MiniMax H3 video vae int8 convrot and 8-step Turbo LoRA
More testing with MiniMax H3. This time, I'm using the fresh, new experimental VAE from Kijai: minimax_h3_video_vae_int8_convrot.safetensors.
I also used the Turbo custom node by larryvrh ComfyUI-MiniMax-H3-Turbo. I did a quick test with the 8-step Turbo LoRA and the new VAE, and the results are better in terms of speed with slightly improved quality.
Everything was tested on an RTX 3060 12GB. Rendering a 5-second video at 864x480 resolution with Turbo at 8 steps took 4.5 minutes.
It's not as fast as LTX, but it's doable. This is just the first test, and I need more time to benchmark everything properly. This includes testing the audio and pushing Minimax H3 with the custom prompts I use as benchmarks for every AI video model.
Cheers!
Seems interesting, have the turbo node degraded the quality?
why dont you use the int4 version of the qwen3vl? I am also on rtx 3060 12gb + 32 gb ram and am using that.
Have you guys try to run in low quality and upscale with Ltx2.3 or Wangp2, maybe it run more fast for low vram cards with 8GB and 12GB vram
Guys try out the new spectrum node, he made a update, its doubles ur speed its now like ltx lol
node github ComfyUI-Spectrum-MiniMax-H3