Hi,
I am using the MiniMax H3 video VAE in ComfyUI.
The official configuration uses vae_clip_length = 17, vae_tile_size = 256, and vae_tile_overlap_min = 64.
With an 864×480, 362-frame video, the original tiling strategy is very slow. However, changing the spatial tile size or overlap causes visible shadows and block-like artifacts.
Could you please clarify:
- Are
tile_size and tile_overlap configurable?
- What alignment rules must they follow? For example, must they be multiples of 16?
- Are temporal chunk size and temporal overlap configurable?
- Is full-frame spatial decoding valid when enough VRAM is available?
- Is there an official way to accelerate VAE decoding without artifacts?
Changing the tile settings causes visible artifacts at tile boundaries. Are there any required padding, blending, or positional-coordinate rules that must be preserved?
Environment:
- ComfyUI
minimax_h3_video_vae_fp16.safetensors- RTX 2080 Ti 22 GB
- 864×480, 362 frames
Hi,
I am using the MiniMax H3 video VAE in ComfyUI.
The official configuration uses
vae_clip_length = 17,vae_tile_size = 256, andvae_tile_overlap_min = 64.With an 864×480, 362-frame video, the original tiling strategy is very slow. However, changing the spatial tile size or overlap causes visible shadows and block-like artifacts.
Could you please clarify:
tile_sizeandtile_overlapconfigurable?Changing the tile settings causes visible artifacts at tile boundaries. Are there any required padding, blending, or positional-coordinate rules that must be preserved?
Environment:
minimax_h3_video_vae_fp16.safetensors