ashesashes/ugly-sweater 🖼️🔢📝❓✓ → 🖼️

▶️ 116 runs 📅 Dec 2023 ⚙️ Cog 0.8.2
christmas clothing text-to-image

Performance

14.0sTypical run time
116Total runs

About

Ugly Sweaters: The only garment that screams "Fashion? Never heard of it."

Example Output

Prompt:

"batman wearing a TOK sweater, superhero"

Output

Example output

Performance Metrics

14.03s Prediction Time
18.74s Total Time
All Input Parameters 
{
  "width": 768,
  "height": 1024,
  "prompt": "batman wearing a TOK sweater, superhero",
  "refine": "no_refiner",
  "scheduler": "K_EULER",
  "lora_scale": 0.6,
  "num_outputs": 1,
  "guidance_scale": 7.5,
  "apply_watermark": true,
  "high_noise_frac": 0.8,
  "negative_prompt": "deformed, blurry, ugly, ",
  "prompt_strength": 0.8,
  "num_inference_steps": 50
}
Input Parameters
mask Type: string
Input mask for inpaint mode. Black areas will be preserved, white areas will be inpainted.
seed Type: integer
Random seed. Leave blank to randomize the seed
image Type: string
Input image for img2img or inpaint mode
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
lora_scale Type: numberDefault: 0.6Range: 0 - 1
LoRA additive scale. Only applicable on trained models.
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
replicate_weights Type: string
Replicate LoRA weights to use. Leave blank to use the default weights.
num_inference_steps Type: integerDefault: 50Range: 1 - 500
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
Output Schema

Output

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

Example Execution Logs 
Using seed: 64441
Ensuring enough disk space...
Free disk space: 1987279429632
Downloading weights: https://replicate.delivery/pbxt/hvDO7VC9RR7eHKvoHxzDoNkHf0CvpIw8o7yxY7uzE67ryQESA/trained_model.tar
2023-12-20T21:25:46Z | INFO  | [ Initiating ] dest=/src/weights-cache/b245a83e2dc9dde2 minimum_chunk_size=150M url=https://replicate.delivery/pbxt/hvDO7VC9RR7eHKvoHxzDoNkHf0CvpIw8o7yxY7uzE67ryQESA/trained_model.tar
2023-12-20T21:25:47Z | INFO  | [ Complete ] dest=/src/weights-cache/b245a83e2dc9dde2 size="186 MB" total_elapsed=0.951s url=https://replicate.delivery/pbxt/hvDO7VC9RR7eHKvoHxzDoNkHf0CvpIw8o7yxY7uzE67ryQESA/trained_model.tar
b''
Downloaded weights in 1.1149499416351318 seconds
Loading fine-tuned model
Does not have Unet. assume we are using LoRA
Loading Unet LoRA
Prompt: batman wearing a <s0><s1> sweater, superhero
txt2img mode
  0%|          | 0/50 [00:00<?, ?it/s]
  2%|▏         | 1/50 [00:00<00:10,  4.53it/s]
  4%|▍         | 2/50 [00:00<00:10,  4.76it/s]
  6%|▌         | 3/50 [00:00<00:09,  4.83it/s]
  8%|▊         | 4/50 [00:00<00:09,  4.87it/s]
 10%|█         | 5/50 [00:01<00:09,  4.89it/s]
 12%|█▏        | 6/50 [00:01<00:08,  4.90it/s]
 14%|█▍        | 7/50 [00:01<00:08,  4.91it/s]
 16%|█▌        | 8/50 [00:01<00:08,  4.91it/s]
 18%|█▊        | 9/50 [00:01<00:08,  4.91it/s]
 20%|██        | 10/50 [00:02<00:08,  4.90it/s]
 22%|██▏       | 11/50 [00:02<00:07,  4.91it/s]
 24%|██▍       | 12/50 [00:02<00:07,  4.91it/s]
 26%|██▌       | 13/50 [00:02<00:07,  4.91it/s]
 28%|██▊       | 14/50 [00:02<00:07,  4.90it/s]
 30%|███       | 15/50 [00:03<00:07,  4.90it/s]
 32%|███▏      | 16/50 [00:03<00:06,  4.90it/s]
 34%|███▍      | 17/50 [00:03<00:06,  4.90it/s]
 36%|███▌      | 18/50 [00:03<00:06,  4.90it/s]
 38%|███▊      | 19/50 [00:03<00:06,  4.89it/s]
 40%|████      | 20/50 [00:04<00:06,  4.90it/s]
 42%|████▏     | 21/50 [00:04<00:05,  4.90it/s]
 44%|████▍     | 22/50 [00:04<00:05,  4.90it/s]
 46%|████▌     | 23/50 [00:04<00:05,  4.90it/s]
 48%|████▊     | 24/50 [00:04<00:05,  4.89it/s]
 50%|█████     | 25/50 [00:05<00:05,  4.90it/s]
 52%|█████▏    | 26/50 [00:05<00:04,  4.89it/s]
 54%|█████▍    | 27/50 [00:05<00:04,  4.90it/s]
 56%|█████▌    | 28/50 [00:05<00:04,  4.90it/s]
 58%|█████▊    | 29/50 [00:05<00:04,  4.89it/s]
 60%|██████    | 30/50 [00:06<00:04,  4.89it/s]
 62%|██████▏   | 31/50 [00:06<00:03,  4.89it/s]
 64%|██████▍   | 32/50 [00:06<00:03,  4.89it/s]
 66%|██████▌   | 33/50 [00:06<00:03,  4.89it/s]
 68%|██████▊   | 34/50 [00:06<00:03,  4.88it/s]
 70%|███████   | 35/50 [00:07<00:03,  4.89it/s]
 72%|███████▏  | 36/50 [00:07<00:02,  4.89it/s]
 74%|███████▍  | 37/50 [00:07<00:02,  4.89it/s]
 76%|███████▌  | 38/50 [00:07<00:02,  4.89it/s]
 78%|███████▊  | 39/50 [00:07<00:02,  4.89it/s]
 80%|████████  | 40/50 [00:08<00:02,  4.89it/s]
 82%|████████▏ | 41/50 [00:08<00:01,  4.89it/s]
 84%|████████▍ | 42/50 [00:08<00:01,  4.89it/s]
 86%|████████▌ | 43/50 [00:08<00:01,  4.89it/s]
 88%|████████▊ | 44/50 [00:08<00:01,  4.89it/s]
 90%|█████████ | 45/50 [00:09<00:01,  4.89it/s]
 92%|█████████▏| 46/50 [00:09<00:00,  4.88it/s]
 94%|█████████▍| 47/50 [00:09<00:00,  4.89it/s]
 96%|█████████▌| 48/50 [00:09<00:00,  4.89it/s]
 98%|█████████▊| 49/50 [00:10<00:00,  4.88it/s]
100%|██████████| 50/50 [00:10<00:00,  4.89it/s]
100%|██████████| 50/50 [00:10<00:00,  4.89it/s]
Version Details
Version ID
74cdb4a7ceaeda1bc758f379d5915831032c2219080033671eaa5908ab6da82f
Version Created
December 20, 2023
Run on Replicate →