═══════════════════════════════════════════════════════════════════════════════ PDD ACC 8-STEP (REF2VA) ═══════════════════════════════════════════════════════════════════════════════ ─────────────────────────────────────────────────────────────────────────────── IDENTITY ─────────────────────────────────────────────────────────────────────────────── Base model MiniMax H3 Generation mode Reference-to-Video (Ref2VA), First-and-Last-Frame-to-Video (FL2VA) Checkpoint ref2va (drives Ref2VA only) Category Speed / step-reduction Author Cybronya Source https://huggingface.co/Cybronya/minimax-h3-toolkit Provenance HuggingFace · Cybronya/minimax-h3-toolkit · loras/minimax_h3_ref2va_pdd_acc_8step_comfyui.safetensors ─────────────────────────────────────────────────────────────────────────────── WEIGHTS ─────────────────────────────────────────────────────────────────────────────── File minimax_h3_ref2va_pdd_acc_8step_comfyui.safetensors Version main Size 1,581.9 MB Format SafeTensor / unknown precision SHA256 5531fa0da887c24ec0083b0050ea9e4ff03c479cfbe21ef586d1c5c79bdc78a1 Published 2026-09-03 ─────────────────────────────────────────────────────────────────────────────── TRIGGER WORDS ─────────────────────────────────────────────────────────────────────────────── No trigger word. The LoRA applies as soon as it is loaded — strength is the only way to dial the effect up or down. ─────────────────────────────────────────────────────────────────────────────── RECOMMENDED SETTINGS ─────────────────────────────────────────────────────────────────────────────── Taken verbatim from the author's description: Sampler steps 8 ─────────────────────────────────────────────────────────────────────────────── ADOPTION & POPULARITY ─────────────────────────────────────────────────────────────────────────────── Downloads 0 Rating no votes yet Comments 0 Published 1 days ago Download rate 0.0/day since release Adoption rank #108 of 113 in this collection (Niche) Momentum rank #108 of 113 by download rate (Long tail · fresh release) Adoption tier is the percentile of total downloads within this collection; momentum is the percentile of downloads-per-day since release. Momentum is ranked rather than measured against a fixed rate, because this base model is itself new and every LoRA looks fast on an absolute scale. Both numbers are CivitAI's, read on the scrape date at the foot of this file. ─────────────────────────────────────────────────────────────────────────────── CHAINING / STACKING ─────────────────────────────────────────────────────────────────────────────── Stacks with others not stated The author gave no chaining guidance. The rules below are the general MiniMax H3 ones, not anything specific to this LoRA. General MiniMax H3 rules that apply here (see REFERENCE.txt): • Load the LoRA with LoraLoaderModelOnly between UNETLoader and your sampler; stacking means chaining several of those nodes in series. • This is a step-distillation (turbo) LoRA. DISTILL LORAS DO NOT COMPOSE — running this alongside another turbo/PDD/lightx2v LoRA breaks generation. Pick exactly one. • Style and character LoRAs stack on top of it normally, with no special strength penalty beyond ordinary multi-LoRA tuning. • Use Euler so the trained sigma schedule is consumed as intended, and keep CFG at 1.0 with BasicGuider. • Only the step counts the LoRA was trained for (usually 4, 6 or 8) work. Other values produce noise — it is not a free dial. • Chain this only onto the ref2va checkpoint. Loading it against the fl2va checkpoint can degrade output silently rather than erroring. ─────────────────────────────────────────────────────────────────────────────── PROS ─────────────────────────────────────────────────────────────────────────────── + Author documents use across several modes (REF2V, FL2V). [source: description] + Author published concrete recommended settings. [source: description] ─────────────────────────────────────────────────────────────────────────────── CONS & CAVEATS ─────────────────────────────────────────────────────────────────────────────── - No trigger word — the LoRA is always on once loaded, so strength is the only control. [source: model metadata] - Large at 1582 MB — slower to load and heavier to stack. [source: file size] - Modest adoption (0 downloads) — less community feedback to rely on. [source: source stats] ─────────────────────────────────────────────────────────────────────────────── COMPATIBILITY WARNING ─────────────────────────────────────────────────────────────────────────────── MiniMax H3 ships two transformers that share tensor key names: the fl2va checkpoint (driving T2VA, I2VA, L2VA and FL2VA) and the separate ref2va checkpoint (driving Ref2VA). Loading a LoRA against the wrong family can silently degrade output instead of raising an error, so confirm the family above matches the checkpoint you have loaded. Likewise, LoRAs built for full checkpoints often throw adaln_proj shape errors on pruned ones — match the build to your checkpoint. ─────────────────────────────────────────────────────────────────────────────── AUTHOR'S DESCRIPTION ─────────────────────────────────────────────────────────────────────────────── The Ref2VA counterpart of the PDD acceleration LoRA above, with metadata naming source_file MiniMax-H3-Ref2VA-Acc-8Step.safetensors from alibaba- pai/MiniMax-H3-Acc-LoRAs at rank 64 / alpha 64. Same 778-tensor ComfyUI layout and same PDD settings (32 steps, block size 4), but a different source_sha256 and a different repo-level file hash, so it is not a mirror of the FL2VA file. ─────────────────────────────────────────────────────────────────────────────── EXAMPLE MEDIA ─────────────────────────────────────────────────────────────────────────────── No work-safe previews were published for this version. ─────────────────────────────────────────────────────────────────────────────── HOW TO USE (COMFYUI) ─────────────────────────────────────────────────────────────────────────────── 1. Copy the .safetensors file into ComfyUI/models/loras/ 2. Load the matching H3 checkpoint with UNETLoader. 3. Insert LoraLoaderModelOnly between the loader and your sampler. 4. Set strength as listed above, then add any trigger word to the prompt. 5. Keep CFG at 1.0 with BasicGuider unless you know you want real CFG. ─────────────────────────────────────────────────────────────────────────────── Scraped by lorakit on 2026-09-05 01:18 UTC. Stats and description are the author's; pros/cons are derived from the evidence tagged beside each line. ───────────────────────────────────────────────────────────────────────────────