ComfyUI Node
Hildegard References Split
Split the upscaled image into tiles and build the three Hildegard reference latents in one pass: - tile_latent: VAE-encoded crop of each tile (with optional high-frequency reduction so the model has room to invent texture) - position_latent: VAE-encoded 3x3 position map (current tile in center, 8 neighbors around it, cyan corner brackets ring the center) - global_latent: VAE-encoded thumbnail of the whole upscaled image tile 0 = all tiles (lists), tile # = only that tile.
Hildegard References Split
- image
- dac_data
- vae
- TILE(S)
- POSITION(S)
- tile_latent
- position_latent
- global_latent
◄tile0►
◄cell_size512►
◄ctrl3_max_size2048►
◄tile_high_freq_reduce0.00►
◄low_freq_radius256►
Categoryupscale/hildegard-refiner
Inputs (8)
| Name | Type | Default | Description |
|---|---|---|---|
| image | IMAGE | Upscaled IMAGE from Hildegard Plan. | |
| dac_data | HILDEGARD_DATA | dac_data from Hildegard Plan. Carries the tile grid, overlaps, and ordering this node has to honor. | |
| vae | VAE | VAE used to encode the three reference image types into latents. For FLUX.2 Klein, the Klein VAE. | |
| tile | INT | 0 | 0 = process all tiles in the grid (each output is a list of N entries). N >= 1 = process only that single tile (each output is a list of 1). Index follows the same linear/spiral ordering Hildegard Plan picked. |
| cell_size | INT | 51264–2048 | Side length (px) of each cell in the 3x3 position map. The final position image is cell_size x 3 on each axis. Larger = more spatial context detail, larger position latent. 512 is the Hildegard training default. |
| ctrl3_max_size | INT | 2048256–8192 | Long-edge cap (px) for the global thumbnail before VAE encoding. The whole upscaled image is downscaled so its longer edge fits this. 2048 is the Hildegard training default. |
| tile_high_freq_reduce | FLOAT | 0.000–1 | Attenuate the tile reference's high-frequency band (micro-detail / edges / texture) before VAE-encoding. 0 = full source detail preserved in the reference (tight fidelity, model has little room to add). 1 = soft, low-contrast version with only broad shapes and color preserved. Only affects the tile_latent output. The TILE(S) image output, position_latent, and global_latent are untouched. |
| low_freq_radius | FLOAT | 2561–256 | Gaussian-blur radius (px) defining the cutoff between low and high frequencies for tile_high_freq_reduce. Larger = more of the source's detail is classified as 'low frequency' and survives the reduce. Smaller = only the very-broadest shapes survive; the model regenerates everything else. |
Outputs (5)
| Name | Type | Description |
|---|---|---|
| TILE(S) | IMAGE | — |
| POSITION(S) | IMAGE | — |
| tile_latent | LATENT | — |
| position_latent | LATENT | — |
| global_latent | LATENT | — |