Kent Dhani(@kentdhani):I tried the X2-Detail-VAE for MiniMax H3 on my RTX5090 locally in ComfyUI. One mode's a free upscale at no extra render time, the other's hit-or-miss. - 2X decode: 736×1280 → 1472×2560. Clean upscale, slightly crisper edges, no new detail. - Detail mode: 7–14% darker. A touch crisper in this clip (lantern text, pattern edges), but no consistent gain across my tests, some came out softer. - Render time: ~320s for both. Links below👇

Kent Dhani

@kentdhani

Sharing Ai Update Stuff🔥 ✉️Dm for Collaborations works

Joined January 2025

117 Following 1.3K Followers

Kent Dhani@kentdhani

2026.10.08 05:23

I tried the X2-Detail-VAE for MiniMax H3 on my RTX5090 locally in ComfyUI. One mode's a free upscale at no extra render time, the other's hit-or-miss. - 2X decode: 736×1280 → 1472×2560. Clean upscale, slightly crisper edges, no new detail. - Detail mode: 7–14% darker. A touch crisper in this clip (lantern text, pattern edges), but no consistent gain across my tests, some came out softer. - Render time: ~320s for both. Links below👇