: 30, loss: 0.793794, losses: 0.793794\n\n30it [00:07,  4.76it/s]\n\n31it [00:07,  2.49it/s]\n\n32it [00:07,  2.93it/s]\n\n33it [00:08,  3.33it/s]\n\n34it [00:08,  3.67it/s]\n\n35it [00:08,  4.00it/s]\n\n36it [00:08,  4.23it/s]\n\n37it [00:08,  4.38it/s]\n\n38it [00:09,  4.53it/s]\n\n39it [00:09,  4.61it/s]\n\n40it [00:09,  4.69it/s]\niter: 40, loss: 0.788617, losses: 0.788617\n\n40it [00:09,  4.69it/s]\n\n41it [00:11,  1.19it/s]\n\n42it [00:12,  1.51it/s]\n\n43it [00:12,  1.90it/s]\n\n44it [00:12,  2.32it/s]\n\n45it [00:12,  2.74it/s]\n\n46it [00:12,  3.16it/s]\n\n47it [00:13,  3.51it/s]\n\n48it [00:13,  3.82it/s]\n\n49it [00:13,  4.06it/s]\n\n50it [00:13,  4.16it/s]\niter: 50, loss: 0.800087, losses: 0.800087\n\n50it [00:13,  4.16it/s]\n\n51it [00:14,  3.83it/s]\n\n52it [00:14,  4.07it/s]\n\n53it [00:14,  4.27it/s]\n\n54it [00:14,  4.40it/s]\n\n55it [00:14,  4.52it/s]\n\n56it [00:15,  4.59it/s]\n\n57it [00:15,  4.64it/s]\n\n58it [00:15,  4.68it/s]\n\n59it [00:15,  4.75it/s]\n\n60it [00:16,  4.76it/s]\niter: 60, loss: 0.798107, losses: 0.798107\n\n60it [00:16,  4.76it/s]\n\n61it [00:16,  3.10it/s]\n\n62it [00:16,  3.51it/s]\n\n63it [00:17,  3.80it/s]\n\n64it [00:17,  4.08it/s]\n\n65it [00:17,  4.31it/s]\n\n66it [00:17,  4.49it/s]\n\n67it [00:17,  4.61it/s]\n\n68it [00:18,  4.70it/s]\n\n69it [00:18,  4.70it/s]\n\n70it [00:18,  4.71it/s]\niter: 70, loss: 0.797794, losses: 0.797794\n\n70it [00:18,  4.71it/s]\n\n71it [00:20,  1.22it/s]\n\n72it [00:20,  1.53it/s]\n\n73it [00:21,  1.92it/s]\n\n74it [00:21,  2.33it/s]\n\n75it [00:21,  2.76it/s]\n\n76it [00:21,  3.16it/s]\n\n77it [00:22,  3.49it/s]\n\n78it [00:22,  3.81it/s]\n\n79it [00:22,  4.06it/s]\n\n80it [00:22,  4.29it/s]\niter: 80, loss: 0.784545, losses: 0.784545\n\n80it [00:22,  4.29it/s]\n\n81it [00:24,  1.26it/s]\n\n82it [00:25,  1.57it/s]\n\n83it [00:25,  1.97it/s]\n\n84it [00:25,  2.39it/s]\n\n85it [00:25,  2.81it/s]\n\n86it [00:25,  3.22it/s]\n\n87it [00:26,  3.57it/s]\n\n88it [00:26,  3.86it/s]\n\n89it [00:26,  4.09it/s]\n\n90it [00:26,  4.28it/s]\niter: 90, loss: 0.784368, losses: 0.784368\n\n90it [00:26,  4.28it/s]\n\n91it [00:27,  1.86it/s]\n\n92it [00:28,  2.30it/s]\n\n93it [00:28,  2.72it/s]\n\n94it [00:28,  3.14it/s]\n\n95it [00:28,  3.49it/s]\n\n96it [00:28,  3.79it/s]\n\n97it [00:29,  4.01it/s]\n\n98it [00:29,  4.24it/s]\n\n99it [00:29,  4.39it/s]\n\n100it [00:29,  4.54it/s]\niter: 100, loss: 0.778032, losses: 0.778032\n\n100it [00:29,  4.54it/s]\n\n101it [00:32,  1.22it/s]\n\n102it [00:32,  1.52it/s]\n\n103it [00:32,  1.91it/s]\n\n104it [00:32,  2.34it/s]\n\n105it [00:32,  2.76it/s]\n\n106it [00:33,  3.19it/s]\n\n107it [00:33,  3.53it/s]\n\n108it [00:33,  3.87it/s]\n\n109it [00:33,  4.12it/s]\n\n110it [00:33,  4.29it/s]\niter: 110, loss: 0.766626, losses: 0.766626\n\n110it [00:34,  4.29it/s]\n\n111it [00:34,  4.14it/s]\n\n112it [00:34,  4.32it/s]\n\n113it [00:34,  4.42it/s]\n\n114it [00:34,  4.59it/s]\n\n115it [00:35,  4.61it/s]\n\n116it [00:35,  4.72it/s]\n\n117it [00:35,  4.77it/s]\n\n118it [00:35,  4.77it/s]\n\n119it [00:35,  4.83it/s]\n\n120it [00:36,  4.80it/s]\niter: 120, loss: 0.776433, losses: 0.776433\n\n120it [00:36,  4.80it/s]\n\n121it [00:36,  3.05it/s]\n\n122it [00:36,  3.42it/s]\n\n123it [00:37,  3.74it/s]\n\n124it [00:37,  3.98it/s]\n\n125it [00:37,  4.20it/s]\n\n126it [00:37,  4.33it/s]\n\n127it [00:37,  4.44it/s]\n\n128it [00:38,  4.50it/s]\n\n129it [00:38,  4.58it/s]\n\n130it [00:38,  4.67it/s]\niter: 130, loss: 0.783198, losses: 0.783198\n\n130it [00:38,  4.67it/s]\n\n131it [00:40,  1.23it/s]\n\n132it [00:41,  1.56it/s]\n\n133it [00:41,  1.96it/s]\n\n134it [00:41,  2.39it/s]\n\n135it [00:41,  2.82it/s]\n\n136it [00:41,  3.20it/s]\n\n137it [00:42,  3.53it/s]\n\n138it [00:42,  3.82it/s]\n\n139it [00:42,  4.06it/s]\n\n140it [00:42,  4.26it/s]\niter: 140, loss: 0.770599, losses: 0.770599\n\n140it [00:42,  4.26it/s]\n\n141it [00:44,  1.28it/s]\n\n142it [00:44,  1.63it/s]\n\n143it [00:45,  2.03it/s]\n\n144it [00:45,  2.43it/s]\n\n145it [00:45,  2.83it/s]\n\n146it [00:45,  3.20it/s]\n\n147it [00:46,  3.53it/s]\n\n148it [00:46,  3.81it/s]\n\n149it [00:46,  4.01it/s]\n\n150it [00:46,  4.22it/s]\niter: 150, loss: 0.75432, losses: 0.75432\n\n150it [00:46,  4.22it/s]\n\n151it [00:48,  1.28it/s]\n\n152it [00:48,  1.60it/s]\n\n153it [00:49,  2.00it/s]\n\n154it [00:49,  2.43it/s]\n\n155it [00:49,  2.84it/s]\n\n156it [00:49,  3.22it/s]\n\n157it [00:50,  3.57it/s]\n\n158it [00:50,  3.84it/s]\n\n159it [00:50,  4.02it/s]\n\n160it [00:50,  4.20it/s]\niter: 160, loss: 0.766017, losses: 0.766017\n\n160it [00:50,  4.20it/s]\n\n161it [00:51,  2.33it/s]\n\n162it [00:51,  2.75it/s]\n\n163it [00:51,  3.15it/s]\n\n164it [00:52,  3.48it/s]\n\n165it [00:52,  3.77it/s]\n\n166it [00:52,  4.03it/s]\n\n167it [00:52,  4.25it/s]\n\n168it [00:53,  4.35it/s]\n\n169it [00:53,  4.47it/s]\n\n170it [00:53,  4.54it/s]\niter: 170, loss: 0.769404, losses: 0.769404\n\n170it [00:53,  4.54it/s]\n\n171it [00:53,  4.33it/s]\n\n172it [00:53,  4.41it/s]\n\n173it [00:54,  4.55it/s]\n\n174it [00:54,  4.59it/s]\n\n175it [00:54,  4.66it/s]\n\n176it [00:54,  4.65it/s]\n\n177it [00:55,  4.69it/s]\n\n178it [00:55,  4.72it/s]\n\n179it [00:55,  4.75it/s]\n\n180it [00:55,  4.72it/s]\niter: 180, loss: 0.772921, losses: 0.772921\n\n180it [00:55,  4.72it/s]\n\n181it [00:55,  4.44it/s]\n\n182it [00:56,  4.54it/s]\n\n183it [00:56,  4.57it/s]\n\n184it [00:56,  4.62it/s]\n\n185it [00:56,  4.62it/s]\n\n186it [00:56,  4.65it/s]\n\n187it [00:57,  4.68it/s]\n\n188it [00:57,  4.72it/s]\n\n189it [00:57,  4.68it/s]\n\n190it [00:57,  4.71it/s]\niter: 190, loss: 0.749382, losses: 0.749382\n\n190it [00:57,  4.71it/s]\n\n191it [00:58,  4.49it/s]\n\n192it [00:58,  4.52it/s]\n\n193it [00:58,  4.60it/s]\n\n194it [00:58,  4.66it/s]\n\n195it [00:58,  4.64it/s]\n\n196it [00:59,  4.67it/s]\n\n197it [00:59,  4.68it/s]\n\n198it [00:59,  4.69it/s]\n\n199it [00:59,  4.68it/s]\n\n200it [00:59,  4.68it/s]\niter: 200, loss: 0.770398, losses: 0.770398\n\n200it [01:00,  4.68it/s]\n\n200it [01:00,  3.32it/s]",
  "metrics": {},
  "output": [
    {
      "file": "https://replicate.delivery/mgxm/5bed9d88-48ee-44fe-bc3d-e3303b650354/out.png"
    }
  ],
  "started_at": null,
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/yt34tm4zi5arvj4bpfjp3apwqa",
    "cancel": "https://api.replicate.com/v1/predictions/yt34tm4zi5arvj4bpfjp3apwqa/cancel"
  },
  "version": "3fab04f1fa2bab29b6b22bbeee2ba5f8cf12eea543482dd28358355bcb459f11"
}

{
  "completed_at": "2021-09-09T21:49:27.989882Z",
  "created_at": "2021-09-09T21:48:33.833859Z",
  "data_removed": false,
  "error": null,
  "id": "gryw2y56h5bfncxnvn4wvb4gp4",
  "input": {
    "aspect": "widescreen",
    "prompts": "cats by Bansky",
    "quality": "draft"
  },
  "logs": "Working with z of shape (1, 256, 16, 16) = 65536 dimensions.\nloaded pretrained LPIPS loss from taming/modules/autoencoder/lpips/vgg.pth\nVQLPIPSWithDiscriminator running with hinge loss.\nRestored from models/vqgan_imagenet_f16_16384.ckpt\nUsing device:\ncuda:0\nOptimising using:\nAdam\nUsing text prompts:\n['cats by Bansky']\nUsing seed:\n2834369569982184821\n\n0it [00:00, ?it/s]\niter: 0, loss: 1.03798, losses: 1.03798\n\n0it [00:00, ?it/s]\n\n1it [00:00,  3.62it/s]\n\n2it [00:00,  3.87it/s]\n\n3it [00:00,  4.08it/s]\n\n4it [00:00,  4.26it/s]\n\n5it [00:01,  4.37it/s]\n\n6it [00:01,  4.47it/s]\n\n7it [00:01,  4.52it/s]\n\n8it [00:01,  4.60it/s]\n\n9it [00:01,  4.62it/s]\n\n10it [00:02,  4.70it/s]\niter: 10, loss: 0.908019, losses: 0.908019\n\n10it [00:02,  4.70it/s]\n\n11it [00:02,  4.46it/s]\n\n12it [00:02,  4.51it/s]\n\n13it [00:02,  4.53it/s]\n\n14it [00:03,  4.57it/s]\n\n15it [00:03,  4.64it/s]\n\n16it [00:03,  4.70it/s]\n\n17it [00:03,  4.69it/s]\n\n18it [00:03,  4.71it/s]\n\n19it [00:04,  4.72it/s]\n\n20it [00:04,  4.70it/s]\niter: 20, loss: 0.84931, losses: 0.84931\n\n20it [00:04,  4.70it/s]\n\n21it [00:04,  4.52it/s]\n\n22it [00:04,  4.57it/s]\n\n23it [00:05,  4.62it/s]\n\n24it [00:05,  4.66it/s]\n\n25it [00:05,  4.66it/s]\n\n26it [00:05,  4.69it/s]\n\n27it [00:05,  4.69it/s]\n\n28it [00:06,  4.69it/s]\n\n29it [00:06,  4.74it/s]\n\n30it [00:06,  4.72it/s]\niter: 30, loss: 0.866546, losses: 0.866546\n\n30it [00:06,  4.72it/s]\n\n31it [00:06,  4.49it/s]\n\n32it [00:06,  4.53it/s]\n\n33it [00:07,  4.55it/s]\n\n34it [00:07,  4.54it/s]\n\n35it [00:07,  4.53it/s]\n\n36it [00:07,  4.58it/s]\n\n37it [00:08,  4.62it/s]\n\n38it [00:08,  4.64it/s]\n\n39it [00:08,  4.60it/s]\n\n40it [00:08,  4.55it/s]\niter: 40, loss: 0.817893, losses: 0.817893\n\n40it [00:08,  4.55it/s]\n\n41it [00:08,  4.35it/s]\n\n42it [00:09,  4.45it/s]\n\n43it [00:09,  4.47it/s]\n\n44it [00:09,  4.53it/s]\n\n45it [00:09,  4.54it/s]\n\n46it [00:10,  4.58it/s]\n\n47it [00:10,  4.58it/s]\n\n48it [00:10,  4.64it/s]\n\n49it [00:10,  4.63it/s]\n\n50it [00:10,  4.64it/s]\niter: 50, loss: 0.812147, losses: 0.812147\n\n50it [00:11,  4.64it/s]\n\n51it [00:11,  4.41it/s]\n\n52it [00:11,  4.51it/s]\n\n53it [00:11,  4.53it/s]\n\n54it [00:11,  4.60it/s]\n\n55it [00:12,  4.59it/s]\n\n56it [00:12,  4.58it/s]\n\n57it [00:12,  4.63it/s]\n\n58it [00:12,  4.64it/s]\n\n59it [00:12,  4.63it/s]\n\n60it [00:13,  4.60it/s]\niter: 60, loss: 0.776441, losses: 0.776441\n\n60it [00:13,  4.60it/s]\n\n61it [00:13,  4.45it/s]\n\n62it [00:13,  4.53it/s]\n\n63it [00:13,  4.59it/s]\n\n64it [00:13,  4.57it/s]\n\n65it [00:14,  4.58it/s]\n\n66it [00:14,  4.61it/s]\n\n67it [00:14,  4.64it/s]\n\n68it [00:14,  4.67it/s]\n\n69it [00:15,  4.62it/s]\n\n70it [00:15,  4.62it/s]\niter: 70, loss: 0.790263, losses: 0.790263\n\n70it [00:15,  4.62it/s]\n\n71it [00:15,  4.38it/s]\n\n72it [00:15,  4.44it/s]\n\n73it [00:15,  4.51it/s]\n\n74it [00:16,  4.53it/s]\n\n75it [00:16,  4.59it/s]\n\n76it [00:16,  4.58it/s]\n\n77it [00:16,  4.62it/s]\n\n78it [00:17,  4.59it/s]\n\n79it [00:17,  4.61it/s]\n\n80it [00:17,  4.60it/s]\niter: 80, loss: 0.758861, losses: 0.758861\n\n80it [00:17,  4.60it/s]\n\n81it [00:17,  4.41it/s]\n\n82it [00:17,  4.47it/s]\n\n83it [00:18,  4.52it/s]\n\n84it [00:18,  4.59it/s]\n\n85it [00:18,  4.59it/s]\n\n86it [00:18,  4.57it/s]\n\n87it [00:19,  4.62it/s]\n\n88it [00:19,  4.66it/s]\n\n89it [00:19,  4.63it/s]\n\n90it [00:19,  4.66it/s]\niter: 90, loss: 0.772865, losses: 0.772865\n\n90it [00:19,  4.66it/s]\n\n91it [00:19,  4.44it/s]\n\n92it [00:20,  4.49it/s]\n\n93it [00:20,  4.58it/s]\n\n94it [00:20,  4.58it/s]\n\n95it [00:20,  4.63it/s]\n\n96it [00:20,  4.65it/s]\n\n97it [00:21,  4.59it/s]\n\n98it [00:21,  4.63it/s]\n\n99it [00:21,  4.62it/s]\n\n100it [00:21,  4.69it/s]\niter: 100, loss: 0.774167, losses: 0.774167\n\n100it [00:21,  4.69it/s]\n\n101it [00:22,  4.42it/s]\n\n102it [00:22,  4.49it/s]\n\n103it [00:22,  4.50it/s]\n\n104it [00:22,  4.58it/s]\n\n105it [00:22,  4.63it/s]\n\n106it [00:23,  4.54it/s]\n\n107it [00:23,  4.58it/s]\n\n108it [00:23,  4.61it/s]\n\n109it [00:23,  4.60it/s]\n\n110it [00:24,  4.63it/s]\niter: 110, loss: 0.727429, losses: 0.727429\n\n110it [00:24,  4.63it/s]\n\n111it [00:24,  4.38it/s]\n\n112it [00:24,  4.49it/s]\n\n113it [00:24,  4.56it/s]\n\n114it [00:24,  4.54it/s]\n\n115it [00:25,  4.56it/s]\n\n116it [00:25,  4.57it/s]\n\n117it [00:25,  4.61it/s]\n\n118it [00:25,  4.59it/s]\n\n119it [00:26,  4.59it/s]\n\n120it [00:26,  4.60it/s]\niter: 120, loss: 0.760857, losses: 0.760857\n\n120it [00:26,  4.60it/s]\n\n121it [00:26,  4.36it/s]\n\n122it [00:26,  4.42it/s]\n\n123it [00:26,  4.43it/s]\n\n124it [00:27,  4.47it/s]\n\n125it [00:27,  4.49it/s]\n\n126it [00:27,  4.55it/s]\n\n127it [00:27,  4.60it/s]\n\n128it [00:28,  4.55it/s]\n\n129it [00:28,  4.53it/s]\n\n130it [00:28,  4.57it/s]\niter: 130, loss: 0.730336, losses: 0.730336\n\n130it [00:28,  4.57it/s]\n\n131it [00:28,  4.37it/s]\n\n132it [00:28,  4.42it/s]\n\n133it [00:29,  4.52it/s]\n\n134it [00:29,  4.54it/s]\n\n135it [00:29,  4.56it/s]\n\n136it [00:29,  4.60it/s]\n\n137it [00:30,  4.60it/s]\n\n138it [00:30,  4.54it/s]\n\n139it [00:30,  4.56it/s]\n\n140it [00:30,  4.58it/s]\niter: 140, loss: 0.759234, losses: 0.759234\n\n140it [00:30,  4.58it/s]\n\n141it [00:30,  4.37it/s]\n\n142it [00:31,  4.42it/s]\n\n143it [00:31,  4.48it/s]\n\n144it [00:31,  4.50it/s]\n\n145it [00:31,  4.52it/s]\n\n146it [00:32,  4.58it/s]\n\n147it [00:32,  4.59it/s]\n\n148it [00:32,  4.58it/s]\n\n149it [00:32,  4.63it/s]\n\n150it [00:32,  4.62it/s]\niter: 150, loss: 0.770327, losses: 0.770327\n\n150it [00:33,  4.62it/s]\n\n151it [00:33,  4.38it/s]\n\n152it [00:33,  4.45it/s]\n\n153it [00:33,  4.48it/s]\n\n154it [00:33,  4.55it/s]\n\n155it [00:34,  4.51it/s]\n\n156it [00:34,  4.52it/s]\n\n157it [00:34,  4.56it/s]\n\n158it [00:34,  4.61it/s]\n\n159it [00:34,  4.61it/s]\n\n160it [00:35,  4.57it/s]\niter: 160, loss: 0.758196, losses: 0.758196\n\n160it [00:35,  4.57it/s]\n\n161it [00:35,  4.32it/s]\n\n162it [00:35,  4.39it/s]\n\n163it [00:35,  4.45it/s]\n\n164it [00:36,  4.43it/s]\n\n165it [00:36,  4.49it/s]\n\n166it [00:36,  4.53it/s]\n\n167it [00:36,  4.55it/s]\n\n168it [00:36,  4.59it/s]\n\n169it [00:37,  4.56it/s]\n\n170it [00:37,  4.56it/s]\niter: 170, loss: 0.775423, losses: 0.775423\n\n170it [00:37,  4.56it/s]\n\n171it [00:37,  4.32it/s]\n\n172it [00:37,  4.39it/s]\n\n173it [00:38,  4.43it/s]\n\n174it [00:38,  4.51it/s]\n\n175it [00:38,  4.53it/s]\n\n176it [00:38,  4.54it/s]\n\n177it [00:38,  4.55it/s]\n\n178it [00:39,  4.54it/s]\n\n179it [00:39,  4.51it/s]\n\n180it [00:39,  4.51it/s]\niter: 180, loss: 0.753732, losses: 0.753732\n\n180it [00:39,  4.51it/s]\n\n181it [00:39,  4.27it/s]\n\n182it [00:40,  4.42it/s]\n\n183it [00:40,  4.44it/s]\n\n184it [00:40,  4.42it/s]\n\n185it [00:40,  4.46it/s]\n\n186it [00:40,  4.49it/s]\n\n187it [00:41,  4.50it/s]\n\n188it [00:41,  4.50it/s]\n\n189it [00:41,  4.52it/s]\n\n190it [00:41,  4.53it/s]\niter: 190, loss: 0.756438, losses: 0.756438\n\n190it [00:41,  4.53it/s]\n\n191it [00:42,  4.30it/s]\n\n192it [00:42,  4.38it/s]\n\n193it [00:42,  4.43it/s]\n\n194it [00:42,  4.48it/s]\n\n195it [00:42,  4.48it/s]\n\n196it [00:43,  4.50it/s]\n\n197it [00:43,  4.52it/s]\n\n198it [00:43,  4.53it/s]\n\n199it [00:43,  4.53it/s]\n\n200it [00:44,  4.48it/s]\niter: 200, loss: 0.746095, losses: 0.746095\n\n200it [00:44,  4.48it/s]\n\n200it [00:44,  4.51it/s]",
  "metrics": {},
  "output": [
    {
      "file": "https://replicate.delivery/mgxm/dfba5a01-7fa3-4804-8533-763cb90122df/out.png"
    }
  ],
  "started_at": null,
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/gryw2y56h5bfncxnvn4wvb4gp4",
    "cancel": "https://api.replicate.com/v1/predictions/gryw2y56h5bfncxnvn4wvb4gp4/cancel"
  },
  "version": "3fab04f1fa2bab29b6b22bbeee2ba5f8cf12eea543482dd28358355bcb459f11"
}

{
  "completed_at": "2021-09-10T17:13:35.662495Z",
  "created_at": "2021-09-10T16:54:26.298159Z",
  "data_removed": false,
  "error": null,
  "id": "a5vzdlzdyjbyxg2rsmtny5jtf4",
  "input": {
    "aspect": "widescreen",
    "prompts": "sunset river snow mountain",
    "quality": "better"
  },
  "logs": "Working with z of shape (1, 256, 16, 16) = 65536 dimensions.\nDownloading: \"https://download.pytorch.org/models/vgg16-397923af.pth\" to /root/.cache/torch/hub/checkpoints/vgg16-397923af.pth\n\n  0%|          | 0.00/528M [00:00<?, ?B/s]\n\n  1%|          | 3.58M/528M [00:00<00:14, 37.5MB/s]\n\n  1%|1         | 7.39M/528M [00:00<00:14, 38.1MB/s]\n\n  6%|6         | 33.8M/528M [00:00<00:10, 51.4MB/s]\n\n 11%|#1        | 60.2M/528M [00:00<00:07, 68.1MB/s]\n\n 16%|#6        | 87.1M/528M [00:00<00:05, 88.1MB/s]\n\n 21%|##1       | 113M/528M [00:00<00:03, 111MB/s]\n\n 26%|##6       | 140M/528M [00:00<00:03, 135MB/s]\n\n 32%|###1      | 167M/528M [00:00<00:02, 160MB/s]\n\n 37%|###6      | 193M/528M [00:00<00:01, 184MB/s]\n\n 42%|####1     | 219M/528M [00:01<00:01, 204MB/s]\n\n 47%|####6     | 246M/528M [00:01<00:01, 222MB/s]\n\n 52%|#####1    | 273M/528M [00:01<00:01, 236MB/s]\n\n 57%|#####6    | 299M/528M [00:01<00:00, 247MB/s]\n\n 62%|######1   | 326M/528M [00:01<00:00, 256MB/s]\n\n 67%|######6   | 352M/528M [00:01<00:00, 261MB/s]\n\n 72%|#######1  | 378M/528M [00:01<00:00, 266MB/s]\n\n 77%|#######6  | 404M/528M [00:01<00:00, 268MB/s]\n\n 82%|########1 | 431M/528M [00:01<00:00, 272MB/s]\n\n 87%|########6 | 458M/528M [00:01<00:00, 275MB/s]\n\n 92%|#########1| 485M/528M [00:02<00:00, 277MB/s]\n\n 97%|#########6| 512M/528M [00:02<00:00, 274MB/s]\n\n100%|##########| 528M/528M [00:02<00:00, 255MB/s]\nloaded pretrained LPIPS loss from taming/modules/autoencoder/lpips/vgg.pth\nVQLPIPSWithDiscriminator running with hinge loss.\nRestored from models/vqgan_imagenet_f16_16384.ckpt\n\n  0%|                                               | 0.00/244M [00:00<?, ?iB/s]\n\n  0%|1                                      | 944k/244M [00:00<00:27, 9.31MiB/s]\n\n  2%|9                                     | 5.95M/244M [00:00<00:20, 12.4MiB/s]\n\n  4%|#3                                    | 8.63M/244M [00:00<00:16, 14.8MiB/s]\n\n  6%|##1                                   | 13.7M/244M [00:00<00:12, 19.0MiB/s]\n\n  7%|##8                                   | 18.3M/244M [00:00<00:10, 23.1MiB/s]\n\n 10%|###6                                  | 23.3M/244M [00:00<00:08, 27.7MiB/s]\n\n 11%|####3                                 | 28.0M/244M [00:00<00:07, 31.9MiB/s]\n\n 13%|#####                                 | 32.6M/244M [00:00<00:06, 35.5MiB/s]\n\n 16%|#####9                                | 37.9M/244M [00:00<00:05, 39.6MiB/s]\n\n 20%|#######4                              | 48.0M/244M [00:01<00:07, 27.7MiB/s]\n\n 21%|########                              | 51.7M/244M [00:01<00:08, 22.5MiB/s]\n\n 22%|########5                             | 54.7M/244M [00:01<00:08, 22.7MiB/s]\n\n 24%|#########1                            | 58.6M/244M [00:02<00:07, 26.2MiB/s]\n\n 26%|#########7                            | 62.5M/244M [00:02<00:06, 29.3MiB/s]\n\n 27%|##########2                           | 65.8M/244M [00:02<00:11, 15.6MiB/s]\n\n 28%|##########7                           | 68.8M/244M [00:02<00:10, 18.3MiB/s]\n\n 30%|###########2                          | 72.0M/244M [00:03<00:12, 14.8MiB/s]\n\n 30%|###########5                          | 74.2M/244M [00:03<00:13, 13.6MiB/s]\n\n 32%|############1                         | 77.8M/244M [00:03<00:10, 16.8MiB/s]\n\n 33%|############4                         | 80.1M/244M [00:03<00:10, 17.1MiB/s]\n\n 34%|#############                         | 84.1M/244M [00:03<00:08, 20.8MiB/s]\n\n 36%|#############5                        | 87.3M/244M [00:03<00:07, 23.4MiB/s]\n\n 37%|##############1                       | 90.9M/244M [00:03<00:06, 26.4MiB/s]\n\n 39%|##############7                       | 95.0M/244M [00:03<00:05, 29.9MiB/s]\n\n 41%|###############4                      | 99.0M/244M [00:03<00:04, 32.6MiB/s]\n\n 42%|################5                      | 104M/244M [00:04<00:04, 35.9MiB/s]\n\n 46%|##################                     | 113M/244M [00:04<00:03, 44.0MiB/s]\n\n 48%|##################8                    | 118M/244M [00:04<00:02, 44.9MiB/s]\n\n 50%|###################6                   | 123M/244M [00:04<00:02, 46.1MiB/s]\n\n 52%|####################4                  | 128M/244M [00:04<00:02, 43.9MiB/s]\n\n 54%|#####################2                 | 133M/244M [00:04<00:02, 44.7MiB/s]\n\n 56%|#####################9                 | 137M/244M [00:05<00:07, 15.8MiB/s]\n\n 58%|######################4                | 141M/244M [00:05<00:06, 17.5MiB/s]\n\n 59%|######################9                | 144M/244M [00:05<00:05, 20.0MiB/s]\n\n 61%|#######################5               | 148M/244M [00:05<00:04, 23.7MiB/s]\n\n 62%|########################2              | 152M/244M [00:05<00:03, 27.3MiB/s]\n\n 64%|########################7              | 155M/244M [00:06<00:08, 11.1MiB/s]\n\n 65%|#########################2             | 158M/244M [00:06<00:06, 13.1MiB/s]\n\n 66%|#########################8             | 162M/244M [00:06<00:05, 16.6MiB/s]\n\n 68%|##########################6            | 167M/244M [00:06<00:03, 20.6MiB/s]\n\n 70%|###########################3           | 171M/244M [00:07<00:03, 24.7MiB/s]\n\n 72%|############################           | 175M/244M [00:07<00:02, 28.4MiB/s]\n\n 73%|############################6          | 179M/244M [00:07<00:02, 30.5MiB/s]\n\n 75%|#############################2         | 183M/244M [00:07<00:02, 32.0MiB/s]\n\n 77%|#############################8         | 187M/244M [00:07<00:01, 34.6MiB/s]\n\n 78%|##############################4        | 191M/244M [00:07<00:01, 35.3MiB/s]\n\n 80%|###############################1       | 195M/244M [00:07<00:01, 36.9MiB/s]\n\n 82%|###############################8       | 199M/244M [00:07<00:01, 39.3MiB/s]\n\n 83%|################################5      | 204M/244M [00:07<00:01, 41.0MiB/s]\n\n 85%|#################################2     | 208M/244M [00:08<00:00, 42.0MiB/s]\n\n 87%|#################################9     | 212M/244M [00:08<00:00, 43.6MiB/s]\n\n 89%|##################################6    | 217M/244M [00:08<00:00, 39.6MiB/s]\n\n 91%|###################################3   | 221M/244M [00:08<00:00, 41.8MiB/s]\n\n 93%|####################################1  | 226M/244M [00:08<00:00, 43.3MiB/s]\n\n 95%|####################################8  | 231M/244M [00:08<00:00, 44.7MiB/s]\n\n 96%|#####################################5 | 235M/244M [00:08<00:00, 43.9MiB/s]\n\n 98%|######################################2| 239M/244M [00:08<00:00, 40.1MiB/s]\n\n100%|######################################8| 243M/244M [00:08<00:00, 40.2MiB/s]\n\n100%|#######################################| 244M/244M [00:08<00:00, 28.7MiB/s]\n\n  0%|                                               | 0.00/338M [00:00<?, ?iB/s]\n\n  0%|                                       | 864k/338M [00:00<00:41, 8.45MiB/s]\n\n  3%|#                                     | 9.55M/338M [00:00<00:29, 11.6MiB/s]\n\n  8%|###1                                  | 28.2M/338M [00:00<00:20, 16.2MiB/s]\n\n 15%|#####5                                | 49.0M/338M [00:00<00:13, 22.4MiB/s]\n\n 21%|#######9                              | 70.2M/338M [00:00<00:09, 30.7MiB/s]\n\n 25%|#########5                            | 84.7M/338M [00:00<00:06, 39.6MiB/s]\n\n 32%|############4                          | 108M/338M [00:00<00:04, 52.9MiB/s]\n\n 39%|###############1                       | 131M/338M [00:00<00:03, 69.1MiB/s]\n\n 46%|#################8                     | 155M/338M [00:00<00:02, 88.2MiB/s]\n\n 53%|#####################                   | 178M/338M [00:01<00:01, 109MiB/s]\n\n 59%|#######################7                | 201M/338M [00:01<00:01, 130MiB/s]\n\n 66%|##########################5             | 224M/338M [00:01<00:00, 151MiB/s]\n\n 73%|#############################2          | 247M/338M [00:01<00:00, 170MiB/s]\n\n 80%|################################        | 270M/338M [00:01<00:00, 187MiB/s]\n\n 87%|##################################7     | 294M/338M [00:01<00:00, 201MiB/s]\n\n 94%|#####################################4  | 316M/338M [00:01<00:00, 211MiB/s]\n\n100%|########################################| 338M/338M [00:01<00:00, 203MiB/s]\n\n  0%|                                               | 0.00/335M [00:00<?, ?iB/s]\n\n  0%|1                                      | 880k/335M [00:00<00:39, 8.81MiB/s]\n\n  3%|#                                     | 9.05M/335M [00:00<00:28, 12.1MiB/s]\n\n  9%|###3                                  | 29.5M/335M [00:00<00:19, 16.8MiB/s]\n\n 15%|#####5                                | 48.8M/335M [00:00<00:12, 23.2MiB/s]\n\n 20%|#######5                              | 66.3M/335M [00:00<00:08, 31.4MiB/s]\n\n 25%|#########6                            | 84.8M/335M [00:00<00:06, 42.0MiB/s]\n\n 31%|############                           | 104M/335M [00:00<00:04, 55.0MiB/s]\n\n 37%|##############4                        | 124M/335M [00:00<00:03, 70.6MiB/s]\n\n 42%|################5                      | 142M/335M [00:00<00:02, 87.0MiB/s]\n\n 48%|###################                     | 159M/335M [00:01<00:01, 102MiB/s]\n\n 53%|#####################1                  | 177M/335M [00:01<00:01, 115MiB/s]\n\n 58%|#######################2                | 194M/335M [00:01<00:01, 129MiB/s]\n\n 64%|#########################4              | 213M/335M [00:01<00:00, 144MiB/s]\n\n 69%|###########################7            | 232M/335M [00:01<00:00, 157MiB/s]\n\n 75%|#############################9          | 251M/335M [00:01<00:00, 167MiB/s]\n\n 80%|################################1       | 269M/335M [00:01<00:00, 173MiB/s]\n\n 86%|##################################3     | 287M/335M [00:01<00:00, 176MiB/s]\n\n 91%|####################################4   | 305M/335M [00:01<00:00, 179MiB/s]\n\n 96%|######################################5 | 323M/335M [00:01<00:00, 175MiB/s]\n\n100%|########################################| 335M/335M [00:02<00:00, 175MiB/s]\nUsing device:\ncuda:0\nOptimising using:\nAdam\nUsing text prompts:\n['sunset river snow mountain']\nUsing seed:\n13134512906597671219\n\n0it [00:00, ?it/s]\n/root/.pyenv/versions/3.8.12/lib/python3.8/site-packages/torch/nn/functional.py:3451: UserWarning: Default upsampling behavior when mode=bilinear is changed to align_corners=False since 0.4.0. Please specify align_corners=True if the old behavior is desired. See the documentation of nn.Upsample for details.\n  warnings.warn(\niter: 0, loss: 2.87432, losses: 1.01627, 0.938799, 0.919253\n\n0it [00:00, ?it/s]\n\n1it [00:01,  1.59s/it]\n\n2it [00:02,  1.46s/it]\n\n3it [00:03,  1.36s/it]\n\n4it [00:05,  1.30s/it]\n\n5it [00:06,  1.26s/it]\n\n6it [00:07,  1.23s/it]\n\n7it [00:08,  1.21s/it]\n\n8it [00:09,  1.19s/it]\n\n9it [00:10,  1.18s/it]\n\n10it [00:11,  1.17s/it]\niter: 10, loss: 2.53385, losses: 0.916875, 0.811756, 0.805219\n\n10it [00:12,  1.17s/it]\n\n11it [00:13,  1.25s/it]\n\n12it [00:14,  1.22s/it]\n\n13it [00:15,  1.20s/it]\n\n14it [00:16,  1.19s/it]\n\n15it [00:18,  1.19s/it]\n\n16it [00:19,  1.18s/it]\n\n17it [00:20,  1.18s/it]\n\n18it [00:21,  1.18s/it]\n\n19it [00:22,  1.18s/it]\n\n20it [00:23,  1.18s/it]\niter: 20, loss: 2.45401, losses: 0.8898, 0.780712, 0.7835\n\n20it [00:24,  1.18s/it]\n\n21it [00:25,  1.26s/it]\n\n22it [00:26,  1.23s/it]\n\n23it [00:27,  1.21s/it]\n\n24it [00:28,  1.21s/it]\n\n25it [00:30,  1.20s/it]\n\n26it [00:31,  1.19s/it]\n\n27it [00:32,  1.19s/it]\n\n28it [00:33,  1.19s/it]\n\n29it [00:34,  1.19s/it]\n\n30it [00:35,  1.18s/it]\niter: 30, loss: 2.39285, losses: 0.859799, 0.764968, 0.768086\n\n30it [00:36,  1.18s/it]\n\n31it [00:37,  1.27s/it]\n\n32it [00:38,  1.24s/it]\n\n33it [00:39,  1.22s/it]\n\n34it [00:40,  1.21s/it]\n\n35it [00:42,  1.20s/it]\n\n36it [00:43,  1.20s/it]\n\n37it [00:44,  1.19s/it]\n\n38it [00:45,  1.19s/it]\n\n39it [00:46,  1.19s/it]\n\n40it [00:48,  1.19s/it]\niter: 40, loss: 2.34407, losses: 0.838778, 0.751518, 0.753775\n\n40it [00:48,  1.19s/it]\n\n41it [00:49,  1.27s/it]\n\n42it [00:50,  1.24s/it]\n\n43it [00:51,  1.23s/it]\n\n44it [00:53,  1.22s/it]\n\n45it [00:54,  1.21s/it]\n\n46it [00:55,  1.21s/it]\n\n47it [00:56,  1.20s/it]\n\n48it [00:57,  1.21s/it]\n\n49it [00:59,  1.20s/it]\n\n50it [01:00,  1.20s/it]\niter: 50, loss: 2.28044, losses: 0.808476, 0.736273, 0.735691\n\n50it [01:01,  1.20s/it]\n\n51it [01:01,  1.29s/it]\n\n52it [01:02,  1.26s/it]\n\n53it [01:04,  1.24s/it]\n\n54it [01:05,  1.23s/it]\n\n55it [01:06,  1.22s/it]\n\n56it [01:07,  1.22s/it]\n\n57it [01:09,  1.22s/it]\n\n58it [01:10,  1.22s/it]\n\n59it [01:11,  1.22s/it]\n\n60it [01:12,  1.22s/it]\niter: 60, loss: 2.31961, losses: 0.821977, 0.746209, 0.751426\n\n60it [01:13,  1.22s/it]\n\n61it [01:14,  1.31s/it]\n\n62it [01:15,  1.28s/it]\n\n63it [01:16,  1.27s/it]\n\n64it [01:17,  1.26s/it]\n\n65it [01:19,  1.25s/it]\n\n66it [01:20,  1.24s/it]\n\n67it [01:21,  1.24s/it]\n\n68it [01:22,  1.24s/it]\n\n69it [01:24,  1.24s/it]\n\n70it [01:25,  1.24s/it]\niter: 70, loss: 2.25297, losses: 0.798291, 0.727504, 0.727176\n\n70it [01:26,  1.24s/it]\n\n71it [01:26,  1.33s/it]\n\n72it [01:28,  1.30s/it]\n\n73it [01:29,  1.28s/it]\n\n74it [01:30,  1.27s/it]\n\n75it [01:31,  1.27s/it]\n\n76it [01:33,  1.26s/it]\n\n77it [01:34,  1.26s/it]\n\n78it [01:35,  1.26s/it]\n\n79it [01:36,  1.26s/it]\n\n80it [01:38,  1.27s/it]\niter: 80, loss: 2.29742, losses: 0.820728, 0.735178, 0.741515\n\n80it [01:38,  1.27s/it]\n\n81it [01:39,  1.36s/it]\n\n82it [01:40,  1.33s/it]\n\n83it [01:42,  1.31s/it]\n\n84it [01:43,  1.30s/it]\n\n85it [01:44,  1.30s/it]\n\n86it [01:46,  1.29s/it]\n\n87it [01:47,  1.29s/it]\n\n88it [01:48,  1.29s/it]\n\n89it [01:49,  1.29s/it]\n\n90it [01:51,  1.29s/it]\niter: 90, loss: 2.31728, losses: 0.823852, 0.747526, 0.745903\n\n90it [01:52,  1.29s/it]\n\n91it [01:52,  1.38s/it]\n\n92it [01:54,  1.36s/it]\n\n93it [01:55,  1.34s/it]\n\n94it [01:56,  1.33s/it]\n\n95it [01:58,  1.32s/it]\n\n96it [01:59,  1.32s/it]\n\n97it [02:00,  1.32s/it]\n\n98it [02:01,  1.31s/it]\n\n99it [02:03,  1.31s/it]\n\n100it [02:04,  1.31s/it]\niter: 100, loss: 2.21957, losses: 0.775672, 0.722175, 0.721722\n\n100it [02:05,  1.31s/it]\n\n101it [02:06,  1.40s/it]\n\n102it [02:07,  1.37s/it]\n\n103it [02:08,  1.34s/it]\n\n104it [02:10,  1.32s/it]\n\n105it [02:11,  1.31s/it]\n\n106it [02:12,  1.30s/it]\n\n107it [02:13,  1.29s/it]\n\n108it [02:15,  1.29s/it]\n\n109it [02:16,  1.28s/it]\n\n110it [02:17,  1.28s/it]\niter: 110, loss: 2.20572, losses: 0.777474, 0.713529, 0.71472\n\n110it [02:18,  1.28s/it]\n\n111it [02:19,  1.37s/it]\n\n112it [02:20,  1.34s/it]\n\n113it [02:21,  1.32s/it]\n\n114it [02:23,  1.30s/it]\n\n115it [02:24,  1.29s/it]\n\n116it [02:25,  1.28s/it]\n\n117it [02:26,  1.28s/it]\n\n118it [02:28,  1.28s/it]\n\n119it [02:29,  1.27s/it]\n\n120it [02:30,  1.26s/it]\niter: 120, loss: 2.25052, losses: 0.793996, 0.726703, 0.729821\n\n120it [02:31,  1.26s/it]\n\n121it [02:32,  1.35s/it]\n\n122it [02:33,  1.32s/it]\n\n123it [02:34,  1.30s/it]\n\n124it [02:35,  1.29s/it]\n\n125it [02:37,  1.28s/it]\n\n126it [02:38,  1.27s/it]\n\n127it [02:39,  1.26s/it]\n\n128it [02:40,  1.26s/it]\n\n129it [02:42,  1.26s/it]\n\n130it [02:43,  1.26s/it]\niter: 130, loss: 2.26218, losses: 0.801104, 0.73463, 0.726444\n\n130it [02:44,  1.26s/it]\n\n131it [02:45,  1.35s/it]\n\n132it [02:46,  1.32s/it]\n\n133it [02:47,  1.30s/it]\n\n134it [02:48,  1.28s/it]\n\n135it [02:50,  1.28s/it]\n\n136it [02:51,  1.27s/it]\n\n137it [02:52,  1.26s/it]\n\n138it [02:53,  1.26s/it]\n\n139it [02:55,  1.26s/it]\n\n140it [02:56,  1.26s/it]\niter: 140, loss: 2.21133, losses: 0.776866, 0.720238, 0.714226\n\n140it [02:57,  1.26s/it]\n\n141it [02:57,  1.35s/it]\n\n142it [02:59,  1.32s/it]\n\n143it [03:00,  1.30s/it]\n\n144it [03:01,  1.29s/it]\n\n145it [03:02,  1.28s/it]\n\n146it [03:04,  1.28s/it]\n\n147it [03:05,  1.27s/it]\n\n148it [03:06,  1.27s/it]\n\n149it [03:07,  1.27s/it]\n\n150it [03:09,  1.27s/it]\niter: 150, loss: 2.25043, losses: 0.79191, 0.725539, 0.732977\n\n150it [03:10,  1.27s/it]\n\n151it [03:10,  1.36s/it]\n\n152it [03:12,  1.33s/it]\n\n153it [03:13,  1.31s/it]\n\n154it [03:14,  1.30s/it]\n\n155it [03:15,  1.29s/it]\n\n156it [03:17,  1.28s/it]\n\n157it [03:18,  1.28s/it]\n\n158it [03:19,  1.28s/it]\n\n159it [03:20,  1.27s/it]\n\n160it [03:22,  1.27s/it]\niter: 160, loss: 2.23944, losses: 0.787206, 0.723273, 0.728956\n\n160it [03:22,  1.27s/it]\n\n161it [03:23,  1.36s/it]\n\n162it [03:25,  1.33s/it]\n\n163it [03:26,  1.31s/it]\n\n164it [03:27,  1.30s/it]\n\n165it [03:28,  1.29s/it]\n\n166it [03:30,  1.29s/it]\n\n167it [03:31,  1.28s/it]\n\n168it [03:32,  1.28s/it]\n\n169it [03:33,  1.28s/it]\n\n170it [03:35,  1.28s/it]\niter: 170, loss: 2.18366, losses: 0.763624, 0.708966, 0.711072\n\n170it [03:36,  1.28s/it]\n\n171it [03:36,  1.37s/it]\n\n172it [03:38,  1.34s/it]\n\n173it [03:39,  1.32s/it]\n\n174it [03:40,  1.31s/it]\n\n175it [03:41,  1.29s/it]\n\n176it [03:43,  1.29s/it]\n\n177it [03:44,  1.28s/it]\n\n178it [03:45,  1.27s/it]\n\n179it [03:46,  1.27s/it]\n\n180it [03:48,  1.27s/it]\niter: 180, loss: 2.17656, losses: 0.758799, 0.708682, 0.709082\n\n180it [03:49,  1.27s/it]\n\n181it [03:49,  1.36s/it]\n\n182it [03:51,  1.33s/it]\n\n183it [03:52,  1.31s/it]\n\n184it [03:53,  1.30s/it]\n\n185it [03:54,  1.29s/it]\n\n186it [03:56,  1.28s/it]\n\n187it [03:57,  1.28s/it]\n\n188it [03:58,  1.27s/it]\n\n189it [03:59,  1.27s/it]\n\n190it [04:01,  1.27s/it]\niter: 190, loss: 2.25759, losses: 0.795768, 0.727799, 0.734025\n\n190it [04:01,  1.27s/it]\n\n191it [04:02,  1.36s/it]\n\n192it [04:04,  1.33s/it]\n\n193it [04:05,  1.31s/it]\n\n194it [04:06,  1.30s/it]\n\n195it [04:07,  1.29s/it]\n\n196it [04:09,  1.28s/it]\n\n197it [04:10,  1.27s/it]\n\n198it [04:11,  1.27s/it]\n\n199it [04:12,  1.27s/it]\n\n200it [04:14,  1.27s/it]\niter: 200, loss: 2.22929, losses: 0.786578, 0.719772, 0.722939\n\n200it [04:14,  1.27s/it]\n\n201it [04:15,  1.36s/it]\n\n202it [04:16,  1.33s/it]\n\n203it [04:18,  1.31s/it]\n\n204it [04:19,  1.29s/it]\n\n205it [04:20,  1.28s/it]\n\n206it [04:21,  1.28s/it]\n\n207it [04:23,  1.27s/it]\n\n208it [04:24,  1.27s/it]\n\n209it [04:25,  1.26s/it]\n\n210it [04:27,  1.27s/it]\niter: 210, loss: 2.17118, losses: 0.76052, 0.702163, 0.708499\n\n210it [04:27,  1.27s/it]\n\n211it [04:28,  1.36s/it]\n\n212it [04:29,  1.33s/it]\n\n213it [04:31,  1.31s/it]\n\n214it [04:32,  1.30s/it]\n\n215it [04:33,  1.29s/it]\n\n216it [04:34,  1.28s/it]\n\n217it [04:36,  1.28s/it]\n\n218it [04:37,  1.28s/it]\n\n219it [04:38,  1.27s/it]\n\n220it [04:40,  1.27s/it]\niter: 220, loss: 2.18328, losses: 0.76311, 0.707958, 0.712216\n\n220it [04:40,  1.27s/it]\n\n221it [04:41,  1.36s/it]\n\n222it [04:42,  1.33s/it]\n\n223it [04:44,  1.31s/it]\n\n224it [04:45,  1.30s/it]\n\n225it [04:46,  1.29s/it]\n\n226it [04:47,  1.29s/it]\n\n227it [04:49,  1.28s/it]\n\n228it [04:50,  1.28s/it]\n\n229it [04:51,  1.27s/it]\n\n230it [04:53,  1.27s/it]\niter: 230, loss: 2.25154, losses: 0.798176, 0.722844, 0.730516\n\n230it [04:53,  1.27s/it]\n\n231it [04:54,  1.37s/it]\n\n232it [04:55,  1.33s/it]\n\n233it [04:57,  1.32s/it]\n\n234it [04:58,  1.30s/it]\n\n235it [04:59,  1.29s/it]\n\n236it [05:00,  1.28s/it]\n\n237it [05:02,  1.28s/it]\n\n238it [05:03,  1.28s/it]\n\n239it [05:04,  1.28s/it]\n\n240it [05:06,  1.28s/it]\niter: 240, loss: 2.17989, losses: 0.761402, 0.708513, 0.709976\n\n240it [05:06,  1.28s/it]\n\n241it [05:07,  1.37s/it]\n\n242it [05:08,  1.34s/it]\n\n243it [05:10,  1.32s/it]\n\n244it [05:11,  1.31s/it]\n\n245it [05:12,  1.30s/it]\n\n246it [05:13,  1.29s/it]\n\n247it [05:15,  1.28s/it]\n\n248it [05:16,  1.28s/it]\n\n249it [05:17,  1.28s/it]\n\n250it [05:19,  1.28s/it]\niter: 250, loss: 2.17274, losses: 0.757853, 0.704662, 0.710222\n\n250it [05:19,  1.28s/it]\n\n251it [05:20,  1.37s/it]\n\n252it [05:21,  1.34s/it]\n\n253it [05:23,  1.32s/it]\n\n254it [05:24,  1.30s/it]\n\n255it [05:25,  1.29s/it]\n\n256it [05:27,  1.29s/it]\n\n257it [05:28,  1.28s/it]\n\n258it [05:29,  1.28s/it]\n\n259it [05:30,  1.27s/it]\n\n260it [05:32,  1.27s/it]\niter: 260, loss: 2.21905, losses: 0.783277, 0.714188, 0.721587\n\n260it [05:32,  1.27s/it]\n\n261it [05:33,  1.36s/it]\n\n262it [05:34,  1.33s/it]\n\n263it [05:36,  1.31s/it]\n\n264it [05:37,  1.30s/it]\n\n265it [05:38,  1.29s/it]\n\n266it [05:39,  1.28s/it]\n\n267it [05:41,  1.28s/it]\n\n268it [05:42,  1.27s/it]\n\n269it [05:43,  1.27s/it]\n\n270it [05:45,  1.27s/it]\niter: 270, loss: 2.16962, losses: 0.76268, 0.702876, 0.704061\n\n270it [05:45,  1.27s/it]\n\n271it [05:46,  1.36s/it]\n\n272it [05:47,  1.33s/it]\n\n273it [05:49,  1.31s/it]\n\n274it [05:50,  1.30s/it]\n\n275it [05:51,  1.29s/it]\n\n276it [05:52,  1.28s/it]\n\n277it [05:54,  1.28s/it]\n\n278it [05:55,  1.27s/it]\n\n279it [05:56,  1.27s/it]\n\n280it [05:57,  1.27s/it]\niter: 280, loss: 2.24343, losses: 0.79148, 0.723849, 0.7281\n\n280it [05:58,  1.27s/it]\n\n281it [05:59,  1.36s/it]\n\n282it [06:00,  1.33s/it]\n\n283it [06:02,  1.31s/it]\n\n284it [06:03,  1.30s/it]\n\n285it [06:04,  1.29s/it]\n\n286it [06:05,  1.28s/it]\n\n287it [06:07,  1.28s/it]\n\n288it [06:08,  1.27s/it]\n\n289it [06:09,  1.27s/it]\n\n290it [06:10,  1.27s/it]\niter: 290, loss: 2.25858, losses: 0.797974, 0.727931, 0.732673\n\n290it [06:11,  1.27s/it]\n\n291it [06:12,  1.37s/it]\n\n292it [06:13,  1.34s/it]\n\n293it [06:15,  1.32s/it]\n\n294it [06:16,  1.31s/it]\n\n295it [06:17,  1.30s/it]\n\n296it [06:18,  1.29s/it]\n\n297it [06:20,  1.29s/it]\n\n298it [06:21,  1.28s/it]\n\n299it [06:22,  1.28s/it]\n\n300it [06:24,  1.28s/it]\niter: 300, loss: 2.23411, losses: 0.790873, 0.71901, 0.724229\n\n300it [06:24,  1.28s/it]\n\n301it [06:25,  1.37s/it]\n\n302it [06:26,  1.34s/it]\n\n303it [06:28,  1.32s/it]\n\n304it [06:29,  1.31s/it]\n\n305it [06:30,  1.30s/it]\n\n306it [06:31,  1.29s/it]\n\n307it [06:33,  1.28s/it]\n\n308it [06:34,  1.28s/it]\n\n309it [06:35,  1.28s/it]\n\n310it [06:37,  1.28s/it]\niter: 310, loss: 2.2213, losses: 0.781752, 0.718001, 0.721544\n\n310it [06:37,  1.28s/it]\n\n311it [06:38,  1.37s/it]\n\n312it [06:39,  1.34s/it]\n\n313it [06:41,  1.32s/it]\n\n314it [06:42,  1.30s/it]\n\n315it [06:43,  1.29s/it]\n\n316it [06:44,  1.28s/it]\n\n317it [06:46,  1.28s/it]\n\n318it [06:47,  1.28s/it]\n\n319it [06:48,  1.27s/it]\n\n320it [06:50,  1.27s/it]\niter: 320, loss: 2.22429, losses: 0.782343, 0.717883, 0.724067\n\n320it [06:50,  1.27s/it]\n\n321it [06:51,  1.36s/it]\n\n322it [06:52,  1.34s/it]\n\n323it [06:54,  1.31s/it]\n\n324it [06:55,  1.30s/it]\n\n325it [06:56,  1.29s/it]\n\n326it [06:57,  1.28s/it]\n\n327it [06:59,  1.28s/it]\n\n328it [07:00,  1.28s/it]\n\n329it [07:01,  1.27s/it]\n\n330it [07:03,  1.27s/it]\niter: 330, loss: 2.22646, losses: 0.786218, 0.717032, 0.72321\n\n330it [07:03,  1.27s/it]\n\n331it [07:04,  1.36s/it]\n\n332it [07:05,  1.33s/it]\n\n333it [07:07,  1.31s/it]\n\n334it [07:08,  1.30s/it]\n\n335it [07:09,  1.28s/it]\n\n336it [07:10,  1.28s/it]\n\n337it [07:12,  1.27s/it]\n\n338it [07:13,  1.27s/it]\n\n339it [07:14,  1.27s/it]\n\n340it [07:15,  1.26s/it]\niter: 340, loss: 2.241, losses: 0.793107, 0.72127, 0.726618\n\n340it [07:16,  1.26s/it]\n\n341it [07:17,  1.35s/it]\n\n342it [07:18,  1.33s/it]\n\n343it [07:20,  1.31s/it]\n\n344it [07:21,  1.29s/it]\n\n345it [07:22,  1.28s/it]\n\n346it [07:23,  1.28s/it]\n\n347it [07:25,  1.27s/it]\n\n348it [07:26,  1.27s/it]\n\n349it [07:27,  1.27s/it]\n\n350it [07:28,  1.27s/it]\niter: 350, loss: 2.23518, losses: 0.784114, 0.722871, 0.728196\n\n350it [07:29,  1.27s/it]\n\n351it [07:30,  1.36s/it]\n\n352it [07:31,  1.33s/it]\n\n353it [07:33,  1.31s/it]\n\n354it [07:34,  1.30s/it]\n\n355it [07:35,  1.29s/it]\n\n356it [07:36,  1.28s/it]\n\n357it [07:38,  1.28s/it]\n\n358it [07:39,  1.28s/it]\n\n359it [07:40,  1.27s/it]\n\n360it [07:41,  1.27s/it]\niter: 360, loss: 2.22824, losses: 0.786418, 0.718143, 0.72368\n\n360it [07:42,  1.27s/it]\n\n361it [07:43,  1.36s/it]\n\n362it [07:44,  1.33s/it]\n\n363it [07:45,  1.32s/it]\n\n364it [07:47,  1.30s/it]\n\n365it [07:48,  1.29s/it]\n\n366it [07:49,  1.28s/it]\n\n367it [07:51,  1.28s/it]\n\n368it [07:52,  1.28s/it]\n\n369it [07:53,  1.28s/it]\n\n370it [07:54,  1.28s/it]\niter: 370, loss: 2.17586, losses: 0.76504, 0.702395, 0.708423\n\n370it [07:55,  1.28s/it]\n\n371it [07:56,  1.37s/it]\n\n372it [07:57,  1.34s/it]\n\n373it [07:59,  1.32s/it]\n\n374it [08:00,  1.31s/it]\n\n375it [08:01,  1.29s/it]\n\n376it [08:02,  1.29s/it]\n\n377it [08:04,  1.28s/it]\n\n378it [08:05,  1.28s/it]\n\n379it [08:06,  1.27s/it]\n\n380it [08:07,  1.27s/it]\niter: 380, loss: 2.16247, losses: 0.75774, 0.699513, 0.705221\n\n380it [08:08,  1.27s/it]\n\n381it [08:09,  1.37s/it]\n\n382it [08:10,  1.34s/it]\n\n383it [08:12,  1.32s/it]\n\n384it [08:13,  1.30s/it]\n\n385it [08:14,  1.29s/it]\n\n386it [08:15,  1.29s/it]\n\n387it [08:17,  1.28s/it]\n\n388it [08:18,  1.28s/it]\n\n389it [08:19,  1.28s/it]\n\n390it [08:20,  1.27s/it]\niter: 390, loss: 2.1718, losses: 0.759508, 0.704626, 0.707668\n\n390it [08:21,  1.27s/it]\n\n391it [08:22,  1.37s/it]\n\n392it [08:23,  1.33s/it]\n\n393it [08:25,  1.32s/it]\n\n394it [08:26,  1.30s/it]\n\n395it [08:27,  1.29s/it]\n\n396it [08:28,  1.29s/it]\n\n397it [08:30,  1.28s/it]\n\n398it [08:31,  1.28s/it]\n\n399it [08:32,  1.28s/it]\n\n400it [08:33,  1.27s/it]\niter: 400, loss: 2.17667, losses: 0.763937, 0.705741, 0.706996\n\n400it [08:34,  1.27s/it]\n\n401it [08:35,  1.36s/it]\n\n402it [08:36,  1.33s/it]\n\n403it [08:38,  1.31s/it]\n\n404it [08:39,  1.30s/it]\n\n405it [08:40,  1.29s/it]\n\n406it [08:41,  1.28s/it]\n\n407it [08:43,  1.27s/it]\n\n408it [08:44,  1.27s/it]\n\n409it [08:45,  1.27s/it]\n\n410it [08:46,  1.27s/it]\niter: 410, loss: 2.16414, losses: 0.755274, 0.701243, 0.707625\n\n410it [08:47,  1.27s/it]\n\n411it [08:48,  1.36s/it]\n\n412it [08:49,  1.33s/it]\n\n413it [08:50,  1.31s/it]\n\n414it [08:52,  1.30s/it]\n\n415it [08:53,  1.29s/it]\n\n416it [08:54,  1.28s/it]\n\n417it [08:56,  1.27s/it]\n\n418it [08:57,  1.27s/it]\n\n419it [08:58,  1.27s/it]\n\n420it [08:59,  1.26s/it]\niter: 420, loss: 2.24109, losses: 0.795919, 0.721658, 0.723515\n\n420it [09:00,  1.26s/it]\n\n421it [09:01,  1.36s/it]\n\n422it [09:02,  1.33s/it]\n\n423it [09:03,  1.31s/it]\n\n424it [09:05,  1.30s/it]\n\n425it [09:06,  1.29s/it]\n\n426it [09:07,  1.28s/it]\n\n427it [09:08,  1.27s/it]\n\n428it [09:10,  1.27s/it]\n\n429it [09:11,  1.27s/it]\n\n430it [09:12,  1.27s/it]\niter: 430, loss: 2.23592, losses: 0.787732, 0.720089, 0.728098\n\n430it [09:13,  1.27s/it]\n\n431it [09:14,  1.37s/it]\n\n432it [09:15,  1.33s/it]\n\n433it [09:16,  1.31s/it]\n\n434it [09:18,  1.30s/it]\n\n435it [09:19,  1.29s/it]\n\n436it [09:20,  1.28s/it]\n\n437it [09:21,  1.28s/it]\n\n438it [09:23,  1.27s/it]\n\n439it [09:24,  1.27s/it]\n\n440it [09:25,  1.27s/it]\niter: 440, loss: 2.24819, losses: 0.792399, 0.723132, 0.732659\n\n440it [09:26,  1.27s/it]\n\n441it [09:27,  1.37s/it]\n\n442it [09:28,  1.33s/it]\n\n443it [09:29,  1.32s/it]\n\n444it [09:31,  1.30s/it]\n\n445it [09:32,  1.29s/it]\n\n446it [09:33,  1.29s/it]\n\n447it [09:34,  1.28s/it]\n\n448it [09:36,  1.27s/it]\n\n449it [09:37,  1.27s/it]\n\n450it [09:38,  1.27s/it]\niter: 450, loss: 2.23246, losses: 0.783947, 0.719741, 0.728769\n\n450it [09:39,  1.27s/it]\n\n451it [09:40,  1.37s/it]\n\n452it [09:41,  1.34s/it]\n\n453it [09:42,  1.32s/it]\n\n454it [09:44,  1.30s/it]\n\n455it [09:45,  1.29s/it]\n\n456it [09:46,  1.29s/it]\n\n457it [09:47,  1.28s/it]\n\n458it [09:49,  1.28s/it]\n\n459it [09:50,  1.27s/it]\n\n460it [09:51,  1.27s/it]\niter: 460, loss: 2.27599, losses: 0.815376, 0.726655, 0.733957\n\n460it [09:52,  1.27s/it]\n\n461it [09:53,  1.37s/it]\n\n462it [09:54,  1.34s/it]\n\n463it [09:55,  1.32s/it]\n\n464it [09:57,  1.30s/it]\n\n465it [09:58,  1.29s/it]\n\n466it [09:59,  1.29s/it]\n\n467it [10:00,  1.28s/it]\n\n468it [10:02,  1.28s/it]\n\n469it [10:03,  1.27s/it]\n\n470it [10:04,  1.27s/it]\niter: 470, loss: 2.20068, losses: 0.773851, 0.712334, 0.714499\n\n470it [10:05,  1.27s/it]\n\n471it [10:06,  1.36s/it]\n\n472it [10:07,  1.33s/it]\n\n473it [10:08,  1.31s/it]\n\n474it [10:10,  1.30s/it]\n\n475it [10:11,  1.29s/it]\n\n476it [10:12,  1.28s/it]\n\n477it [10:13,  1.28s/it]\n\n478it [10:15,  1.27s/it]\n\n479it [10:16,  1.27s/it]\n\n480it [10:17,  1.27s/it]\niter: 480, loss: 2.23543, losses: 0.794325, 0.717294, 0.723813\n\n480it [10:18,  1.27s/it]\n\n481it [10:19,  1.36s/it]\n\n482it [10:20,  1.33s/it]\n\n483it [10:21,  1.31s/it]\n\n484it [10:23,  1.30s/it]\n\n485it [10:24,  1.29s/it]\n\n486it [10:25,  1.28s/it]\n\n487it [10:26,  1.28s/it]\n\n488it [10:28,  1.27s/it]\n\n489it [10:29,  1.27s/it]\n\n490it [10:30,  1.27s/it]\niter: 490, loss: 2.23271, losses: 0.794116, 0.716999, 0.721594\n\n490it [10:31,  1.27s/it]\n\n491it [10:32,  1.37s/it]\n\n492it [10:33,  1.33s/it]\n\n493it [10:34,  1.32s/it]\n\n494it [10:36,  1.30s/it]\n\n495it [10:37,  1.29s/it]\n\n496it [10:38,  1.28s/it]\n\n497it [10:39,  1.28s/it]\n\n498it [10:41,  1.27s/it]\n\n499it [10:42,  1.27s/it]\n\n500it [10:43,  1.27s/it]\niter: 500, loss: 2.2241, losses: 0.787178, 0.715713, 0.72121\n\n500it [10:44,  1.27s/it]\n\n500it [10:45,  1.29s/it]",
  "metrics": {},
  "output": [
    {
      "file": "https://replicate.delivery/mgxm/a19baad3-3d31-404c-9893-5784f1eb532f/out.png"
    }
  ],
  "started_at": null,
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/a5vzdlzdyjbyxg2rsmtny5jtf4",
    "cancel": "https://api.replicate.com/v1/predictions/a5vzdlzdyjbyxg2rsmtny5jtf4/cancel"
  },
  "version": "3fab04f1fa2bab29b6b22bbeee2ba5f8cf12eea543482dd28358355bcb459f11"
}

{
  "completed_at": "2021-09-21T15:49:03.126574Z",
  "created_at": "2021-09-21T15:43:48.641034Z",
  "data_removed": false,
  "error": null,
  "id": "nkyhl3jfpfaprjblubnsexssoq",
  "input": {
    "aspect": "widescreen",
    "prompts": "sunset river snow mountain",
    "quality": "normal"
  },
  "logs": "Working with z of shape (1, 256, 16, 16) = 65536 dimensions.\nloaded pretrained LPIPS loss from taming/modules/autoencoder/lpips/vgg.pth\nVQLPIPSWithDiscriminator running with hinge loss.\nRestored from models/vqgan_imagenet_f16_16384.ckpt\n\n  0%|                                               | 0.00/335M [00:00<?, ?iB/s]\n\n  0%|                                       | 736k/335M [00:00<00:55, 6.25MiB/s]\n\n  3%|#1                                    | 9.78M/335M [00:00<00:39, 8.69MiB/s]\n\n  8%|###1                                  | 28.0M/335M [00:00<00:26, 12.2MiB/s]\n\n 14%|#####3                                | 47.2M/335M [00:00<00:17, 17.0MiB/s]\n\n 21%|########                              | 70.6M/335M [00:00<00:11, 23.5MiB/s]\n\n 28%|##########7                           | 94.9M/335M [00:00<00:07, 32.3MiB/s]\n\n 34%|#############2                         | 114M/335M [00:00<00:05, 43.1MiB/s]\n\n 41%|###############8                       | 136M/335M [00:00<00:03, 57.1MiB/s]\n\n 47%|##################4                    | 159M/335M [00:00<00:02, 74.0MiB/s]\n\n 55%|#####################3                 | 183M/335M [00:01<00:01, 94.0MiB/s]\n\n 61%|########################4               | 204M/335M [00:01<00:01, 103MiB/s]\n\n 67%|##########################6             | 223M/335M [00:01<00:01, 103MiB/s]\n\n 72%|############################6           | 240M/335M [00:01<00:00, 116MiB/s]\n\n 78%|###############################1        | 261M/335M [00:01<00:00, 136MiB/s]\n\n 84%|#################################7      | 282M/335M [00:01<00:00, 154MiB/s]\n\n 90%|####################################    | 302M/335M [00:01<00:00, 167MiB/s]\n\n 96%|######################################3 | 321M/335M [00:01<00:00, 175MiB/s]\n\n100%|########################################| 335M/335M [00:01<00:00, 178MiB/s]\nUsing device:\ncuda:0\nOptimising using:\nAdam\nUsing text prompts:\n['sunset river snow mountain']\nUsing seed:\n7059562411278813627\n\n0it [00:00, ?it/s]\niter: 0, loss: 1.87591, losses: 0.945593, 0.930314\n\n0it [00:00, ?it/s]\n\n1it [00:00,  1.02it/s]\n\n2it [00:01,  1.06it/s]\n\n3it [00:02,  1.09it/s]\n\n4it [00:03,  1.12it/s]\n\n5it [00:04,  1.13it/s]\n\n6it [00:05,  1.14it/s]\n\n7it [00:06,  1.15it/s]\n\n8it [00:06,  1.16it/s]\n\n9it [00:07,  1.15it/s]\n\n10it [00:08,  1.13it/s]\niter: 10, loss: 1.66744, losses: 0.83799, 0.829451\n\n10it [00:09,  1.13it/s]\n\n11it [00:09,  1.02it/s]\n\n12it [00:11,  1.04s/it]\n\n13it [00:12,  1.08s/it]\n\n14it [00:13,  1.07s/it]\n\n15it [00:14,  1.03s/it]\n\n16it [00:15,  1.01s/it]\n\n17it [00:16,  1.01it/s]\n\n18it [00:17,  1.02it/s]\n\n19it [00:18,  1.06it/s]\n\n20it [00:18,  1.10it/s]\niter: 20, loss: 1.56737, losses: 0.785052, 0.78232\n\n20it [00:19,  1.10it/s]\n\n21it [00:19,  1.07it/s]\n\n22it [00:20,  1.10it/s]\n\n23it [00:21,  1.12it/s]\n\n24it [00:22,  1.14it/s]\n\n25it [00:23,  1.15it/s]\n\n26it [00:24,  1.16it/s]\n\n27it [00:24,  1.16it/s]\n\n28it [00:25,  1.17it/s]\n\n29it [00:26,  1.17it/s]\n\n30it [00:27,  1.17it/s]\niter: 30, loss: 1.55591, losses: 0.781376, 0.774534\n\n30it [00:27,  1.17it/s]\n\n31it [00:28,  1.12it/s]\n\n32it [00:29,  1.14it/s]\n\n33it [00:30,  1.15it/s]\n\n34it [00:31,  1.16it/s]\n\n35it [00:31,  1.16it/s]\n\n36it [00:32,  1.17it/s]\n\n37it [00:33,  1.17it/s]\n\n38it [00:34,  1.18it/s]\n\n39it [00:35,  1.18it/s]\n\n40it [00:36,  1.19it/s]\niter: 40, loss: 1.53087, losses: 0.772241, 0.758628\n\n40it [00:36,  1.19it/s]\n\n41it [00:37,  1.14it/s]\n\n42it [00:37,  1.16it/s]\n\n43it [00:38,  1.17it/s]\n\n44it [00:39,  1.18it/s]\n\n45it [00:40,  1.19it/s]\n\n46it [00:41,  1.19it/s]\n\n47it [00:42,  1.20it/s]\n\n48it [00:42,  1.20it/s]\n\n49it [00:43,  1.20it/s]\n\n50it [00:44,  1.21it/s]\niter: 50, loss: 1.50661, losses: 0.759649, 0.746958\n\n50it [00:44,  1.21it/s]\n\n51it [00:45,  1.15it/s]\n\n52it [00:46,  1.17it/s]\n\n53it [00:47,  1.18it/s]\n\n54it [00:47,  1.19it/s]\n\n55it [00:48,  1.19it/s]\n\n56it [00:49,  1.20it/s]\n\n57it [00:50,  1.20it/s]\n\n58it [00:51,  1.21it/s]\n\n59it [00:52,  1.21it/s]\n\n60it [00:52,  1.21it/s]\niter: 60, loss: 1.5028, losses: 0.759857, 0.74294\n\n60it [00:53,  1.21it/s]\n\n61it [00:53,  1.15it/s]\n\n62it [00:54,  1.17it/s]\n\n63it [00:55,  1.18it/s]\n\n64it [00:56,  1.19it/s]\n\n65it [00:57,  1.20it/s]\n\n66it [00:58,  1.20it/s]\n\n67it [00:58,  1.21it/s]\n\n68it [00:59,  1.21it/s]\n\n69it [01:00,  1.21it/s]\n\n70it [01:01,  1.21it/s]\niter: 70, loss: 1.49035, losses: 0.75404, 0.736313\n\n70it [01:01,  1.21it/s]\n\n71it [01:02,  1.15it/s]\n\n72it [01:03,  1.17it/s]\n\n73it [01:03,  1.19it/s]\n\n74it [01:04,  1.20it/s]\n\n75it [01:05,  1.20it/s]\n\n76it [01:06,  1.21it/s]\n\n77it [01:07,  1.21it/s]\n\n78it [01:07,  1.22it/s]\n\n79it [01:08,  1.22it/s]\n\n80it [01:09,  1.22it/s]\niter: 80, loss: 1.48894, losses: 0.754004, 0.734938\n\n80it [01:10,  1.22it/s]\n\n81it [01:10,  1.16it/s]\n\n82it [01:11,  1.17it/s]\n\n83it [01:12,  1.19it/s]\n\n84it [01:13,  1.20it/s]\n\n85it [01:13,  1.20it/s]\n\n86it [01:14,  1.21it/s]\n\n87it [01:15,  1.21it/s]\n\n88it [01:16,  1.21it/s]\n\n89it [01:17,  1.21it/s]\n\n90it [01:17,  1.21it/s]\niter: 90, loss: 1.46546, losses: 0.740261, 0.725197\n\n90it [01:18,  1.21it/s]\n\n91it [01:18,  1.15it/s]\n\n92it [01:19,  1.17it/s]\n\n93it [01:20,  1.18it/s]\n\n94it [01:21,  1.19it/s]\n\n95it [01:22,  1.20it/s]\n\n96it [01:23,  1.20it/s]\n\n97it [01:23,  1.20it/s]\n\n98it [01:24,  1.21it/s]\n\n99it [01:25,  1.20it/s]\n\n100it [01:26,  1.21it/s]\niter: 100, loss: 1.47515, losses: 0.745841, 0.729311\n\n100it [01:26,  1.21it/s]\n\n101it [01:27,  1.15it/s]\n\n102it [01:28,  1.17it/s]\n\n103it [01:29,  1.18it/s]\n\n104it [01:29,  1.19it/s]\n\n105it [01:30,  1.20it/s]\n\n106it [01:31,  1.20it/s]\n\n107it [01:32,  1.20it/s]\n\n108it [01:33,  1.20it/s]\n\n109it [01:33,  1.20it/s]\n\n110it [01:34,  1.21it/s]\niter: 110, loss: 1.48614, losses: 0.754961, 0.731177\n\n110it [01:35,  1.21it/s]\n\n111it [01:35,  1.15it/s]\n\n112it [01:36,  1.17it/s]\n\n113it [01:37,  1.18it/s]\n\n114it [01:38,  1.19it/s]\n\n115it [01:39,  1.19it/s]\n\n116it [01:39,  1.20it/s]\n\n117it [01:40,  1.20it/s]\n\n118it [01:41,  1.20it/s]\n\n119it [01:42,  1.20it/s]\n\n120it [01:43,  1.20it/s]\niter: 120, loss: 1.43145, losses: 0.728015, 0.703438\n\n120it [01:43,  1.20it/s]\n\n121it [01:44,  1.14it/s]\n\n122it [01:45,  1.16it/s]\n\n123it [01:45,  1.17it/s]\n\n124it [01:46,  1.18it/s]\n\n125it [01:47,  1.19it/s]\n\n126it [01:48,  1.19it/s]\n\n127it [01:49,  1.19it/s]\n\n128it [01:50,  1.20it/s]\n\n129it [01:50,  1.20it/s]\n\n130it [01:51,  1.20it/s]\niter: 130, loss: 1.4728, losses: 0.749317, 0.723478\n\n130it [01:52,  1.20it/s]\n\n131it [01:52,  1.14it/s]\n\n132it [01:53,  1.15it/s]\n\n133it [01:54,  1.17it/s]\n\n134it [01:55,  1.18it/s]\n\n135it [01:56,  1.19it/s]\n\n136it [01:56,  1.19it/s]\n\n137it [01:57,  1.19it/s]\n\n138it [01:58,  1.19it/s]\n\n139it [01:59,  1.20it/s]\n\n140it [02:00,  1.19it/s]\niter: 140, loss: 1.47461, losses: 0.745884, 0.728723\n\n140it [02:00,  1.19it/s]\n\n141it [02:01,  1.13it/s]\n\n142it [02:02,  1.16it/s]\n\n143it [02:02,  1.17it/s]\n\n144it [02:03,  1.18it/s]\n\n145it [02:04,  1.19it/s]\n\n146it [02:05,  1.19it/s]\n\n147it [02:06,  1.19it/s]\n\n148it [02:07,  1.19it/s]\n\n149it [02:07,  1.20it/s]\n\n150it [02:08,  1.20it/s]\niter: 150, loss: 1.42148, losses: 0.723862, 0.697613\n\n150it [02:09,  1.20it/s]\n\n151it [02:09,  1.14it/s]\n\n152it [02:10,  1.16it/s]\n\n153it [02:11,  1.17it/s]\n\n154it [02:12,  1.18it/s]\n\n155it [02:12,  1.19it/s]\n\n156it [02:13,  1.19it/s]\n\n157it [02:14,  1.19it/s]\n\n158it [02:15,  1.20it/s]\n\n159it [02:16,  1.20it/s]\n\n160it [02:17,  1.20it/s]\niter: 160, loss: 1.48197, losses: 0.751354, 0.730616\n\n160it [02:17,  1.20it/s]\n\n161it [02:18,  1.14it/s]\n\n162it [02:18,  1.16it/s]\n\n163it [02:19,  1.17it/s]\n\n164it [02:20,  1.18it/s]\n\n165it [02:21,  1.19it/s]\n\n166it [02:22,  1.19it/s]\n\n167it [02:23,  1.19it/s]\n\n168it [02:23,  1.20it/s]\n\n169it [02:24,  1.20it/s]\n\n170it [02:25,  1.20it/s]\niter: 170, loss: 1.4567, losses: 0.741225, 0.715471\n\n170it [02:26,  1.20it/s]\n\n171it [02:26,  1.14it/s]\n\n172it [02:27,  1.16it/s]\n\n173it [02:28,  1.18it/s]\n\n174it [02:29,  1.19it/s]\n\n175it [02:29,  1.19it/s]\n\n176it [02:30,  1.19it/s]\n\n177it [02:31,  1.20it/s]\n\n178it [02:32,  1.20it/s]\n\n179it [02:33,  1.20it/s]\n\n180it [02:34,  1.20it/s]\niter: 180, loss: 1.45621, losses: 0.739763, 0.716449\n\n180it [02:34,  1.20it/s]\n\n181it [02:35,  1.14it/s]\n\n182it [02:35,  1.16it/s]\n\n183it [02:36,  1.18it/s]\n\n184it [02:37,  1.19it/s]\n\n185it [02:38,  1.19it/s]\n\n186it [02:39,  1.19it/s]\n\n187it [02:39,  1.20it/s]\n\n188it [02:40,  1.20it/s]\n\n189it [02:41,  1.21it/s]\n\n190it [02:42,  1.21it/s]\niter: 190, loss: 1.47477, losses: 0.744979, 0.729792\n\n190it [02:42,  1.21it/s]\n\n191it [02:43,  1.14it/s]\n\n192it [02:44,  1.16it/s]\n\n193it [02:45,  1.17it/s]\n\n194it [02:45,  1.18it/s]\n\n195it [02:46,  1.19it/s]\n\n196it [02:47,  1.20it/s]\n\n197it [02:48,  1.20it/s]\n\n198it [02:49,  1.20it/s]\n\n199it [02:50,  1.21it/s]\n\n200it [02:50,  1.21it/s]\niter: 200, loss: 1.41969, losses: 0.724852, 0.694841\n\n200it [02:51,  1.21it/s]\n\n201it [02:51,  1.15it/s]\n\n202it [02:52,  1.17it/s]\n\n203it [02:53,  1.18it/s]\n\n204it [02:54,  1.19it/s]\n\n205it [02:55,  1.19it/s]\n\n206it [02:55,  1.20it/s]\n\n207it [02:56,  1.20it/s]\n\n208it [02:57,  1.20it/s]\n\n209it [02:58,  1.20it/s]\n\n210it [02:59,  1.21it/s]\niter: 210, loss: 1.46267, losses: 0.742046, 0.720624\n\n210it [02:59,  1.21it/s]\n\n211it [03:00,  1.14it/s]\n\n212it [03:01,  1.17it/s]\n\n213it [03:01,  1.18it/s]\n\n214it [03:02,  1.19it/s]\n\n215it [03:03,  1.20it/s]\n\n216it [03:04,  1.20it/s]\n\n217it [03:05,  1.21it/s]\n\n218it [03:06,  1.21it/s]\n\n219it [03:06,  1.21it/s]\n\n220it [03:07,  1.21it/s]\niter: 220, loss: 1.44763, losses: 0.733925, 0.713701\n\n220it [03:08,  1.21it/s]\n\n221it [03:08,  1.15it/s]\n\n222it [03:09,  1.17it/s]\n\n223it [03:10,  1.18it/s]\n\n224it [03:11,  1.19it/s]\n\n225it [03:11,  1.19it/s]\n\n226it [03:12,  1.20it/s]\n\n227it [03:13,  1.20it/s]\n\n228it [03:14,  1.20it/s]\n\n229it [03:15,  1.20it/s]\n\n230it [03:16,  1.21it/s]\niter: 230, loss: 1.45722, losses: 0.740597, 0.71662\n\n230it [03:16,  1.21it/s]\n\n231it [03:17,  1.14it/s]\n\n232it [03:17,  1.16it/s]\n\n233it [03:18,  1.18it/s]\n\n234it [03:19,  1.19it/s]\n\n235it [03:20,  1.20it/s]\n\n236it [03:21,  1.20it/s]\n\n237it [03:22,  1.20it/s]\n\n238it [03:22,  1.20it/s]\n\n239it [03:23,  1.20it/s]\n\n240it [03:24,  1.21it/s]\niter: 240, loss: 1.46076, losses: 0.737396, 0.723366\n\n240it [03:25,  1.21it/s]\n\n241it [03:25,  1.15it/s]\n\n242it [03:26,  1.16it/s]\n\n243it [03:27,  1.18it/s]\n\n244it [03:27,  1.19it/s]\n\n245it [03:28,  1.20it/s]\n\n246it [03:29,  1.20it/s]\n\n247it [03:30,  1.20it/s]\n\n248it [03:31,  1.20it/s]\n\n249it [03:32,  1.21it/s]\n\n250it [03:32,  1.20it/s]\niter: 250, loss: 1.46064, losses: 0.741409, 0.719233\n\n250it [03:33,  1.20it/s]\n\n251it [03:33,  1.14it/s]\n\n252it [03:34,  1.16it/s]\n\n253it [03:35,  1.17it/s]\n\n254it [03:36,  1.18it/s]\n\n255it [03:37,  1.19it/s]\n\n256it [03:38,  1.19it/s]\n\n257it [03:38,  1.19it/s]\n\n258it [03:39,  1.20it/s]\n\n259it [03:40,  1.20it/s]\n\n260it [03:41,  1.20it/s]\niter: 260, loss: 1.45437, losses: 0.734091, 0.720275\n\n260it [03:41,  1.20it/s]\n\n261it [03:42,  1.14it/s]\n\n262it [03:43,  1.16it/s]\n\n263it [03:44,  1.17it/s]\n\n264it [03:44,  1.18it/s]\n\n265it [03:45,  1.19it/s]\n\n266it [03:46,  1.20it/s]\n\n267it [03:47,  1.20it/s]\n\n268it [03:48,  1.20it/s]\n\n269it [03:48,  1.21it/s]\n\n270it [03:49,  1.20it/s]\niter: 270, loss: 1.4758, losses: 0.74596, 0.729841\n\n270it [03:50,  1.20it/s]\n\n271it [03:50,  1.14it/s]\n\n272it [03:51,  1.16it/s]\n\n273it [03:52,  1.17it/s]\n\n274it [03:53,  1.18it/s]\n\n275it [03:54,  1.19it/s]\n\n276it [03:54,  1.19it/s]\n\n277it [03:55,  1.20it/s]\n\n278it [03:56,  1.20it/s]\n\n279it [03:57,  1.20it/s]\n\n280it [03:58,  1.20it/s]\niter: 280, loss: 1.46246, losses: 0.742268, 0.720194\n\n280it [03:58,  1.20it/s]\n\n281it [03:59,  1.14it/s]\n\n282it [04:00,  1.16it/s]\n\n283it [04:00,  1.17it/s]\n\n284it [04:01,  1.19it/s]\n\n285it [04:02,  1.19it/s]\n\n286it [04:03,  1.19it/s]\n\n287it [04:04,  1.20it/s]\n\n288it [04:05,  1.20it/s]\n\n289it [04:05,  1.20it/s]\n\n290it [04:06,  1.20it/s]\niter: 290, loss: 1.45674, losses: 0.736173, 0.720568\n\n290it [04:07,  1.20it/s]\n\n291it [04:07,  1.14it/s]\n\n292it [04:08,  1.16it/s]\n\n293it [04:09,  1.18it/s]\n\n294it [04:10,  1.19it/s]\n\n295it [04:11,  1.19it/s]\n\n296it [04:11,  1.20it/s]\n\n297it [04:12,  1.20it/s]\n\n298it [04:13,  1.21it/s]\n\n299it [04:14,  1.21it/s]\n\n300it [04:15,  1.20it/s]\niter: 300, loss: 1.46753, losses: 0.742301, 0.725231\n\n300it [04:15,  1.20it/s]\n\n301it [04:16,  1.14it/s]\n\n302it [04:16,  1.16it/s]\n\n303it [04:17,  1.17it/s]\n\n304it [04:18,  1.18it/s]\n\n305it [04:19,  1.19it/s]\n\n306it [04:20,  1.19it/s]\n\n307it [04:21,  1.20it/s]\n\n308it [04:21,  1.20it/s]\n\n309it [04:22,  1.20it/s]\n\n310it [04:23,  1.21it/s]\niter: 310, loss: 1.44706, losses: 0.731625, 0.71544\n\n310it [04:24,  1.21it/s]\n\n311it [04:24,  1.15it/s]\n\n312it [04:25,  1.16it/s]\n\n313it [04:26,  1.18it/s]\n\n314it [04:27,  1.19it/s]\n\n315it [04:27,  1.19it/s]\n\n316it [04:28,  1.20it/s]\n\n317it [04:29,  1.20it/s]\n\n318it [04:30,  1.20it/s]\n\n319it [04:31,  1.20it/s]\n\n320it [04:32,  1.20it/s]\niter: 320, loss: 1.45095, losses: 0.732868, 0.718083\n\n320it [04:32,  1.20it/s]\n\n321it [04:32,  1.14it/s]\n\n322it [04:33,  1.16it/s]\n\n323it [04:34,  1.17it/s]\n\n324it [04:35,  1.18it/s]\n\n325it [04:36,  1.19it/s]\n\n326it [04:37,  1.20it/s]\n\n327it [04:37,  1.20it/s]\n\n328it [04:38,  1.20it/s]\n\n329it [04:39,  1.20it/s]\n\n330it [04:40,  1.20it/s]\niter: 330, loss: 1.45507, losses: 0.737884, 0.717185\n\n330it [04:40,  1.20it/s]\n\n331it [04:41,  1.14it/s]\n\n332it [04:42,  1.16it/s]\n\n333it [04:43,  1.18it/s]\n\n334it [04:43,  1.19it/s]\n\n335it [04:44,  1.20it/s]\n\n336it [04:45,  1.19it/s]\n\n337it [04:46,  1.20it/s]\n\n338it [04:47,  1.20it/s]\n\n339it [04:48,  1.20it/s]\n\n340it [04:48,  1.21it/s]\niter: 340, loss: 1.43972, losses: 0.732735, 0.706989\n\n340it [04:49,  1.21it/s]\n\n341it [04:49,  1.14it/s]\n\n342it [04:50,  1.16it/s]\n\n343it [04:51,  1.17it/s]\n\n344it [04:52,  1.19it/s]\n\n345it [04:53,  1.19it/s]\n\n346it [04:54,  1.20it/s]\n\n347it [04:54,  1.20it/s]\n\n348it [04:55,  1.20it/s]\n\n349it [04:56,  1.20it/s]\n\n350it [04:57,  1.20it/s]\niter: 350, loss: 1.457, losses: 0.736383, 0.720621\n\n350it [04:57,  1.20it/s]\n\n350it [04:58,  1.17it/s]",
  "metrics": {},
  "output": [
    {
      "file": "https://replicate.delivery/mgxm/66cef0b3-613d-44ce-aed7-7d4722261240/out.png"
    }
  ],
  "started_at": null,
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/nkyhl3jfpfaprjblubnsexssoq",
    "cancel": "https://api.replicate.com/v1/predictions/nkyhl3jfpfaprjblubnsexssoq/cancel"
  },
  "version": "3fab04f1fa2bab29b6b22bbeee2ba5f8cf12eea543482dd28358355bcb459f11"
}