feat: add minimax-h3 support

[leejet]

Summary

• Add Minimax-H3 support

Related Issue / Discussion

N/A

Additional Information

T2AV example

.\bin\Release\sd-cli.exe -M vid_gen --diffusion-model  ..\models\diffusion_models\minimax_h3_fl2va-Q4_K_M.gguf --vae ..\models\vae\minimax_h3_video_vae_fp16.safetensors --audio-vae ..\models\vae\minimax_h3_audio_vae_fp32.safetensors --llm ..\models\text_encoders\qwen3vl_32b_minimax_h3-Q4_K_M.gguf -p "A cute American Shorthair silver tabby kitten surfs on a tropical ocean wave, riding a white surfboard with the clear text 'sd.cpp' on it. Cinematic tracking shot, realistic water, bright sunlight, smooth motion, and consistent character appearance. Add upbeat tropical surf-rock background music with cheerful drums and guitar, synchronized with the kitten’s energetic surfing." --cfg-scale 1.0 -v -W 864 -H 480 --diffusion-fa --offload-to-cpu --rng cpu --fps 24 --video-frames 56

t2av.mp4

Checklist

• I have read and confirmed this PR follows the contribution guidelines.

[stduhpf]

So fast as always

[stduhpf]

I was very confused because it was segfaulting for me when building diffusion model graph (specifically after calling split_av_latents()). Turns out that's just because I forgot to specify -M vid_gen. Maybe it would be nice to find a way to foolproof this.