cmenguy/toshiro-ai-1_5 🔢🖼️❓📝✓ → 🖼️

▶️ 111 runs 📅 Apr 2023 ⚙️ Cog 0.6.0

About

A stable diffusion model trained on pictures from my buddy Toshiro (truly the best boy there is)

Example Output

Prompt:

"Adorably cute qdg dog portrait, artstation winner by Victo Ngai, Kilian Eng and by Jake Parker, vibrant colors, winning-award masterpiece, fantastically gaudy, aesthetic octane render, 8K HD Resolution"

Output

Performance Metrics

15.30s Prediction Time

210.08s Total Time

All Input Parameters

{
  "width": 512,
  "height": 512,
  "prompt": "Adorably cute qdg dog portrait, artstation winner by Victo Ngai, Kilian Eng and by Jake Parker, vibrant colors, winning-award masterpiece, fantastically gaudy, aesthetic octane render, 8K HD Resolution",
  "scheduler": "DDIM",
  "num_outputs": 1,
  "guidance_scale": 7.5,
  "negative_prompt": "cartoon, blurry, deformed, watermark, dark lighting, image caption, caption, text, cropped, low quality, low resolution, malformed, messy, blurry, watermark",
  "prompt_strength": 0.8,
  "num_inference_steps": 50
}

Input Parameters

seed Type: integer: Random seed. Leave blank to randomize the seed
image Type: string: A starting image from which to generate variations (aka 'img2img'). If this input is set, the `width` and `height` inputs are ignored and the output will have the same dimensions as the input image.
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: a photo of a qdg dog: Input prompt
scheduler Default: DDIM: Choose a scheduler
num_outputs Type: integerDefault: 1Range: 1 - 4: Number of images to output.
guidance_scale Type: numberDefault: 7.5Range: 1 - 20: Scale for classifier-free guidance
negative_prompt Type: string: Specify things to not see in the output
prompt_strength Type: numberDefault: 0.8: Prompt strength when using init image. 1.0 corresponds to full destruction of information in init image
num_inference_steps Type: integerDefault: 50Range: 1 - 500: Number of denoising steps
disable_safety_check Type: booleanDefault: false: Disable safety check. Use at your own risk!

Output Schema

Output

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

Example Execution Logs

Using seed: 62756
using txt2img
  0%|          | 0/50 [00:00<?, ?it/s]
  2%|▏         | 1/50 [00:03<02:40,  3.28s/it]
  4%|▍         | 2/50 [00:03<01:09,  1.45s/it]
  6%|▌         | 3/50 [00:03<00:40,  1.15it/s]
  8%|▊         | 4/50 [00:03<00:27,  1.67it/s]
 10%|█         | 5/50 [00:03<00:20,  2.24it/s]
 12%|█▏        | 6/50 [00:04<00:15,  2.81it/s]
 14%|█▍        | 7/50 [00:04<00:12,  3.34it/s]
 16%|█▌        | 8/50 [00:04<00:10,  3.84it/s]
 18%|█▊        | 9/50 [00:04<00:09,  4.26it/s]
 20%|██        | 10/50 [00:04<00:08,  4.59it/s]
 22%|██▏       | 11/50 [00:05<00:08,  4.87it/s]
 24%|██▍       | 12/50 [00:05<00:07,  5.08it/s]
 26%|██▌       | 13/50 [00:05<00:07,  5.22it/s]
 28%|██▊       | 14/50 [00:05<00:06,  5.35it/s]
 30%|███       | 15/50 [00:05<00:06,  5.41it/s]
 32%|███▏      | 16/50 [00:05<00:06,  5.46it/s]
 34%|███▍      | 17/50 [00:06<00:05,  5.50it/s]
 36%|███▌      | 18/50 [00:06<00:05,  5.53it/s]
 38%|███▊      | 19/50 [00:06<00:05,  5.57it/s]
 40%|████      | 20/50 [00:06<00:05,  5.59it/s]
 42%|████▏     | 21/50 [00:06<00:05,  5.58it/s]
 44%|████▍     | 22/50 [00:07<00:05,  5.57it/s]
 46%|████▌     | 23/50 [00:07<00:04,  5.55it/s]
 48%|████▊     | 24/50 [00:07<00:04,  5.54it/s]
 50%|█████     | 25/50 [00:07<00:04,  5.55it/s]
 52%|█████▏    | 26/50 [00:07<00:04,  5.59it/s]
 54%|█████▍    | 27/50 [00:07<00:04,  5.59it/s]
 56%|█████▌    | 28/50 [00:08<00:03,  5.58it/s]
 58%|█████▊    | 29/50 [00:08<00:03,  5.56it/s]
 60%|██████    | 30/50 [00:08<00:03,  5.54it/s]
 62%|██████▏   | 31/50 [00:08<00:03,  5.53it/s]
 64%|██████▍   | 32/50 [00:08<00:03,  5.53it/s]
 66%|██████▌   | 33/50 [00:09<00:03,  5.54it/s]
 68%|██████▊   | 34/50 [00:09<00:02,  5.54it/s]
 70%|███████   | 35/50 [00:09<00:02,  5.53it/s]
 72%|███████▏  | 36/50 [00:09<00:02,  5.53it/s]
 74%|███████▍  | 37/50 [00:09<00:02,  5.56it/s]
 76%|███████▌  | 38/50 [00:09<00:02,  5.59it/s]
 78%|███████▊  | 39/50 [00:10<00:01,  5.57it/s]
 80%|████████  | 40/50 [00:10<00:01,  5.58it/s]
 82%|████████▏ | 41/50 [00:10<00:01,  5.57it/s]
 84%|████████▍ | 42/50 [00:10<00:01,  5.55it/s]
 86%|████████▌ | 43/50 [00:10<00:01,  5.54it/s]
 88%|████████▊ | 44/50 [00:10<00:01,  5.55it/s]
 90%|█████████ | 45/50 [00:11<00:00,  5.57it/s]
 92%|█████████▏| 46/50 [00:11<00:00,  5.59it/s]
 94%|█████████▍| 47/50 [00:11<00:00,  5.60it/s]
 96%|█████████▌| 48/50 [00:11<00:00,  5.57it/s]
 98%|█████████▊| 49/50 [00:11<00:00,  5.56it/s]
100%|██████████| 50/50 [00:12<00:00,  5.57it/s]
100%|██████████| 50/50 [00:12<00:00,  4.14it/s]

Version Details

Version ID: e340e1f267472e33be6075e4926403494eb749fdd0da283fc70f659f4f61b2c8
Version Created: April 18, 2023

Run on Replicate →