cjwbw/analog-diffusion 🔢❓📝 → 🖼️

▶️ 234.6K runs 📅 Dec 2022 ⚙️ Cog 0.6.1
analog-film analog-style nsfw text-to-image vintage-photography

About

a dreambooth model trained on a diverse set of analog photographs

Example Output

Prompt:

"analog style closeup portrait of cowboy George Washington"

Output

Example output

Performance Metrics

31.11s Prediction Time
151.02s Total Time
All Input Parameters
{
  "width": 512,
  "height": 512,
  "prompt": "analog style closeup portrait of cowboy George Washington",
  "scheduler": "K_EULER_ANCESTRAL",
  "num_outputs": 1,
  "guidance_scale": 7,
  "negative_prompt": "blur haze",
  "num_inference_steps": 20
}
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: analog style closeup portrait of cowboy George Washington
Input prompt
scheduler Default: K_EULER_ANCESTRAL
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: stringDefault: blur haze
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: arrayItems Type: stringItems Format: uri

Example Execution Logs
Using seed: 52975
  0%|          | 0/20 [00:00<?, ?it/s]
  5%|▌         | 1/20 [00:03<00:57,  3.02s/it]
 10%|█         | 2/20 [00:03<00:27,  1.52s/it]
 15%|█▌        | 3/20 [00:03<00:17,  1.05s/it]
 20%|██        | 4/20 [00:04<00:13,  1.21it/s]
 25%|██▌       | 5/20 [00:04<00:10,  1.43it/s]
 30%|███       | 6/20 [00:05<00:08,  1.59it/s]
 35%|███▌      | 7/20 [00:05<00:07,  1.72it/s]
 40%|████      | 8/20 [00:06<00:06,  1.81it/s]
 45%|████▌     | 9/20 [00:06<00:05,  1.88it/s]
 50%|█████     | 10/20 [00:07<00:05,  1.93it/s]
 55%|█████▌    | 11/20 [00:07<00:04,  1.97it/s]
 60%|██████    | 12/20 [00:08<00:04,  1.99it/s]
 65%|██████▌   | 13/20 [00:08<00:03,  2.01it/s]
 70%|███████   | 14/20 [00:09<00:02,  2.02it/s]
 75%|███████▌  | 15/20 [00:09<00:02,  2.03it/s]
 80%|████████  | 16/20 [00:10<00:01,  2.03it/s]
 85%|████████▌ | 17/20 [00:10<00:01,  2.04it/s]
 90%|█████████ | 18/20 [00:11<00:00,  2.04it/s]
 95%|█████████▌| 19/20 [00:11<00:00,  2.04it/s]
100%|██████████| 20/20 [00:12<00:00,  2.04it/s]
100%|██████████| 20/20 [00:12<00:00,  1.63it/s]
Version Details
Version ID
1f7f51e8b2e43ade14fb7d6d62385854477e078ac870778aafecf70c0a6de006
Version Created
January 1, 2023
Run on Replicate →