richard-megavision/model_laylite 🖼️🔢❓📝✓ → 🖼️

▶️ 30 runs 📅 Apr 2025 ⚙️ Cog 0.14.3

About

Example Output

Prompt:

The model_laylite is a very coarsely corrugated narrow cylindrical black plastic HDPE corrugated culvert pipe.

draw the model_laylite with a person standing beside it as accurately and to scale as possible

Output

Performance Metrics

36.93s Prediction Time

36.97s Total Time

All Input Parameters

{
  "model": "dev",
  "height": 1074,
  "prompt": "\nThe model_laylite is a very coarsely corrugated narrow cylindrical black plastic HDPE corrugated culvert pipe.\n\ndraw the model_laylite with a person standing beside it as accurately  and to scale as possible ",
  "go_fast": false,
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 4,
  "aspect_ratio": "1:1",
  "output_format": "png",
  "guidance_scale": 3,
  "output_quality": 80,
  "prompt_strength": 0.8,
  "extra_lora_scale": 1,
  "num_inference_steps": 32
}

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=26449264717824
Downloading weights
2025-04-04T07:07:54Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmpuaaya2r7/weights url=https://replicate.delivery/xezq/O1YlQgdMfVTSOSwQDn8SxGVxzq4HCKvDdoabcTAQzY1ieRfoA/trained_model.tar
2025-04-04T07:07:56Z | INFO  | [ Complete ] dest=/tmp/tmpuaaya2r7/weights size="172 MB" total_elapsed=1.733s url=https://replicate.delivery/xezq/O1YlQgdMfVTSOSwQDn8SxGVxzq4HCKvDdoabcTAQzY1ieRfoA/trained_model.tar
Downloaded weights in 1.75s
Loaded LoRAs in 4.29s
Using seed: 39149
Prompt:
The model_laylite is a very coarsely corrugated narrow cylindrical black plastic HDPE corrugated culvert pipe.
draw the model_laylite with a person standing beside it as accurately  and to scale as possible
[!] txt2img mode
  0%|          | 0/32 [00:00<?, ?it/s]
  3%|▎         | 1/32 [00:00<00:30,  1.03it/s]
  6%|▋         | 2/32 [00:01<00:25,  1.17it/s]
  9%|▉         | 3/32 [00:02<00:26,  1.10it/s]
 12%|█▎        | 4/32 [00:03<00:26,  1.07it/s]
 16%|█▌        | 5/32 [00:04<00:25,  1.05it/s]
 19%|█▉        | 6/32 [00:05<00:24,  1.04it/s]
 22%|██▏       | 7/32 [00:06<00:24,  1.04it/s]
 25%|██▌       | 8/32 [00:07<00:23,  1.03it/s]
 28%|██▊       | 9/32 [00:08<00:22,  1.03it/s]
 31%|███▏      | 10/32 [00:09<00:21,  1.03it/s]
 34%|███▍      | 11/32 [00:10<00:20,  1.03it/s]
 38%|███▊      | 12/32 [00:11<00:19,  1.03it/s]
 41%|████      | 13/32 [00:12<00:18,  1.02it/s]
 44%|████▍     | 14/32 [00:13<00:17,  1.02it/s]
 47%|████▋     | 15/32 [00:14<00:16,  1.02it/s]
 50%|█████     | 16/32 [00:15<00:15,  1.02it/s]
 53%|█████▎    | 17/32 [00:16<00:14,  1.02it/s]
 56%|█████▋    | 18/32 [00:17<00:13,  1.02it/s]
 59%|█████▉    | 19/32 [00:18<00:12,  1.02it/s]
 62%|██████▎   | 20/32 [00:19<00:11,  1.02it/s]
 66%|██████▌   | 21/32 [00:20<00:10,  1.02it/s]
 69%|██████▉   | 22/32 [00:21<00:09,  1.02it/s]
 72%|███████▏  | 23/32 [00:22<00:08,  1.02it/s]
 75%|███████▌  | 24/32 [00:23<00:07,  1.02it/s]
 78%|███████▊  | 25/32 [00:24<00:06,  1.02it/s]
 81%|████████▏ | 26/32 [00:25<00:05,  1.02it/s]
 84%|████████▍ | 27/32 [00:26<00:04,  1.02it/s]
 88%|████████▊ | 28/32 [00:27<00:03,  1.02it/s]
 91%|█████████ | 29/32 [00:28<00:02,  1.02it/s]
 94%|█████████▍| 30/32 [00:29<00:01,  1.02it/s]
 97%|█████████▋| 31/32 [00:30<00:00,  1.02it/s]
100%|██████████| 32/32 [00:31<00:00,  1.02it/s]
100%|██████████| 32/32 [00:31<00:00,  1.03it/s]
Total safe images: 4 out of 4

Version Details

Version ID: 17758786768428291f3d2158a7febd86b99617ed37b61e0e9c15510f609006f8
Version Created: April 4, 2025

Run on Replicate →