cjwbw/animagine-xl-3.1 🔢📝❓ → 🖼️

▶️ 9.2M runs 📅 Mar 2024 ⚙️ Cog 0.9.4 ⚖️ License

About

Anime-themed text-to-image stable diffusion model

Example Output

Prompt:

"1girl, cagliostro, granblue fantasy, violet eyes, standing, hand on own chin, looking at object, smile, closed mouth, table, beaker, glass tube, experiment apparatus, dark room, laboratory, upper body"

Output

Performance Metrics

7.79s Prediction Time

7.83s Total Time

All Input Parameters

{
  "width": 896,
  "height": 1152,
  "prompt": "1girl, cagliostro, granblue fantasy, violet eyes, standing, hand on own chin, looking at object, smile, closed mouth, table, beaker, glass tube, experiment apparatus, dark room, laboratory, upper body",
  "guidance_scale": 7,
  "style_selector": "(None)",
  "negative_prompt": "nsfw, lowres, (bad), text, error, fewer, extra, missing, worst quality, jpeg artifacts, low quality, watermark, unfinished, displeasing, oldest, early, chromatic aberration, signature, extra digits, artistic error, username, scan, [abstract]",
  "quality_selector": "Standard v3.1",
  "num_inference_steps": 28
}

Input Parameters

seed Type: integer: Random seed. Leave blank to randomize the seed
width Type: integerDefault: 896: Width of output image
height Type: integerDefault: 1152: Height of output image
prompt Type: stringDefault: 1girl, cagliostro, granblue fantasy, violet eyes, standing, hand on own chin, looking at object, smile, closed mouth, table, beaker, glass tube, experiment apparatus, dark room, laboratory, upper body: Input prompt
guidance_scale Type: numberDefault: 7Range: 1 - 20: Scale for classifier-free guidance
style_selector Default: (None): Style Preset
negative_prompt Type: stringDefault: nsfw, lowres, (bad), text, error, fewer, extra, missing, worst quality, jpeg artifacts, low quality, watermark, unfinished, displeasing, oldest, early, chromatic aberration, signature, extra digits, artistic error, username, scan, [abstract]: Specify things to not see in the output
quality_selector Default: Standard v3.1: Quality Tags Presets
num_inference_steps Type: integerDefault: 28Range: 1 - 500: Number of denoising steps

Output Schema

Output

Type: string • Format: uri

Example Execution Logs

Using seed: 54376
  0%|          | 0/28 [00:00<?, ?it/s]
  7%|▋         | 2/28 [00:00<00:03,  7.01it/s]
 11%|█         | 3/28 [00:00<00:04,  6.08it/s]
 14%|█▍        | 4/28 [00:00<00:04,  5.68it/s]
 18%|█▊        | 5/28 [00:00<00:04,  5.47it/s]
 21%|██▏       | 6/28 [00:01<00:04,  5.32it/s]
 25%|██▌       | 7/28 [00:01<00:03,  5.25it/s]
 29%|██▊       | 8/28 [00:01<00:03,  5.20it/s]
 32%|███▏      | 9/28 [00:01<00:03,  5.17it/s]
 36%|███▌      | 10/28 [00:01<00:03,  5.14it/s]
 39%|███▉      | 11/28 [00:02<00:03,  5.11it/s]
 43%|████▎     | 12/28 [00:02<00:03,  5.10it/s]
 46%|████▋     | 13/28 [00:02<00:02,  5.10it/s]
 50%|█████     | 14/28 [00:02<00:02,  5.10it/s]
 54%|█████▎    | 15/28 [00:02<00:02,  5.09it/s]
 57%|█████▋    | 16/28 [00:03<00:02,  5.08it/s]
 61%|██████    | 17/28 [00:03<00:02,  5.07it/s]
 64%|██████▍   | 18/28 [00:03<00:01,  5.07it/s]
 68%|██████▊   | 19/28 [00:03<00:01,  5.08it/s]
 71%|███████▏  | 20/28 [00:03<00:01,  5.08it/s]
 75%|███████▌  | 21/28 [00:04<00:01,  5.07it/s]
 79%|███████▊  | 22/28 [00:04<00:01,  5.07it/s]
 82%|████████▏ | 23/28 [00:04<00:00,  5.07it/s]
 86%|████████▌ | 24/28 [00:04<00:00,  5.07it/s]
 89%|████████▉ | 25/28 [00:04<00:00,  5.07it/s]
 93%|█████████▎| 26/28 [00:05<00:00,  5.06it/s]
 96%|█████████▋| 27/28 [00:05<00:00,  5.06it/s]
100%|██████████| 28/28 [00:05<00:00,  5.07it/s]
100%|██████████| 28/28 [00:05<00:00,  5.18it/s]

Version Details

Version ID: 6afe2e6b27dad2d6f480b59195c221884b6acc589ff4d05ff0e5fc058690fbb9
Version Created: March 20, 2024

Run on Replicate →