baoliwaters/sector_keypad2 🖼️🔢❓📝✓ → 🖼️

▶️ 67 runs 📅 May 2025 ⚙️ Cog 0.14.3

About

Example Output

Prompt:

"A standalone white rectangular (sectorKeypad), placed upright on a clean, neutral background. The device is centered, photographed under soft natural light. Minimalistic, high-resolution product photography style, everything in sharp focus. In the image, a human hand is seen pressing a button on a white digital keypad. The keypad is mounted on a white wall, and the hand is positioned on the right side of the keypad. The keypad has a total of 12 buttons, each marked with a number from 0 to 9, and also includes the numbers 1, 2, and 3. The background of the image reveals a room with a white ceiling and a window, providing a stark contrast to the white wall and keypad. The image does not contain any discernible text. The overall scene suggests an interaction with a digital interface, possibly for security or access control purposes. "

Output

Performance Metrics

35.91s Prediction Time

36.04s Total Time

All Input Parameters

{
  "model": "dev",
  "prompt": "A standalone white rectangular (sectorKeypad), placed upright on a clean, neutral background. The device is centered, photographed under soft natural light. Minimalistic, high-resolution product photography style, everything in sharp focus. In the image, a human hand is seen pressing a button on a white digital keypad. The keypad is mounted on a white wall, and the hand is positioned on the right side of the keypad. The keypad has a total of 12 buttons, each marked with a number from 0 to 9, and also includes the numbers 1, 2, and 3. The background of the image reveals a room with a white ceiling and a window, providing a stark contrast to the white wall and keypad. The image does not contain any discernible text. The overall scene suggests an interaction with a digital interface, possibly for security or access control purposes. ",
  "go_fast": false,
  "lora_scale": 0.8,
  "megapixels": "1",
  "num_outputs": 4,
  "aspect_ratio": "5:4",
  "output_format": "png",
  "guidance_scale": 3,
  "output_quality": 100,
  "prompt_strength": 0.85,
  "extra_lora_scale": 1,
  "num_inference_steps": 33
}

Input Parameters

mask Type: string: Image mask for image inpainting mode. If provided, aspect_ratio, width, and height inputs are ignored.
seed Type: integer: Random seed. Set for reproducible generation
image Type: string: Input image for image to image or inpainting mode. If provided, aspect_ratio, width, and height inputs are ignored.
model Default: dev: Which model to run inference with. The dev model performs best with around 28 inference steps but the schnell model only needs 4 steps.
width Type: integerRange: 256 - 1440: Width of generated image. Only works if `aspect_ratio` is set to custom. Will be rounded to nearest multiple of 16. Incompatible with fast generation
height Type: integerRange: 256 - 1440: Height of generated image. Only works if `aspect_ratio` is set to custom. Will be rounded to nearest multiple of 16. Incompatible with fast generation
prompt (required) Type: string: Prompt for generated image. If you include the `trigger_word` used in the training process you are more likely to activate the trained object, style, or concept in the resulting image.
go_fast Type: booleanDefault: false: Run faster predictions with model optimized for speed (currently fp8 quantized); disable to run in original bf16
extra_lora Type: string: Load LoRA weights. Supports Replicate models in the format <owner>/<username> or <owner>/<username>/<version>, HuggingFace URLs in the format huggingface.co/<owner>/<model-name>, CivitAI URLs in the format civitai.com/models/<id>[/<model-name>], or arbitrary .safetensors URLs from the Internet. For example, 'fofr/flux-pixar-cars'
lora_scale Type: numberDefault: 1Range: -1 - 3: Determines how strongly the main LoRA should be applied. Sane results between 0 and 1 for base inference. For go_fast we apply a 1.5x multiplier to this value; we've generally seen good performance when scaling the base value by that amount. You may still need to experiment to find the best value for your particular lora.
megapixels Default: 1: Approximate number of megapixels for generated image
num_outputs Type: integerDefault: 1Range: 1 - 4: Number of outputs to generate
aspect_ratio Default: 1:1: Aspect ratio for the generated image. If custom is selected, uses height and width below & will run in bf16 mode
output_format Default: webp: Format of the output images
guidance_scale Type: numberDefault: 3Range: 0 - 10: Guidance scale for the diffusion process. Lower values can give more realistic images. Good values to try are 2, 2.5, 3 and 3.5
output_quality Type: integerDefault: 80Range: 0 - 100: Quality when saving the output images, from 0 to 100. 100 is best quality, 0 is lowest quality. Not relevant for .png outputs
prompt_strength Type: numberDefault: 0.8Range: 0 - 1: Prompt strength when using img2img. 1.0 corresponds to full destruction of information in image
extra_lora_scale Type: numberDefault: 1Range: -1 - 3: Determines how strongly the extra LoRA should be applied. Sane results between 0 and 1 for base inference. For go_fast we apply a 1.5x multiplier to this value; we've generally seen good performance when scaling the base value by that amount. You may still need to experiment to find the best value for your particular lora.
replicate_weights Type: string: Load LoRA weights. Supports Replicate models in the format <owner>/<username> or <owner>/<username>/<version>, HuggingFace URLs in the format huggingface.co/<owner>/<model-name>, CivitAI URLs in the format civitai.com/models/<id>[/<model-name>], or arbitrary .safetensors URLs from the Internet. For example, 'fofr/flux-pixar-cars'
num_inference_steps Type: integerDefault: 28Range: 1 - 50: Number of denoising steps. More steps can give more detailed images, but take longer.
disable_safety_checker Type: booleanDefault: false: Disable safety checker for generated images.

Output Schema

Output

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

Example Execution Logs

free=27906332049408
Downloading weights
2025-05-16T20:10:01Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmp4si7l1ov/weights url=https://replicate.delivery/xezq/ju0JClpZ6fQZYiLrMrxV958YRD5rY8eGZj1ZmV3l282OkUtUA/trained_model.tar
2025-05-16T20:10:01Z | INFO  | [ Cache Service ] enabled=true scheme=http target=hermes.services.svc.cluster.local
2025-05-16T20:10:03Z | INFO  | [ Complete ] dest=/tmp/tmp4si7l1ov/weights size="172 MB" total_elapsed=1.834s url=https://replicate.delivery/xezq/ju0JClpZ6fQZYiLrMrxV958YRD5rY8eGZj1ZmV3l282OkUtUA/trained_model.tar
Downloaded weights in 1.85s
Loaded LoRAs in 2.42s
Using seed: 56536
Prompt: A standalone white rectangular (sectorKeypad), placed upright on a clean, neutral background. The device is centered, photographed under soft natural light. Minimalistic, high-resolution product photography style, everything in sharp focus. In the image, a human hand is seen pressing a button on a white digital keypad. The keypad is mounted on a white wall, and the hand is positioned on the right side of the keypad. The keypad has a total of 12 buttons, each marked with a number from 0 to 9, and also includes the numbers 1, 2, and 3. The background of the image reveals a room with a white ceiling and a window, providing a stark contrast to the white wall and keypad. The image does not contain any discernible text. The overall scene suggests an interaction with a digital interface, possibly for security or access control purposes.
[!] txt2img mode
  0%|          | 0/33 [00:00<?, ?it/s]
  3%|▎         | 1/33 [00:00<00:28,  1.11it/s]
  6%|▌         | 2/33 [00:01<00:24,  1.24it/s]
  9%|▉         | 3/33 [00:02<00:25,  1.18it/s]
 12%|█▏        | 4/33 [00:03<00:25,  1.15it/s]
 15%|█▌        | 5/33 [00:04<00:24,  1.14it/s]
 18%|█▊        | 6/33 [00:05<00:23,  1.13it/s]
 21%|██        | 7/33 [00:06<00:23,  1.12it/s]
 24%|██▍       | 8/33 [00:07<00:22,  1.11it/s]
 27%|██▋       | 9/33 [00:07<00:21,  1.11it/s]
 30%|███       | 10/33 [00:08<00:20,  1.11it/s]
 33%|███▎      | 11/33 [00:09<00:19,  1.12it/s]
 36%|███▋      | 12/33 [00:10<00:18,  1.11it/s]
 39%|███▉      | 13/33 [00:11<00:17,  1.11it/s]
 42%|████▏     | 14/33 [00:12<00:17,  1.11it/s]
 45%|████▌     | 15/33 [00:13<00:16,  1.11it/s]
 48%|████▊     | 16/33 [00:14<00:15,  1.11it/s]
 52%|█████▏    | 17/33 [00:15<00:14,  1.11it/s]
 55%|█████▍    | 18/33 [00:16<00:13,  1.11it/s]
 58%|█████▊    | 19/33 [00:16<00:12,  1.11it/s]
 61%|██████    | 20/33 [00:17<00:11,  1.11it/s]
 64%|██████▎   | 21/33 [00:18<00:10,  1.11it/s]
 67%|██████▋   | 22/33 [00:19<00:09,  1.11it/s]
 70%|██████▉   | 23/33 [00:20<00:09,  1.11it/s]
 73%|███████▎  | 24/33 [00:21<00:08,  1.11it/s]
 76%|███████▌  | 25/33 [00:22<00:07,  1.11it/s]
 79%|███████▉  | 26/33 [00:23<00:06,  1.11it/s]
 82%|████████▏ | 27/33 [00:24<00:05,  1.11it/s]
 85%|████████▍ | 28/33 [00:25<00:04,  1.11it/s]
 88%|████████▊ | 29/33 [00:25<00:03,  1.11it/s]
 91%|█████████ | 30/33 [00:26<00:02,  1.11it/s]
 94%|█████████▍| 31/33 [00:27<00:01,  1.11it/s]
 97%|█████████▋| 32/33 [00:28<00:00,  1.11it/s]
100%|██████████| 33/33 [00:29<00:00,  1.11it/s]
100%|██████████| 33/33 [00:29<00:00,  1.12it/s]
Total safe images: 4 out of 4

Version Details

Version ID: 7250489e07309a1ee80124f0f4cd59c6882ef58c5e1cd91058af832f056abe78
Version Created: May 16, 2025

Run on Replicate →