Testing Virile Reality v1



I rendered these a long time ago — in June 2023 — to test Virile Reality version 1, a checkpoint model in Stable Diffusion intended for photography. VR is now in version 3, so it may not seem to be very relevant now — though there are some thigns in v1 that’s missing in v3 and vice versa, so it’s good to compare the two.
Since these are mostly technical tests, I never posted these before. I was browsing my archive today to look for something, and found that these images looked quite nice — and even though one could argue that they are not near photographic as Virile v3, it has some quality of it that I liked.
All the checkpoint models that Scratchproof makes has this charm in the men that’s really beautiful to me. I can’t explain it. See for yourself.
Also — highly impressive for a 25-step render.
Steps: 25, Sampler: DPM++ SDE Karras, CFG scale: 7, Seed: 3918292112, Size: 512x512, Model hash: d9911d91a2, Model: virileReality_v10, Denoising strength: 0.5, ADetailer model: face_yolov8n.pt, ADetailer confidence: 0.3, ADetailer dilate/erode: 4, ADetailer mask blur: 4, ADetailer denoising strength: 0.4, ADetailer inpaint only masked: True, ADetailer inpaint padding: 32, ADetailer model 2nd: hand_yolov8n.pt, ADetailer confidence 2nd: 0.3, ADetailer dilate/erode 2nd: 4, ADetailer mask blur 2nd: 4, ADetailer denoising strength 2nd: 0.4, ADetailer inpaint only masked 2nd: True, ADetailer inpaint padding 2nd: 32, ADetailer version: 23.6.2, Hires upscale: 2, Hires steps: 10, Hires upscaler: R-ESRGAN 4x+, Version: v1.3.2
- Rendered: 2023-06-15
- Published: 2023-11-04