chigozienri/visual-anagrams 🔢📝✓ → 🖼️

▶️ 1.5K runs 📅 Dec 2023 ⚙️ Cog 0.8.6 🔗 GitHub 📄 Paper ⚖️ License

optical-illusion text-to-image

Performance

14.5sTypical run time

~40sCold start (first call)

1.5KTotal runs

About

Generates multi-view optical illusions

Example Output

Output

Performance Metrics

14.48s Prediction Time

40.45s Total Time

All Input Parameters

{
  "seed": 0,
  "style": "an oil painting of ",
  "video": true,
  "views": "identity, jigsaw",
  "prompts": "a rabbit, a coffee cup",
  "noise_level": 50,
  "num_samples": 1,
  "guidance_scale_1": 10,
  "guidance_scale_2": 10,
  "num_inference_steps_1": 30,
  "num_inference_steps_2": 30
}

Input Parameters

seed Type: integerDefault: null: Leave empty for a random seed
style Type: stringDefault:: Prompt prefix of the visual style, e.g. 'an oil painting of'. Looser styles work better.
video Type: booleanDefault: true
views Type: stringDefault: identity, jigsaw: Comma-separated list of views. Must be same length as prompts. First view should usually be 'identity'. Available Views: 'identity', 'flip', 'rotate_cw', 'rotate_ccw', 'rotate_180', 'negate', 'skew', 'patch_permute', 'pixel_permute', 'jigsaw', 'inner_circle'
prompts Type: stringDefault: a rabbit, a coffee cup: Comma-separated list of prompts
num_samples Type: integerDefault: 1
guidance_scale_1 Type: numberDefault: 10
guidance_scale_2 Type: numberDefault: 10
num_inference_steps_1 Type: integerDefault: 30
num_inference_steps_2 Type: integerDefault: 30

Output Schema

Output

Type: array • Items Type: string • Items Format: uri

Example Execution Logs

0%|          | 0/30 [00:00<?, ?it/s]
  3%|▎         | 1/30 [00:00<00:22,  1.28it/s]
 13%|█▎        | 4/30 [00:00<00:04,  5.67it/s]
 23%|██▎       | 7/30 [00:00<00:02,  9.94it/s]
 33%|███▎      | 10/30 [00:01<00:01, 13.79it/s]
 43%|████▎     | 13/30 [00:01<00:00, 17.13it/s]
 53%|█████▎    | 16/30 [00:01<00:00, 19.95it/s]
 63%|██████▎   | 19/30 [00:01<00:00, 22.06it/s]
 73%|███████▎  | 22/30 [00:01<00:00, 23.68it/s]
 83%|████████▎ | 25/30 [00:01<00:00, 25.04it/s]
 93%|█████████▎| 28/30 [00:01<00:00, 25.83it/s]
100%|██████████| 30/30 [00:01<00:00, 16.58it/s]
  0%|          | 0/30 [00:00<?, ?it/s]
  3%|▎         | 1/30 [00:00<00:05,  5.44it/s]
  7%|▋         | 2/30 [00:00<00:04,  6.08it/s]
 10%|█         | 3/30 [00:00<00:04,  6.31it/s]
 13%|█▎        | 4/30 [00:00<00:04,  6.44it/s]
 17%|█▋        | 5/30 [00:00<00:03,  6.52it/s]
 20%|██        | 6/30 [00:00<00:03,  6.56it/s]
 23%|██▎       | 7/30 [00:01<00:03,  6.58it/s]
 27%|██▋       | 8/30 [00:01<00:03,  6.58it/s]
 30%|███       | 9/30 [00:01<00:03,  6.58it/s]
 33%|███▎      | 10/30 [00:01<00:03,  6.58it/s]
 37%|███▋      | 11/30 [00:01<00:02,  6.59it/s]
 40%|████      | 12/30 [00:01<00:02,  6.61it/s]
 43%|████▎     | 13/30 [00:01<00:02,  6.61it/s]
 47%|████▋     | 14/30 [00:02<00:02,  6.62it/s]
 50%|█████     | 15/30 [00:02<00:02,  6.62it/s]
 53%|█████▎    | 16/30 [00:02<00:02,  6.62it/s]
 57%|█████▋    | 17/30 [00:02<00:01,  6.62it/s]
 60%|██████    | 18/30 [00:02<00:01,  6.63it/s]
 63%|██████▎   | 19/30 [00:02<00:01,  6.63it/s]
 67%|██████▋   | 20/30 [00:03<00:01,  6.63it/s]
 70%|███████   | 21/30 [00:03<00:01,  6.61it/s]
 73%|███████▎  | 22/30 [00:03<00:01,  6.60it/s]
 77%|███████▋  | 23/30 [00:03<00:01,  6.58it/s]
 80%|████████  | 24/30 [00:03<00:00,  6.59it/s]
 83%|████████▎ | 25/30 [00:03<00:00,  6.61it/s]
 87%|████████▋ | 26/30 [00:03<00:00,  6.61it/s]
 90%|█████████ | 27/30 [00:04<00:00,  6.62it/s]
 93%|█████████▎| 28/30 [00:04<00:00,  6.61it/s]
 97%|█████████▋| 29/30 [00:04<00:00,  6.61it/s]
100%|██████████| 30/30 [00:04<00:00,  6.72it/s]
100%|██████████| 30/30 [00:04<00:00,  6.58it/s]
['sample_256.png', 'sample_256.views.png']
  0%|          | 0/45 [00:00<?, ?it/s]
  4%|▍         | 2/45 [00:00<00:03, 12.93it/s]
  9%|▉         | 4/45 [00:00<00:03, 12.98it/s]
 13%|█▎        | 6/45 [00:00<00:03, 12.93it/s]
 18%|█▊        | 8/45 [00:00<00:02, 12.80it/s]
 22%|██▏       | 10/45 [00:00<00:02, 12.85it/s]
 27%|██▋       | 12/45 [00:00<00:02, 12.87it/s]
 31%|███       | 14/45 [00:01<00:02, 12.79it/s]
 36%|███▌      | 16/45 [00:01<00:02, 12.79it/s]
 40%|████      | 18/45 [00:01<00:02, 12.74it/s]
 44%|████▍     | 20/45 [00:01<00:01, 12.65it/s]
 49%|████▉     | 22/45 [00:01<00:01, 12.51it/s]
 53%|█████▎    | 24/45 [00:01<00:01, 12.37it/s]
 58%|█████▊    | 26/45 [00:02<00:01, 12.31it/s]
 62%|██████▏   | 28/45 [00:02<00:01, 12.34it/s]
 67%|██████▋   | 30/45 [00:02<00:01, 12.46it/s]
 71%|███████   | 32/45 [00:02<00:01, 12.56it/s]
 76%|███████▌  | 34/45 [00:02<00:00, 12.65it/s]
 80%|████████  | 36/45 [00:02<00:00, 12.74it/s]
 84%|████████▍ | 38/45 [00:02<00:00, 12.80it/s]
 89%|████████▉ | 40/45 [00:03<00:00, 12.82it/s]
 93%|█████████▎| 42/45 [00:03<00:00, 12.85it/s]
 98%|█████████▊| 44/45 [00:03<00:00, 12.87it/s]
100%|██████████| 45/45 [00:03<00:00, 12.71it/s]
Making video...

Version Details

Version ID: a7131633ac3dcf60b18db27ded1ed4545533adf99305f2f3a5a4d252dc85d4d4
Version Created: December 4, 2023

Run on Replicate →