See full description and find LoRAs for other base models at this page: <a target="_blank" rel="ugc" href="https://civarchive.com/models/971952">https://civarchive.com/models/971952</a><hr />Update log:(8/1/2025) v0.10 zeroTrained on 4.0zero. Synced latest 7K dataset and training parameters, close to illus v1.198.(3/30/2025) v0.6 optTrained on 4.0opt.(3/4/2025) v0.4The plan was to bring <s>RTX</s> natural lighting and super detailed texture to 2D characters.Trained on 4.0Zero with ~1k main stabilizer dataset, then with ~1k sub dataset contains real world images with dynamic lighting.Unlike usual style/concept LoRAs, this LoRA was trained in a way that will only add small final details. It won't blow up your output and create a realistic 3D character. So the effect may not that obvious at first glance.Recommended strength 0.5~1.No trigger word needed. However, using keywords that related to some kind of light sources, such as "lamp", "daylight", "soft lighting", may bring better results.In case someone may think this is placebo, here are 2 full size XY images. The composition of the images does not change. But the overall details change a lot.It even generated diffuse reflection of the clothes on the table surface. (👇 bottom left image below)<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/1d609c51-bf25-413f-a860-32861fd8d77c/original=true,quality=90,optimized=true/xyz_grid-0099-1.jpeg" alt="xyz_grid-0099-1.webp" /> <img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/5ab632e1-37b9-4667-8a8d-b3052c753bcc/original=true,quality=90,optimized=true/xyz_grid-0125-1.jpeg" alt="xyz_grid-0125-1.webp" />

Stabilizer AnimagineXL 4.0

ani40z_stabilizer_v0.4.safetensors

zero v0.4

zero v0.10

opt v0.6

See full description here: <a href="https://civitai.com/models/971952" rel="ugc noopener noreferrer nofollow" target="_blank">https://civitai.com/models/971952</a>

Files with SHA256: 8d8ebdeeefe9a749d9dcb95a563242a2e3e33d6f221bd5fd5e35798f0df7a7e2