Overview
This LoRA is published exclusively for debugging and evaluation purposes,
to investigate a potential LoRA strength scaling issue in ComfyUI.
Test Prompt
1evospazio, SUV, front three-quarter view, full vehicle in frame,
2correct proportions, standard wheelbase,
3clean studio lighting, neutral background
3️⃣ Reference image (training dataset)
_MG_7173Training Reference Image
The following image is taken directly from the training dataset and shows
the intended vehicle geometry and proportions learned by the LoRA.
Inference Comparison
The images below were generated using the same prompt, seed, sampler, steps,
CFG, resolution, and LoRA strength.
Strenght 1.0
Base model generation
Base model generationDistilled model generation
Distilled model generationStrenght 3.0
Base model generation
Base model generationDistilled model generation
Distilled model generationAt LoRA strength = 1.0 the trained vehicle geometry is barely visible.
Only at strength ≈ 3.0 does the result match the training reference.
Usage Notice
This LoRA is published solely for debugging and evaluation purposes
in the context of ComfyUI and related tooling.
Commercial use, redistribution, fine-tuning, merging, or derivative works
are not permitted.
If you need to test this model for debugging purposes, you may do so,
but the generated outputs must not be used commercially.
