Add spatial batching to latent upscale

This commit is contained in:
2026-09-03 15:12:42 +00:00
parent 2cb3c694f0
commit 36d9f4369c
5 changed files with 131 additions and 8 deletions
+2 -2
View File
@@ -47,9 +47,9 @@
- Per-shot directives now support `continuity:`, `ref_mode:`, `ref_noise_aug:`, `anchor_add:`, `soundscape:`, and `music:` in addition to the existing timing and wardrobe directives.
- `Dumas H3 Latent Upscale Params`
- Inputs: `mode`, `model_name`, `method`, `width`, `height`, `device`, `precision`, `sampler_name`, `scheduler`, `steps`, `denoise`, `megapixels`
- Inputs: `mode`, `model_name`, `method`, `width`, `height`, `device`, `precision`, `sampler_name`, `scheduler`, `steps`, `denoise`, `megapixels`, `tile_width`, `tile_height`, `overlap`, `fade_width`, `overlap_mode`
- Output: `latent_upscale_param`
- Bundles the optional latent-space upscaler settings used by `Dumas H3 Long Videos` before decode, so the main node can rebuild conditioning at the target size and run a short refinement pass with your chosen sampler, scheduler, step count, and denoise.
- Bundles the optional latent-space upscaler settings used by `Dumas H3 Long Videos` before decode, so the main node can rebuild conditioning at the target size and run a short refinement pass with your chosen sampler, scheduler, step count, denoise, and optional spatial batching.
- `Dumas H3 Beat Prompt`
- Inputs: authored through the custom front-end beat editor