daanelson/speedy-sdxl-test 🔢📝❓✓ → 🖼️

▶️ 2.5K runs 📅 Sep 2023 ⚙️ Cog 0.8.3
sdxl text-to-image

About

SDXL, but faster

Example Output

Prompt:

"An astronaut riding a rainbow unicorn"

Output

Example output

Performance Metrics

9.42s Prediction Time
9.42s Total Time
All Input Parameters
{
  "width": 1024,
  "height": 1024,
  "prompt": "An astronaut riding a rainbow unicorn",
  "refine": "no_refiner",
  "scheduler": "K_EULER",
  "num_outputs": 1,
  "guidance_scale": 7.5,
  "apply_watermark": true,
  "high_noise_frac": 0.8,
  "negative_prompt": "",
  "prompt_strength": 0.8,
  "num_inference_steps": 50
}
Input Parameters
seed Type: integer
Random seed. Leave blank to randomize the seed
width Type: integerDefault: 1024
Width of output image
height Type: integerDefault: 1024
Height of output image
prompt Type: stringDefault: An astronaut riding a rainbow unicorn
Input prompt
refine Default: no_refiner
Which refine style to use
scheduler Default: K_EULER
scheduler
num_outputs Type: integerDefault: 1Range: 1 - 4
Number of images to output.
refine_steps Type: integer
For base_image_refiner, the number of steps to refine, defaults to num_inference_steps
guidance_scale Type: numberDefault: 7.5Range: 1 - 50
Scale for classifier-free guidance
apply_watermark Type: booleanDefault: true
Applies a watermark to enable determining if an image is generated in downstream applications. If you have other provisions for generating or deploying images safely, you can use this to disable watermarking.
high_noise_frac Type: numberDefault: 0.8Range: 0 - 1
For expert_ensemble_refiner, the fraction of noise to use
negative_prompt Type: stringDefault:
Input Negative Prompt
prompt_strength Type: numberDefault: 0.8Range: 0 - 1
Prompt strength when using img2img / inpaint. 1.0 corresponds to full destruction of information in image
num_inference_steps Type: integerDefault: 50Range: 1 - 500
Number of denoising steps
Output Schema

Output

Type: arrayItems Type: stringItems Format: uri

Example Execution Logs
Using seed: 31413
Prompt: An astronaut riding a rainbow unicorn
txt2img mode
  0%|          | 0/50 [00:00<?, ?it/s]
  2%|▏         | 1/50 [00:00<00:07,  6.79it/s]
  4%|▍         | 2/50 [00:00<00:07,  6.74it/s]
  6%|▌         | 3/50 [00:00<00:06,  6.73it/s]
  8%|▊         | 4/50 [00:00<00:06,  6.72it/s]
 10%|█         | 5/50 [00:00<00:06,  6.72it/s]
 12%|█▏        | 6/50 [00:00<00:06,  6.70it/s]
 14%|█▍        | 7/50 [00:01<00:06,  6.69it/s]
 16%|█▌        | 8/50 [00:01<00:06,  6.70it/s]
 18%|█▊        | 9/50 [00:01<00:06,  6.70it/s]
 20%|██        | 10/50 [00:01<00:05,  6.71it/s]
 22%|██▏       | 11/50 [00:01<00:05,  6.72it/s]
 24%|██▍       | 12/50 [00:01<00:05,  6.72it/s]
 26%|██▌       | 13/50 [00:01<00:05,  6.70it/s]
 28%|██▊       | 14/50 [00:02<00:05,  6.69it/s]
 30%|███       | 15/50 [00:02<00:05,  6.70it/s]
 32%|███▏      | 16/50 [00:02<00:05,  6.69it/s]
 34%|███▍      | 17/50 [00:02<00:04,  6.71it/s]
 36%|███▌      | 18/50 [00:02<00:04,  6.70it/s]
 38%|███▊      | 19/50 [00:02<00:04,  6.70it/s]
 40%|████      | 20/50 [00:02<00:04,  6.70it/s]
 42%|████▏     | 21/50 [00:03<00:04,  6.70it/s]
 44%|████▍     | 22/50 [00:03<00:04,  6.70it/s]
 46%|████▌     | 23/50 [00:03<00:04,  6.70it/s]
 48%|████▊     | 24/50 [00:03<00:03,  6.70it/s]
 50%|█████     | 25/50 [00:03<00:03,  6.69it/s]
 52%|█████▏    | 26/50 [00:03<00:03,  6.70it/s]
 54%|█████▍    | 27/50 [00:04<00:03,  6.69it/s]
 56%|█████▌    | 28/50 [00:04<00:03,  6.70it/s]
 58%|█████▊    | 29/50 [00:04<00:03,  6.70it/s]
 60%|██████    | 30/50 [00:04<00:02,  6.70it/s]
 62%|██████▏   | 31/50 [00:04<00:02,  6.70it/s]
 64%|██████▍   | 32/50 [00:04<00:02,  6.69it/s]
 66%|██████▌   | 33/50 [00:04<00:02,  6.68it/s]
 68%|██████▊   | 34/50 [00:05<00:02,  6.67it/s]
 70%|███████   | 35/50 [00:05<00:02,  6.66it/s]
 72%|███████▏  | 36/50 [00:05<00:02,  6.67it/s]
 74%|███████▍  | 37/50 [00:05<00:01,  6.67it/s]
 76%|███████▌  | 38/50 [00:05<00:01,  6.68it/s]
 78%|███████▊  | 39/50 [00:05<00:01,  6.68it/s]
 80%|████████  | 40/50 [00:05<00:01,  6.68it/s]
 82%|████████▏ | 41/50 [00:06<00:01,  6.68it/s]
 84%|████████▍ | 42/50 [00:06<00:01,  6.68it/s]
 86%|████████▌ | 43/50 [00:06<00:01,  6.68it/s]
 88%|████████▊ | 44/50 [00:06<00:00,  6.69it/s]
 90%|█████████ | 45/50 [00:06<00:00,  6.69it/s]
 92%|█████████▏| 46/50 [00:06<00:00,  6.68it/s]
 94%|█████████▍| 47/50 [00:07<00:00,  6.67it/s]
 96%|█████████▌| 48/50 [00:07<00:00,  6.66it/s]
 98%|█████████▊| 49/50 [00:07<00:00,  6.67it/s]
100%|██████████| 50/50 [00:07<00:00,  6.67it/s]
100%|██████████| 50/50 [00:07<00:00,  6.69it/s]
Version Details
Version ID
c3368e8507c19578b460a8f2f42224f7712c108b0eb0edd1e7b71f9f4f3b2ef9
Version Created
September 24, 2023
Run on Replicate →