FL2VA - first last (frame) to video / audio REF2VA - refimages / refvideos / refvideoaudios / refaudios: up to 9 reference images, 3 reference videos (each may carry its own paired soundtrack), and 3 standalone...
Model source
Source description
Minimax H3 INT8/INT4 Convrot
FL2VA - first last (frame) to video / audio REF2VA - ref_images / ref_videos / ref_video_audios / ref_audios: up to 9 reference images, 3 reference videos (each may carry its own paired soundtrack), and 3 standalone reference audio clips
Both models can generate t2v (Text to video), i2v (Image to video), v2v (Video to Video), a2v (Audio to video), and multiple references (image/video/audio). But were further fine-tuned/trained for higher-quality outputs for the intended use.
14.81 GB INT4BQ Balanced-Quality leaning: int8_ratio 0.41 by count, 0.47 by params; int8mm_ratio 0.58
17.27 GB INT4Q Quality: int8_ratio 0.73 by count, 0.75 by params; int8mm_ratio 0.27
Sources
1 sourceModel artifacts
5 artifactsminimax_h3_fl2va_bf16.safetensors
safetensors · 61.7 GB · Civitai
minimax_h3_fl2va_pruned_int8_convrot.safetensors
safetensors · 19.5 GB · SHA-256 e889202c41da…c47a · Civitai
Downloadminimax_h3_ref2va_bf16.safetensors
safetensors · 61.7 GB · Civitai
minimax_h3_ref2va_int8_convrot.safetensors
safetensors · 31.7 GB · SHA-256 9eef934046a0…76a9 · Civitai
Source excerpts
1 excerptSource context: 8304 downloads · Type Checkpoint · Base model MiniMax H3
minimaxH3INT8INT4_fl2vaINT8Pruned.safetensors
safetensors · 19.5 GB · SHA-256 e889202c41da…c47a · Civitai
Download