anotherjesse/sd15-consistency-decoder-vae 🔢❓📝✓ → 🖼️

▶️ 3.0K runs 📅 Nov 2023 ⚙️ Cog v0.8.1+dev 🔗 GitHub ⚖️ License
consistency-decoder stable-diffusion-1-5 text-to-image

About

SD1.5 and OpenAI's Consistency Decoder

Example Output

Prompt:

"a illustration of an bunny on a rainbow"

Output

Example outputExample outputExample outputExample output

Performance Metrics

14.21s Prediction Time
14.16s Total Time
All Input Parameters 
{
  "seed": 0,
  "width": 512,
  "height": 512,
  "prompt": "a illustration of an bunny on a rainbow",
  "scheduler": "DPMSolverMultistep",
  "num_outputs": 4,
  "guidance_scale": 7.5,
  "consistency_decoder": true,
  "num_inference_steps": 50
}
Input Parameters
seed Type: integer
Random seed. Leave blank to randomize the seed
width Default: 768
Width of output image. Maximum size is 1024x768 or 768x1024 because of memory limits
height Default: 768
Height of output image. Maximum size is 1024x768 or 768x1024 because of memory limits
prompt Type: stringDefault: a photo of an astronaut riding a horse on mars
Input prompt
scheduler Default: DPMSolverMultistep
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
consistency_decoder Type: booleanDefault: true
Enable consistency decoder
num_inference_steps Type: integerDefault: 50Range: 1 - 500
Number of denoising steps
Output Schema

Output

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

Example Execution Logs 
Using seed: 0
  0%|          | 0/50 [00:00<?, ?it/s]
  2%|▏         | 1/50 [00:00<00:06,  8.00it/s]
  6%|▌         | 3/50 [00:00<00:04, 10.92it/s]
 10%|█         | 5/50 [00:00<00:04,  9.15it/s]
 12%|█▏        | 6/50 [00:00<00:04,  8.80it/s]
 14%|█▍        | 7/50 [00:00<00:05,  8.53it/s]
 16%|█▌        | 8/50 [00:00<00:05,  8.35it/s]
 18%|█▊        | 9/50 [00:01<00:04,  8.22it/s]
 20%|██        | 10/50 [00:01<00:04,  8.14it/s]
 22%|██▏       | 11/50 [00:01<00:04,  8.10it/s]
 24%|██▍       | 12/50 [00:01<00:04,  8.06it/s]
 26%|██▌       | 13/50 [00:01<00:04,  8.03it/s]
 28%|██▊       | 14/50 [00:01<00:04,  8.01it/s]
 30%|███       | 15/50 [00:01<00:04,  8.00it/s]
 32%|███▏      | 16/50 [00:01<00:04,  7.99it/s]
 34%|███▍      | 17/50 [00:02<00:04,  7.99it/s]
 36%|███▌      | 18/50 [00:02<00:04,  7.98it/s]
 38%|███▊      | 19/50 [00:02<00:03,  7.98it/s]
 40%|████      | 20/50 [00:02<00:03,  7.98it/s]
 42%|████▏     | 21/50 [00:02<00:03,  7.96it/s]
 44%|████▍     | 22/50 [00:02<00:03,  7.97it/s]
 46%|████▌     | 23/50 [00:02<00:03,  7.97it/s]
 48%|████▊     | 24/50 [00:02<00:03,  7.96it/s]
 50%|█████     | 25/50 [00:03<00:03,  7.96it/s]
 52%|█████▏    | 26/50 [00:03<00:03,  7.96it/s]
 54%|█████▍    | 27/50 [00:03<00:02,  7.96it/s]
 56%|█████▌    | 28/50 [00:03<00:02,  7.96it/s]
 58%|█████▊    | 29/50 [00:03<00:02,  7.96it/s]
 60%|██████    | 30/50 [00:03<00:02,  7.97it/s]
 62%|██████▏   | 31/50 [00:03<00:02,  7.96it/s]
 64%|██████▍   | 32/50 [00:03<00:02,  7.96it/s]
 66%|██████▌   | 33/50 [00:04<00:02,  7.97it/s]
 68%|██████▊   | 34/50 [00:04<00:02,  7.96it/s]
 70%|███████   | 35/50 [00:04<00:01,  7.96it/s]
 72%|███████▏  | 36/50 [00:04<00:01,  7.96it/s]
 74%|███████▍  | 37/50 [00:04<00:01,  7.97it/s]
 76%|███████▌  | 38/50 [00:04<00:01,  7.95it/s]
 78%|███████▊  | 39/50 [00:04<00:01,  7.95it/s]
 80%|████████  | 40/50 [00:04<00:01,  7.95it/s]
 82%|████████▏ | 41/50 [00:05<00:01,  7.96it/s]
 84%|████████▍ | 42/50 [00:05<00:01,  7.96it/s]
 86%|████████▌ | 43/50 [00:05<00:00,  7.95it/s]
 88%|████████▊ | 44/50 [00:05<00:00,  7.95it/s]
 90%|█████████ | 45/50 [00:05<00:00,  7.95it/s]
 92%|█████████▏| 46/50 [00:05<00:00,  7.95it/s]
 94%|█████████▍| 47/50 [00:05<00:00,  7.95it/s]
 96%|█████████▌| 48/50 [00:05<00:00,  7.95it/s]
 98%|█████████▊| 49/50 [00:06<00:00,  7.95it/s]
100%|██████████| 50/50 [00:06<00:00,  7.95it/s]
100%|██████████| 50/50 [00:06<00:00,  8.07it/s]
Inference took 6.20884895324707 seconds
Running consistency decoder...
Consistency decoder took 0.803274393081665 seconds
Running consistency decoder...
Consistency decoder took 0.7121260166168213 seconds
Running consistency decoder...
Consistency decoder took 0.7130522727966309 seconds
Running consistency decoder...
Consistency decoder took 0.7134041786193848 seconds
Version Details
Version ID
7a5d96bdd41ffe8c449f6c6818a9aaa31db3fb4d7d7154feef3fd778318c64a3
Version Created
November 6, 2023
Run on Replicate →