I used 45 images from my final dataset of a realistic character based on Cruella De Vil to train this model: "Cruella De Vil - Realistic (ToonToLife) - One Hundred and One Dalmatians (1961)" who is canonically in her 30's, but often perceived as being in her 50s and is generally attributed to her severe lifestyle; specifically her gaunt frame, stark black-and-white hair, and relentless chain-smoking through a long cigarette holder, combined with a caricature-driven depiction meant to emphasize her villainous and sharp personality. This specific version is trained at ~2,500 steps. I recommend using at 0.8 strength. Because the source material is a highly stylized 2D cartoon, the measure of success and interpretation of a "realistic" counterpart is inherently subjective. I welcome your feedback and test images!

This LoRA is an experiment in translating a 2D animated style into photorealism. I used a combination of custom cartoon-style character LoRAs at low weights (0.3–0.5 strength) alongside detailed prompting and other style LoRAs to push the outputs toward realism. From these, I selected the best 20–60 images to train an initial realistic LoRA. Then, as needed, I generated a new batch of images and selected those that most closely matched the target body shape and consistent facial features to train the final LoRA.