Use target dimensions for 2D H3 upscale

This commit is contained in:
2026-11-12 09:10:38 +00:00
parent 100f17d356
commit 8c0d0cf6e3
3 changed files with 28 additions and 18 deletions
+3 -2
View File
@@ -92,8 +92,9 @@ checkpoint from [LBH-123-AI](https://huggingface.co/LBH-123-AI/Minimax_h3_latent
It uses the model's published loader and architecture, but keeps DUMAS ownership
of the node and adds X/Y tiling. The full temporal latent is passed through each
tile; temporal splitting is intentionally not used. Put the checkpoint in
`models/latent_upscale_models`, then set `tile_size` and `tile_overlap` to fit
available VRAM.
`models/latent_upscale_models`, then set the target `width` and `height` in
pixels. The dimensions are converted to H3 latent dimensions internally. Set
`tile_size` and `tile_overlap` to fit available VRAM.
`DumasMMH3LatentUpscale2DModelParams` is the matching parameter node. Its output
is `latent_upscale_param` with type `H3_UPSCALE_PARAM`, so it connects to the