cjwbw/anything-v3-better-vae 🔢❓📝 → 🖼️

▶️ 3.5M runs 📅 Jan 2023 ⚙️ Cog 0.6.1

About

high-quality, highly detailed anime style stable-diffusion with better VAE

Example Output

Prompt:

"masterpiece, best quality, illustration, beautiful detailed, finely detailed, dramatic light, intricate details, 1girl, brown hair, green eyes, colorful, autumn, cumulonimbus clouds, lighting, blue sky, falling leaves, garden"

Output

Performance Metrics

41.28s Prediction Time

322.51s Total Time

All Input Parameters

{
  "width": 512,
  "height": "640",
  "prompt": "masterpiece, best quality, illustration, beautiful detailed, finely detailed, dramatic light, intricate details, 1girl, brown hair, green eyes, colorful, autumn, cumulonimbus clouds, lighting, blue sky, falling leaves, garden",
  "scheduler": "DPMSolverMultistep",
  "num_outputs": 1,
  "guidance_scale": "12",
  "negative_prompt": "lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name",
  "num_inference_steps": "50"
}

Input Parameters

seed Type: integer: Random seed. Leave blank to randomize the seed
width Default: 512: Width of output image. Maximum size is 1024x768 or 768x1024 because of memory limits
height Default: 512: Height of output image. Maximum size is 1024x768 or 768x1024 because of memory limits
prompt Type: stringDefault: masterpiece, best quality, illustration, beautiful detailed, finely detailed, dramatic light, intricate details, 1girl, brown hair, green eyes, colorful, autumn, cumulonimbus clouds, lighting, blue sky, falling leaves, garden: Input prompt
scheduler Default: DPMSolverMultistep: Choose a scheduler.
num_outputs Default: 1: Number of images to output
guidance_scale Type: numberDefault: 7Range: 1 - 20: Scale for classifier-free guidance
negative_prompt Type: string: The prompt or prompts not to guide the image generation (what you do not want to see in the generation). Ignored when not using guidance.
num_inference_steps Type: integerDefault: 20Range: 1 - 500: Number of denoising steps

Output Schema

Output

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

Example Execution Logs

Using seed: 42642
  0%|          | 0/50 [00:00<?, ?it/s]
  2%|▏         | 1/50 [00:02<02:08,  2.62s/it]
  4%|▍         | 2/50 [00:03<01:10,  1.47s/it]
  6%|▌         | 3/50 [00:03<00:51,  1.10s/it]
  8%|▊         | 4/50 [00:04<00:42,  1.07it/s]
 10%|█         | 5/50 [00:05<00:37,  1.19it/s]
 12%|█▏        | 6/50 [00:05<00:34,  1.28it/s]
 14%|█▍        | 7/50 [00:06<00:32,  1.34it/s]
 16%|█▌        | 8/50 [00:07<00:30,  1.38it/s]
 18%|█▊        | 9/50 [00:07<00:29,  1.41it/s]
 20%|██        | 10/50 [00:08<00:27,  1.43it/s]
 22%|██▏       | 11/50 [00:09<00:27,  1.44it/s]
 24%|██▍       | 12/50 [00:10<00:26,  1.45it/s]
 26%|██▌       | 13/50 [00:10<00:25,  1.46it/s]
 28%|██▊       | 14/50 [00:11<00:24,  1.46it/s]
 30%|███       | 15/50 [00:12<00:23,  1.46it/s]
 32%|███▏      | 16/50 [00:12<00:23,  1.46it/s]
 34%|███▍      | 17/50 [00:13<00:22,  1.46it/s]
 36%|███▌      | 18/50 [00:14<00:21,  1.46it/s]
 38%|███▊      | 19/50 [00:14<00:21,  1.46it/s]
 40%|████      | 20/50 [00:15<00:20,  1.46it/s]
 42%|████▏     | 21/50 [00:16<00:20,  1.45it/s]
 44%|████▍     | 22/50 [00:16<00:19,  1.45it/s]
 46%|████▌     | 23/50 [00:17<00:18,  1.45it/s]
 48%|████▊     | 24/50 [00:18<00:18,  1.44it/s]
 50%|█████     | 25/50 [00:18<00:17,  1.45it/s]
 52%|█████▏    | 26/50 [00:19<00:16,  1.45it/s]
 54%|█████▍    | 27/50 [00:20<00:15,  1.45it/s]
 56%|█████▌    | 28/50 [00:21<00:15,  1.45it/s]
 58%|█████▊    | 29/50 [00:21<00:14,  1.45it/s]
 60%|██████    | 30/50 [00:22<00:13,  1.45it/s]
 62%|██████▏   | 31/50 [00:23<00:13,  1.44it/s]
 64%|██████▍   | 32/50 [00:23<00:12,  1.44it/s]
 66%|██████▌   | 33/50 [00:24<00:11,  1.44it/s]
 68%|██████▊   | 34/50 [00:25<00:11,  1.44it/s]
 70%|███████   | 35/50 [00:25<00:10,  1.43it/s]
 72%|███████▏  | 36/50 [00:26<00:09,  1.43it/s]
 74%|███████▍  | 37/50 [00:27<00:09,  1.43it/s]
 76%|███████▌  | 38/50 [00:28<00:08,  1.42it/s]
 78%|███████▊  | 39/50 [00:28<00:07,  1.43it/s]
 80%|████████  | 40/50 [00:29<00:07,  1.42it/s]
 82%|████████▏ | 41/50 [00:30<00:06,  1.42it/s]
 84%|████████▍ | 42/50 [00:30<00:05,  1.42it/s]
 86%|████████▌ | 43/50 [00:31<00:04,  1.42it/s]
 88%|████████▊ | 44/50 [00:32<00:04,  1.42it/s]
 90%|█████████ | 45/50 [00:32<00:03,  1.42it/s]
 92%|█████████▏| 46/50 [00:33<00:02,  1.42it/s]
 94%|█████████▍| 47/50 [00:34<00:02,  1.42it/s]
 96%|█████████▌| 48/50 [00:35<00:01,  1.42it/s]
 98%|█████████▊| 49/50 [00:35<00:00,  1.42it/s]
100%|██████████| 50/50 [00:36<00:00,  1.41it/s]
100%|██████████| 50/50 [00:36<00:00,  1.37it/s]

Version Details

Version ID: 09a5805203f4c12da649ec1923bb7729517ca25fcac790e640eaa9ed66573b65
Version Created: January 15, 2023

Run on Replicate →