charlesmccarthy/terminus-xl-gamma-v2 🔢📝❓✓ → 🖼️

▶️ 322 runs 📅 Dec 2023 ⚙️ Cog 0.8.6
text-to-image

About

Terminus XL Gamma is a new state-of-the-art latent diffusion model that uses zero-terminal SNR noise schedule and velocity prediction objective at training and inference time.

Example Output

Prompt:

"joe biden eating a cheeseburger at mcdonalds"

Output

Example output

Performance Metrics

8.22s Prediction Time
8.26s Total Time
All Input Parameters 
{
  "width": 1024,
  "height": 1024,
  "prompt": "joe biden eating a cheeseburger at mcdonalds",
  "scheduler": "DPMSolverMultistep",
  "num_outputs": 1,
  "guidance_scale": 6.5,
  "apply_watermark": false,
  "negative_prompt": "",
  "num_inference_steps": 32
}
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
scheduler Default: K_EULER
scheduler
num_outputs Type: integerDefault: 1Range: 1 - 4
Number of images to output.
guidance_scale Type: numberDefault: 2Range: 1 - 20
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.
negative_prompt Type: stringDefault:
Input Negative Prompt
num_inference_steps Type: integerDefault: 6Range: 1 - 50
Number of denoising steps
disable_safety_checker Type: booleanDefault: false
Disable safety checker for generated images. This feature is only available through the API. See [https://replicate.com/docs/how-does-replicate-work#safety](https://replicate.com/docs/how-does-replicate-work#safety)
Output Schema

Output

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

Example Execution Logs 
Using seed: 10943700
  0%|          | 0/32 [00:00<?, ?it/s]
  3%|▎         | 1/32 [00:00<00:06,  5.02it/s]
  9%|▉         | 3/32 [00:00<00:04,  6.21it/s]
 12%|█▎        | 4/32 [00:00<00:04,  5.75it/s]
 16%|█▌        | 5/32 [00:00<00:04,  5.49it/s]
 19%|█▉        | 6/32 [00:01<00:04,  5.32it/s]
 22%|██▏       | 7/32 [00:01<00:04,  5.21it/s]
 25%|██▌       | 8/32 [00:01<00:04,  5.15it/s]
 28%|██▊       | 9/32 [00:01<00:04,  5.11it/s]
 31%|███▏      | 10/32 [00:01<00:04,  5.08it/s]
 34%|███▍      | 11/32 [00:02<00:04,  5.06it/s]
 38%|███▊      | 12/32 [00:02<00:03,  5.04it/s]
 41%|████      | 13/32 [00:02<00:03,  5.03it/s]
 44%|████▍     | 14/32 [00:02<00:03,  5.02it/s]
 47%|████▋     | 15/32 [00:02<00:03,  5.02it/s]
 50%|█████     | 16/32 [00:03<00:03,  5.01it/s]
 53%|█████▎    | 17/32 [00:03<00:02,  5.01it/s]
 56%|█████▋    | 18/32 [00:03<00:02,  5.01it/s]
 59%|█████▉    | 19/32 [00:03<00:02,  5.00it/s]
 62%|██████▎   | 20/32 [00:03<00:02,  5.00it/s]
 66%|██████▌   | 21/32 [00:04<00:02,  5.00it/s]
 69%|██████▉   | 22/32 [00:04<00:01,  5.00it/s]
 72%|███████▏  | 23/32 [00:04<00:01,  4.99it/s]
 75%|███████▌  | 24/32 [00:04<00:01,  4.99it/s]
 78%|███████▊  | 25/32 [00:04<00:01,  5.00it/s]
 81%|████████▏ | 26/32 [00:05<00:01,  4.99it/s]
 84%|████████▍ | 27/32 [00:05<00:01,  4.99it/s]
 88%|████████▊ | 28/32 [00:05<00:00,  4.99it/s]
 91%|█████████ | 29/32 [00:05<00:00,  4.99it/s]
 94%|█████████▍| 30/32 [00:05<00:00,  4.99it/s]
 97%|█████████▋| 31/32 [00:06<00:00,  4.99it/s]
100%|██████████| 32/32 [00:06<00:00,  4.99it/s]
100%|██████████| 32/32 [00:06<00:00,  5.08it/s]
Version Details
Version ID
991d0656366cbaec46d5457fe8994b1a09cca74f3f7590370d1a3669ad891189
Version Created
December 24, 2023
Run on Replicate →