Add 25 LoRA(s): roxi, holi-festival-of-colors-minimax-h3-by-sarcastic-tofu, comfyui-fastvideo-fasth3-4-step-lora-unofficial, jacked-huge-muscles…
6481511 verified | ═══════════════════════════════════════════════════════════════════════════════ | |
| H3 TURBO 4-8 STEP (ADALN-PRUNED) | |
| ═══════════════════════════════════════════════════════════════════════════════ | |
| ─────────────────────────────────────────────────────────────────────────────── | |
| IDENTITY | |
| ─────────────────────────────────────────────────────────────────────────────── | |
| Base model MiniMax H3 | |
| Generation mode First-and-Last-Frame-to-Video (FL2VA), Reference-to-Video (Ref2VA) | |
| Checkpoint both families — see the author's builds | |
| Category Speed / step-reduction | |
| Author Rkss | |
| Source https://huggingface.co/Rkss/Minimax_h3_fl2v_lightx2v_turbo_4to8step_v0.1-v1.0_768p_v4_step600_dareties_fro095_native | |
| Provenance HuggingFace · Rkss/Minimax_h3_fl2v_lightx2v_turbo_4to8step_v0.1-v1.0_768p_v4_step600_dareties_fro095_native · minimax_h3_fl2v_lightx2v_turbo_4to8step_v0.1-v1.0_768p_v4_step600_dareties_fro095_pruned.safetensors | |
| ─────────────────────────────────────────────────────────────────────────────── | |
| WEIGHTS | |
| ─────────────────────────────────────────────────────────────────────────────── | |
| File minimax_h3_fl2v_lightx2v_turbo_4to8step_v0.1-v1.0_768p_v4_step600_dareties_fro095_pruned.safetensors | |
| Version main | |
| Size 818.9 MB | |
| Format SafeTensor / unknown precision | |
| SHA256 063df5592549161ff62a1e29ef49978625ee5060eda7d97edfa631bd9aa713b1 | |
| Published 2026-09-04 | |
| ─────────────────────────────────────────────────────────────────────────────── | |
| 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 4–8 | |
| ─────────────────────────────────────────────────────────────────────────────── | |
| ADOPTION & POPULARITY | |
| ─────────────────────────────────────────────────────────────────────────────── | |
| Downloads 941 | |
| Rating 100% positive (1/1) | |
| Comments 0 | |
| Published 0 days ago | |
| Download rate 941.0/day since release | |
| Adoption rank #38 of 113 in this collection (Moderate) | |
| Momentum rank #12 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. | |
| • The author ships builds for both checkpoint families — pair each build | |
| with its own checkpoint and never cross-pair them. | |
| ─────────────────────────────────────────────────────────────────────────────── | |
| PROS | |
| ─────────────────────────────────────────────────────────────────────────────── | |
| + Author documents use across several modes (FL2V, REF2V). [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 819 MB — slower to load and heavier to stack. [source: file | |
| size] | |
| - Modest adoption (941 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 second of this repo's two builds of the same Turbo step-distillation | |
| LoRA: this one has the AdaLN modules pruned (624 tensors vs. 726 in the | |
| native port; its metadata states the only intentional information removal | |
| is all 51 AdaLN LoRA pairs, with no SVD or requantization of the retained | |
| factors). Same 4-8 step acceleration and strength guidance as the native | |
| build. Distinct weights, not a re-upload. | |
| ─────────────────────────────────────────────────────────────────────────────── | |
| EXAMPLE MEDIA | |
| ─────────────────────────────────────────────────────────────────────────────── | |
| 1 preview(s) in ./example_images/ — community results for | |
| this LoRA. Videos keep a matching _poster.jpg still frame. | |
| No prompts are recorded below: CivitAI's public API flags these posts as | |
| having generation metadata but does not return it, so the prompts cannot be | |
| scraped. Open the model page to read them. | |
| 01_image.png (image, ) | |
| ─────────────────────────────────────────────────────────────────────────────── | |
| 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 01:13 UTC. | |
| Stats and description are the author's; pros/cons are derived from the | |
| evidence tagged beside each line. | |
| ─────────────────────────────────────────────────────────────────────────────── | |