A high-rank fine art LoRA focused on academic marine painting, atmospheric lighting, and dramatic sea physics in the style of Ivan Aivazovsky. Built for deep dynamic range, authentic brushwork, and dual-light source contrast (moonlight vs. fire/sunlight).
Training Specs & Dataset
Dataset Size: 350+ curated high-quality images.
Dataset Resolution: Native 512 x 512 crop tagging to force the model to learn macro-lighting, sfumato, and color temperatures instead of micro-noise.
Training Duration: 2,000 steps.
LoRA Rank: 128 (provides exact gesture, light dispersion, and structural control without over-fitting).
Showcase Integrity (Pure Raw Generations)
No Post-Processing: All preview images are 100% raw outputs straight from the pipeline. No inpainting, no Photoshop, no external upscaling, and no seed cherry-picking tricks.
Prompt Consistency: All showcase images were generated using a unified single-prompt approach to demonstrate true model versatility.
Recommended Parameters
LoRA Weight / Strength:
1.0(Default)CLIP Weight:
1.0(Default)Aspect Ratio: 1024 x1536 (2:3 aspect ratio provides the sweet spot for spatial attention density and vertical composition depth).
Step Count Advice: 50 – 60 steps.
(Note: Showcase renders were experimentally pushed up to 65 steps to test latent limits. If you notice faint vertical sampling lines in high-frequency sky areas, drop steps down to 55-60 for clean, smooth gradients).
Workflow: Full ComfyUI workflow is embedded directly into the post file metadata.