|
|
--- |
|
|
base_model: |
|
|
- black-forest-labs/FLUX.1-Krea-dev |
|
|
tags: |
|
|
- lora |
|
|
--- |
|
|
Comic-Style LoRA for FLUX.1-dev (c0m4i4) |
|
|
Base Model: FLUX.1-dev |
|
|
Type: LoRA (Flux Architecture) |
|
|
Trigger Word: c0m4i4 |
|
|
|
|
|
This LoRA brings a clean, bold comic-style aesthetic to your Flux generations. Trained on 37 high-resolution images at 1024px, it captures strong linework, vibrant color blocking, and stylized shading—perfect for portraits, character art, and vivid scene work. |
|
|
|
|
|
The model was trained for 16 epochs using Flux’s fp8 mixed-precision setup, with LoRA rank 16 for a balance between quality and file size. It adapts well to a variety of prompts, retaining the core comic feel while allowing for subject and scene diversity. |
|
|
|
|
|
Recommended Use: |
|
|
|
|
|
Resolution: 768–1024 |
|
|
|
|
|
Sampler: Flow/Euler (Flux schedulers) |
|
|
|
|
|
Steps: 24 (20–28 works well) |
|
|
|
|
|
Guidance (CFG): 1.0 |
|
|
|
|
|
LoRA Strength: 0.75 (UNet) / 0.6 (Text Encoder) |
|
|
|
|
|
Negative Prompt: low quality, artifacts, watermark |
|
|
|
|
|
Example Prompts: |
|
|
|
|
|
c0m4i4 as president, bold lines, vibrant shadows, comic illustration |
|
|
|
|
|
c0m4i4 in a black shirt standing in front of a stained glass window, glowing details, clean lines |
|
|
|
|
|
c0m4i4 playing a guitar, warm tones, sharp ink outlines |
|
|
|
|
|
Training Details: |
|
|
|
|
|
Dataset: 37 images × 5 repeats (185 samples per epoch) |
|
|
|
|
|
Network: LoRA rank 16, alpha 1 |
|
|
|
|
|
Loss: L2 with min_snr_gamma=5 and noise_offset=0.1 |
|
|
|
|
|
Text Encoders: CLIP-L + T5-XXL (mixed bf16/fp8) |
|
|
|
|
|
This LoRA is designed for artists and creators who want a consistent, high-quality comic style without sacrificing detail or prompt flexibility. |
