blinkdotleh/MiniMax H3 with SEEDVR2 upscaler + Ollama prompt helper | 16GB VRAM 32GB RAM
Attempt to build sage attention 2.2+ it speeds up MiniMax significantly. Tested on rtx5070ti. Diffusion model: https://huggingface.co/Comfy-Org/MiniMax-H3/blob/main/diffusion_models/minimax_h3_ref2va_pruned_int8_convrot.safetensors Text encoder: https://huggingface.co/ethanfel/Qwen3-VL-32B-Ultra-Heretic-H3-ComfyUI-INT8-ConvRot/blob/main/qwen3vl_32b_h3_ultra_uncensored_heretic_int8_convrot.safetensors VAEs: https://huggingface.co/Comfy-Org/MiniMax-H3/tree/main/vae https://huggingface.co/Kijai/MiniMax-H3-TAE/blob/main/vae_approx/taeh3.safetensors Turbo LoRA: https://huggingface.co/drbaph/MiniMax
| Author / organization | blinkdotleh |
|---|---|
| Downloads | 4.6K (as reported by Civitai) |
| Likes | 78 |
| Task | text-to-image |
| Created | 16 August 2026 |
| Last updated at source | — |
Popularity, last 2 days
4,576 now (+23 since 2026-10-15). Counts as reported by the source, snapshotted daily by Silytics.
More from blinkdotleh
Silytics shows public metadata from Civitai and links to the original. Information may be incomplete or out of date. Last refreshed 16 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.