-
-
Notifications
You must be signed in to change notification settings - Fork 577
MiniMax
MiniMax H3 is an omni-modal generative video model with support for unified understanding of multimodal contexts composed of text, images, video, and audio, and can generate video with native stereo audio at resolutions up to 2K and durations of up to 15 seconds.
Note
MiniMax H3 is massive! 33B transformer and 32B text-encoder (qwen3-vl) combine to 134GB of model weights in bfloat16!
Important
See offloading and quantization sections below before attempting to load MiniMax-H3
Important
Video support requires ffmpeg to be installed and available in the PATH
Due to size, MiniMax-H3 may not run properly on systems with less than 64GB of RAM
Depending on quantization and offloading methods, MiniMax-H3 can run comfortably on GPUs with as little as 16GB of VRAM
Tip
SD.Next provides access to SDNQ pre-quantized weights in uint4 precision which reduces the model size to 47GB
To use pre-quantized weights, simply select them from model selection dropdown
If you choose to use non-quantized weights, you should enable desired quantization
For more information see Quantization Wiki and SDNQ Wiki
SD.Next default offload method is balanced offloading which is the best starting point for most models. However, MiniMax-H3 is so massive that it may require more aggressive offloading to fit into your GPU memory
with balanced offloading, MiniMax-H3 requires a GPU with at least 24GB of VRAM.
recommended offload method for MiniMax-H3 is group offloading which allows MiniMax-H3 to run on a GPU with as little as 16GB of VRAM.
Tip
group offloading is a more aggressive offload method which does result in some performance loss, but it is the only way to run MiniMax-H3 on GPUs with less than 24GB of VRAM.
for more information see Offloading Wiki
MiniMax H3 has two separate variants which use different transformers weights:
- base: fl2va: used for text-to-video, image-to-video and first-last-frame-to-video video generation
- ref: ref2va: used for reference-based video generation
both base and ref variants use the same text-encoder weights, but have different transformer weights
pruned: Also, both base and ref variants are available in a pruned variant which is slightly smaller as parts of the transformer model are pruned/removed.
depending on which variant you load, you will have access to different workflows
available if base model is loaded
- prompting guide
- text-to-video is used when there are no input images provided
- image-to-video is used when a single input image is provided
- first-last-frame-to-video is used when two input images are provided
available if ref model is loaded
- prompting guide
- reference-to-video
in ref2va workflow, you can upload any combination of:
- 9 reference images
- 3 reference videos
- 3 reference audio files
total number of reference media must be up to 12 files
lengths of reference videos and audio files must be up to duration of generated video
everything as above except that MiniMax-H3 can also be used as a regular text-to-image/image-to-image model, not limited to Video generation
to use MiniMax-H3 as a t2i/i2i model, simply select it from the networks -> reference and use as any other model
MiniMax-H2 can be used with Turbo LoRA to reduce steps from base 30-50 down to 4-8 steps only!
Warning
Turbo LoRA is not compatible with pruned variant!
Due to pending lawsuit, MiniMax-H3 license comes with a disclaimer