This is a lossless diff-LoRA extraction of TenStrip's 10Eros_Max fine-tune of MiniMax H3, for anyone who wants the fine-tune without running the full 40 GB checkpoint — including on the ref2va (reference-to-video-audio) variant, which has no official 10Eros release.What it is. 10Eros_Max's training touched only the fused QKV projections in transformer blocks 0–31; every other tensor is identical to the base model. This LoRA contains exactly those weight deltas, extracted by direct tensor subtraction (fine-tune minus base) and stored in ComfyUI's <code>.diff</code> LoRA format — not an SVD/rank approximation. At strength 1.0 on the FL2VA checkpoint it was extracted from, it reproduces the full fine-tune bit-for-bit; on sibling H3 variants it transplants the fine-tuned attention weights onto the shared transformer.How it was made. Both checkpoints (<code>10Eros_Max_h3_fl2va_bf16_test4_pruned</code> and stock <code>minimax_h3_fl2va_pruned_bf16</code>) were streamed tensor-by-tensor; differing tensors were identified by comparison and their fp32 deltas saved as <code>.diff</code> / <code>.diff_b</code> keys in bf16. Pruned-vs-pruned extraction, so the diff matches the pruned checkpoint family's layout.Usage.<ul><li>Load with LoraLoaderModelOnly (stock ComfyUI, no custom nodes needed).</li><li>On fl2va pruned bf16: strength 1.0 = the complete fine-tune.</li><li>On ref2va pruned bf16: start at 0.7–0.8. The fine-tune was trained in FL2VA context, so at high strength it can compete with reference-image adherence — lower strength trades fine-tune character for reference fidelity. Find your balance.</li><li>Strength scales the whole fine-tune continuously — something the full checkpoint can't do.</li><li>refva turbo lora (4steps) seems to not be enough for good results yet... still testing so not 100% sure. Anyways, safer to use higher steps or simply bypass the turbo lora.</li></ul>Requirements. A MiniMax H3 pruned-family checkpoint (bf16 recommended; applying onto int8/nvfp4 quants works via runtime patching but bf16 is cleanest), plus the standard H3 stack (Qwen3-VL text encoder, H3 video/audio VAEs).Credits &amp; license. Base model by MiniMax; 10Eros_Max fine-tune by TenStrip — all creative credit for the fine-tune is theirs, this is only a repackaging of their released weights. Use is subject to the MiniMax H3 Community License Agreement (same terms as the source checkpoints). Community conversion, not an official MiniMax or TenStrip release; TenStrip has indicated an official LoRA may accompany a future beta — prefer that when it exists.

Files with SHA256: 5512323817271bde085832ff06e362305cd91cfe9dbf6b59c0c320c34902edaf