Add 17 LoRA(s): ai-girl-fictional-women-series31-31-minimax-h3, nagisa-mini-max-h3, chr-nea-north-eastern-asian-female-model, minimax-h3-turbo-sla-4-step-768p-lightx2v…
10cf674 verified | ═══════════════════════════════════════════════════════════════════════════════ | |
| H3 REF2VA PDD 8-STEP SIDECAR (ADALN2688, ANY BASE) | |
| ═══════════════════════════════════════════════════════════════════════════════ | |
| ─────────────────────────────────────────────────────────────────────────────── | |
| IDENTITY | |
| ─────────────────────────────────────────────────────────────────────────────── | |
| Base model MiniMax H3 | |
| Generation mode Reference-to-Video (Ref2VA) | |
| Checkpoint ref2va (drives Ref2VA only) | |
| Category Speed / step-reduction | |
| Author fbjr | |
| Source https://huggingface.co/fbjr/MiniMax-H3-Acc-LoRAs-sidecar | |
| Provenance HuggingFace · fbjr/MiniMax-H3-Acc-LoRAs-sidecar · minimax_h3_ref2va_pdd_8step_adaln2688_comfy.safetensors | |
| ─────────────────────────────────────────────────────────────────────────────── | |
| WEIGHTS | |
| ─────────────────────────────────────────────────────────────────────────────── | |
| File minimax_h3_ref2va_pdd_8step_adaln2688_comfy.safetensors | |
| Version main | |
| Size 1,595.2 MB | |
| Format SafeTensor / unknown precision | |
| SHA256 0ae7dd67aee7e73cb8f16f799fe872634851614530bdf3e8b7a82075701ef646 | |
| 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 | |
| ─────────────────────────────────────────────────────────────────────────────── | |
| The author did not publish specific settings. | |
| Start at strength 0.7 and adjust; see REFERENCE.txt for the MiniMax H3 | |
| community baseline. | |
| ─────────────────────────────────────────────────────────────────────────────── | |
| ADOPTION & POPULARITY | |
| ─────────────────────────────────────────────────────────────────────────────── | |
| Downloads 1,077 | |
| Rating 100% positive (4/4) | |
| Comments 0 | |
| Published 1 days ago | |
| Download rate 967.2/day since release | |
| Adoption rank #35 of 113 in this collection (Moderate) | |
| Momentum rank #10 of 113 by download rate (Hot · 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 | |
| ─────────────────────────────────────────────────────────────────────────────── | |
| + Well established — 1,077 downloads. [source: CivitAI stats] | |
| ─────────────────────────────────────────────────────────────────────────────── | |
| CONS & CAVEATS | |
| ─────────────────────────────────────────────────────────────────────────────── | |
| - Has a stated dependency — read the author's description before loading. | |
| [source: description] | |
| - No trigger word — the LoRA is always on once loaded, so strength is the | |
| only control. [source: model metadata] | |
| - Large at 1595 MB — slower to load and heavier to stack. [source: file | |
| size] | |
| ─────────────────────────────────────────────────────────────────────────────── | |
| 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 full-width Ref2VA acceleration sidecar converted from alibaba- | |
| pai/MiniMax-H3-Acc-LoRAs, carrying the AdaLN modulation update at its full | |
| 2688 width (metadata h3_pdd_loads_on: "either the pruned or the unpruned | |
| build") so it loads on any Ref2VA checkpoint, pruned or not. Header | |
| verified: rank-64 LoRA over 208 backbone modules plus the h3_pdd.* | |
| modulation and 32-head bank. Requires the repo's MiniMaxH3PDDLoRA custom | |
| node taken from the same revision as the file, with its SIGMAS output wired | |
| to the sampler instead of a BasicScheduler. | |
| ─────────────────────────────────────────────────────────────────────────────── | |
| 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 01:12 UTC. | |
| Stats and description are the author's; pros/cons are derived from the | |
| evidence tagged beside each line. | |
| ─────────────────────────────────────────────────────────────────────────────── | |