MiniMax-H3-Lora-ComfyUI

About

What MiniMax-H3-Lora-ComfyUI is

MiniMax-H3 Turbo LoRAs for ComfyUI This repository contains MiniMax-H3 Turbo LoRAs converted and optimized for ComfyUI: - dynamic-rank FL2V and Ref2V LoRAs derived from the official ComfyUI weights in lightx2v/Minimax-h3-Turbo; - pruned/curve-form compatibility conversions of the Turbo LoRAs released by larryvrh. These LoRAs accelerate MiniMax-H3 video and synchronized-audio generation by reducing the required number of sampling steps. Update — LightX2V FL2V and Ref2V Dynamic-Rank LoRAs Three dynamically resized BF16 LoRAs are now included. Their source weights were published in the correct MiniMax-H3 ComfyUI layout by: lightx2v/Minimax-h3-Turbo New files The LightX2V files were already supplied in the correct ComfyUI namespace and QKV layout. No namespace conversion or AdaLN pruning was required. How the LoRAs were resized Each LoRA was compressed using an exact compact SVD calculated from its LoRA A/B factors without materializing the full dense weight updates. The process: 1. Treats every attention, MLP and token-refiner projection independently. 2. Separates fused QKV adapters into their original Q, K and V projections. 3. Calculates the exact singular spectrum of each effective B @ A update. 4. Selects a dynamic rank independently for every projection. 5. Preserves one additional safety rank beyond the Frobenius-energy threshold. 6. Rebuilds balanced factors as A = sqrt(S) × Vh and B = U × sqrt(S). 7. Re-fuses Q, K and V using concatenated A factors and a block-diagonal B matrix. 8. Bakes the source alpha / rank scale into loraB. 9. Removes the no-longer-required alpha tensors. 10. Saves all output tensors as BF16. All three files target the same projection-level average rank: - Rank sum: 6778 - Projection count: 312 - Average projection rank: 21.724359 - Filename rank: floor(21.724359) = 21 Q, K and V are counted separately. The stored rank of a fused QKV adapter is the sum of its three independently selected ranks. Resize results The Ref2V source was reduced from approximately 1,865.57 MiB to 311.79 MiB, an 83.29% reduction. The v1.1 768p source (1,865.57 MiB) was reduced to 891.65 MiB (−52.21%) at rank 64 and to 375.55 MiB (−79.87%) at rank 28. A separat

Summarised from the published model card. Read the full card on the HuggingFace links below.

Specifications

What it is

How it works

How video models work

Variants

Sizes & precisions

Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys minimax-h3-lora-comfyui for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (minimax-h3-lora-comfyui below is illustrative; you get the exact model name on deployment.)

$ curl -sS https://api.axforge.ai/v1/videos/generations \
  -H "Authorization: Bearer $AXFORGE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"minimax-h3-lora-comfyui","prompt":"a drone shot over a forest"}'

Details

Languages, data & research

Licence

Open weights

Sources

Weights & code

Explore

More video models