| ═══════════════════════════════════════════════════════════════════════════════ |
| LIGHTX2V TURBO REF2V 4-STEP V0.1 (RESIZED RANK 20) |
| ═══════════════════════════════════════════════════════════════════════════════ |
|
|
| ─────────────────────────────────────────────────────────────────────────────── |
| 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 Kijai |
| Source https://huggingface.co/Kijai/MiniMax-H3_comfy |
| Provenance HuggingFace · Kijai/MiniMax-H3_comfy · loras/minimax_h3_ref2v_lightx2v_turbo_4step_v0.1_resized_avg_rank_20_bf16.safetensors |
|
|
| ─────────────────────────────────────────────────────────────────────────────── |
| WEIGHTS |
| ─────────────────────────────────────────────────────────────────────────────── |
| File minimax_h3_ref2v_lightx2v_turbo_4step_v0.1_resized_avg_rank_20_bf16.safetensors |
| Version main |
| Size 292.5 MB |
| Format SafeTensor / unknown precision |
| SHA256 9ea3bd3a6aac22994153e294cf1ecab0a8766fc0f8d056ace645a01d1a6a4daf |
| Published 2026-08-13 |
|
|
| ─────────────────────────────────────────────────────────────────────────────── |
| 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: |
|
|
| LoRA strength 0.75 |
| Sampler steps 4 |
|
|
| ─────────────────────────────────────────────────────────────────────────────── |
| ADOPTION & POPULARITY |
| ─────────────────────────────────────────────────────────────────────────────── |
| Downloads 0 |
| Rating 100% positive (412/412) |
| Comments 0 |
| Published 22 days ago |
| Download rate 0.0/day since release |
|
|
| Adoption rank #93 of 113 in this collection (Niche) |
| Momentum rank #93 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 |
| ─────────────────────────────────────────────────────────────────────────────── |
| + Positively received — 412 thumbs-up with no down-votes. [source: |
| CivitAI stats] |
| + Author documents use across several modes (REF2V, FL2V). [source: |
| description] |
| + Compact at 293 MB — cheap to stack with other LoRAs. [source: file |
| size] |
| + 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] |
| - 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 |
| ─────────────────────────────────────────────────────────────────────────────── |
| ComfyUI conversion of LightX2V's 4-step distillation LoRA for the REF2V |
| (reference-to-video) MiniMax-H3 checkpoint, dynamically resized from rank |
| 128 to an average rank of about 20 in BF16 (header metadata: sv_fro 0.96 |
| dynamic resize from 128, alpha 8, scale 0.0625 baked in as a flat |
| multiplier). Load it on the REF2V checkpoint rather than the FL2V one; the |
| README's demo settings are 4 steps at 0.75 strength. |
|
|
| ─────────────────────────────────────────────────────────────────────────────── |
| 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 2026-09-04 23:23 UTC. |
| Stats and description are the author's; pros/cons are derived from the |
| evidence tagged beside each line. |
| ─────────────────────────────────────────────────────────────────────────────── |
|
|
