fofr/kontext-old-and-damaged 🔢📝❓🖼️✓ → 🖼️

▶️ 3.0K runs 📅 Jul 2025 ⚙️ Cog 0.15.10

About

Use this kontext fine-tune to turn any photo into an old and damaged photo

Example Output

Prompt:

"make it an old and damaged photo, scratched and faded"

Output

Performance Metrics

14.68s Prediction Time

14.68s Total Time

All Input Parameters

{
  "prompt": "make it an old and damaged photo, scratched and faded",
  "guidance": 3.5,
  "megapixels": "1",
  "input_image": "https://replicate.delivery/pbxt/NMXf0gosOqghKDa7ZYOinBuFvxWq1hjYGI8ehkdHRnYqdlZQ/02af5045-87d8-4553-b8e5-e6a1f8591d5b.png",
  "aspect_ratio": "3:2",
  "lora_strength": 1.4,
  "output_format": "webp",
  "output_quality": 80,
  "num_inference_steps": 30
}

Input Parameters

seed Type: integer: Random seed for reproducible generation. Leave blank for random.
prompt (required) Type: string: Text description of what you want to generate, or the instruction on how to edit the given image.
guidance Type: numberDefault: 2.5Range: 0 - 10: Guidance scale for generation
megapixels Default: 1: Approximate number of megapixels for generated image
input_image (required) Type: string: Image to use as reference. Must be jpeg, png, gif, or webp.
aspect_ratio Default: match_input_image: Aspect ratio of the generated image. Use 'match_input_image' to match the aspect ratio of the input image.
lora_strength Type: numberDefault: 1: Strength of the lora
output_format Default: webp: Output image format
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
replicate_weights Type: string: Path to the lora weights
num_inference_steps Type: integerDefault: 30Range: 4 - 50: Number of inference steps
disable_safety_checker Type: booleanDefault: false: Disable NSFW safety checker

Output Schema

Output

Type: string • Format: uri

Example Execution Logs

Unloaded 304 layers
LoRAs unloaded in 0.0032s
Loading LoRA weights for /src/weights-cache/aafb2a82ec3dc292
LoRA weights loaded
Extracting keys
Keys extracted
Applying LoRA:   0%|          | 0/304 [00:00<?, ?it/s]
Applying LoRA:  91%|█████████ | 277/304 [00:00<00:00, 2737.63it/s]
Applying LoRA: 100%|██████████| 304/304 [00:00<00:00, 2675.95it/s]
Loading LoRA in bf16
LoRA applied in 0.19s
Starting generate image
Using seed: 50407
Target dimensions: 1216x832
Starting prepare input
prepare input took 0.15 seconds
Starting denoise
denoise took 13.78 seconds
Starting decode
decode took 0.10 seconds
Starting convert to image
convert to image took 0.21 seconds
Starting Running safety checker
Total safe images: 1 out of 1
Running safety checker took 0.02 seconds
generate image took 14.34 seconds

Version Details

Version ID: 26f32770e4891a635eadbe5d10a8552287ff3a5b4f9190c593a85a962d2df16c
Version Created: July 15, 2025

Run on Replicate →