jyoung105/playground-v2.5 🔢📝 → 🖼️

▶️ 58.9K runs 📅 Feb 2024 ⚙️ Cog 0.13.2 🔗 GitHub
text-to-image

About

Playground v2.5: Three Insights towards Enhancing Aesthetic Quality in Text-to-Image Generation

Example Output

Prompt:

"A man with hoodie on, illustration"

Output

Example output

Performance Metrics

8.87s Prediction Time
178.17s Total Time
All Input Parameters 
{
  "eta": 0,
  "steps": 25,
  "width": 1024,
  "height": 1024,
  "prompt": "A man with hoodie on, illustration",
  "clip_skip": 0,
  "num_images": 1,
  "guidance_scale": 3
}
Input Parameters
eta Type: numberDefault: 0Range: 0 - 1
Stochastic parameter to control the randomness.
seed Type: integer
Random seed. Leave blank to randomize the seed.
steps Type: integerDefault: 25Range: 1 - 50
Number of denoising steps.
width Type: integerDefault: 1024Range: 1 - 2048
Width of the output image.
height Type: integerDefault: 1024Range: 1 - 2048
Height of the output image.
prompt Type: string
Input prompt, text of what you want to generate.
clip_skip Type: integerDefault: 0
Number of the layers to skip in CLIP.
num_images Type: integerDefault: 1Range: 1 - 4
Number of output images.
guidance_scale Type: numberDefault: 3Range: 0 - 20
Scale for classifier-free guidance.
negative_prompt Type: string
Input negative prompt, text of what you don't want to generate.
Output Schema

Output

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

Example Execution Logs 
[Debug] DEVICE: cuda
[Debug] DTYPE: torch.float16
Setup completed in 0.00 seconds.
[~] Generating images...
[Debug] Prompt: A man with hoodie on, illustration, best quality, high detail, sharp focus
[Debug] Seed: 53071
  0%|          | 0/25 [00:00<?, ?it/s]
  4%|▍         | 1/25 [00:01<00:31,  1.30s/it]
 12%|█▏        | 3/25 [00:01<00:09,  2.29it/s]
 16%|█▌        | 4/25 [00:01<00:07,  2.84it/s]
 20%|██        | 5/25 [00:01<00:05,  3.35it/s]
 24%|██▍       | 6/25 [00:02<00:05,  3.79it/s]
 28%|██▊       | 7/25 [00:02<00:04,  4.12it/s]
 32%|███▏      | 8/25 [00:02<00:03,  4.41it/s]
 36%|███▌      | 9/25 [00:02<00:03,  4.63it/s]
 40%|████      | 10/25 [00:02<00:03,  4.80it/s]
 44%|████▍     | 11/25 [00:03<00:02,  4.92it/s]
 48%|████▊     | 12/25 [00:03<00:02,  4.98it/s]
 52%|█████▏    | 13/25 [00:03<00:02,  5.05it/s]
 56%|█████▌    | 14/25 [00:03<00:02,  5.09it/s]
 60%|██████    | 15/25 [00:03<00:01,  5.13it/s]
 64%|██████▍   | 16/25 [00:04<00:01,  5.15it/s]
 68%|██████▊   | 17/25 [00:04<00:01,  5.16it/s]
 72%|███████▏  | 18/25 [00:04<00:01,  5.17it/s]
 76%|███████▌  | 19/25 [00:04<00:01,  5.18it/s]
 80%|████████  | 20/25 [00:04<00:00,  5.18it/s]
 84%|████████▍ | 21/25 [00:05<00:00,  5.19it/s]
 88%|████████▊ | 22/25 [00:05<00:00,  5.18it/s]
 92%|█████████▏| 23/25 [00:05<00:00,  5.18it/s]
 96%|█████████▌| 24/25 [00:05<00:00,  5.18it/s]
100%|██████████| 25/25 [00:05<00:00,  5.19it/s]
100%|██████████| 25/25 [00:05<00:00,  4.31it/s]
Image generation completed in 7.10 seconds.
Version Details
Version ID
1f56546a4d802097aa5e153c89e566772a9b2de3ff177d3711f5aaf14e32a39f
Version Created
November 22, 2024
Run on Replicate →