zhangp365/flux-redux-dev-lora 🔢📝❓🖼️✓ → 🖼️

▶️ 267 runs 📅 Apr 2025 ⚙️ Cog 0.13.3 🔗 GitHub ⚖️ License

image-editing image-to-image lora

About

update the official flux-redux-dev to support lora.

Example Output

Prompt:

"art nouveau"

Output

Performance Metrics

16.20s Prediction Time

16.21s Total Time

All Input Parameters

{
  "prompt": "art nouveau",
  "guidance": 3,
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 1,
  "redux_image": "https://replicate.delivery/pbxt/MpUZxGp2ETAVs8PcIx1HuycjpMUFTwLD23mCnGVta8Fite1x/00044-3696149592.png",
  "aspect_ratio": "3:4",
  "lora_weights": "civitai.com/models/782219/lora-flux-art-nouveau",
  "output_format": "png",
  "output_quality": 80,
  "num_inference_steps": 28
}

Input Parameters

seed Type: integer: Random seed. Set for reproducible generation
prompt (required) Type: string: Prompt for generated image
guidance Type: numberDefault: 3Range: 0 - 10: Guidance for generated image
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
redux_image (required) Type: string: Input image to condition your output on. This replaces prompt for FLUX.1 Redux models
aspect_ratio Default: 1:1: Aspect ratio for the generated image
lora_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'
output_format Default: webp: Format of the output images
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
num_inference_steps Type: integerDefault: 28Range: 1 - 50: Number of denoising steps. Recommended range is 28-50
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

Lora civitai.com/models/782219/lora-flux-art-nouveau already loaded
Using seed: 13968
0it [00:00, ?it/s]
1it [00:00,  3.35it/s]
2it [00:00,  2.27it/s]
3it [00:01,  2.05it/s]
4it [00:01,  1.96it/s]
5it [00:02,  1.91it/s]
6it [00:03,  1.88it/s]
7it [00:03,  1.87it/s]
8it [00:04,  1.86it/s]
9it [00:04,  1.85it/s]
10it [00:05,  1.84it/s]
11it [00:05,  1.84it/s]
12it [00:06,  1.83it/s]
13it [00:06,  1.83it/s]
14it [00:07,  1.83it/s]
15it [00:07,  1.83it/s]
16it [00:08,  1.83it/s]
17it [00:09,  1.83it/s]
18it [00:09,  1.83it/s]
19it [00:10,  1.83it/s]
20it [00:10,  1.82it/s]
21it [00:11,  1.82it/s]
22it [00:11,  1.83it/s]
23it [00:12,  1.82it/s]
24it [00:12,  1.82it/s]
25it [00:13,  1.82it/s]
26it [00:13,  1.82it/s]
27it [00:14,  1.82it/s]
28it [00:15,  1.82it/s]
28it [00:15,  1.86it/s]
Total safe images: 1 out of 1

Version Details

Version ID: 0fb2657da17422619c72349f1f7f90d834f9ae27a6a30ff53671d041605f28e8
Version Created: April 14, 2025

Run on Replicate →