ComfyUI Node
ApplyRAUNet
This node is used to enable generation at higher resolutions than a model was trained for with less artifacts or other negative effects. This is the advanced version with more tuneable parameters, use ApplyRAUNetSimple if this seems too complex. NOTE: Only supports SD1.x, SD2.x and SDXL.
ApplyRAUNet
- model
- MODEL
◄input_blocks3►
◄output_blocks8►
◄time_modepercent►
◄start_time0.00►
◄end_time0.45►
◄upscale_mode▾►
◄ca_start_time0.00►
◄ca_end_time0.30►
◄ca_input_blocks4►
◄ca_output_blocks8►
◄ca_upscale_mode▾►
◄ca_downscale_modeadaptive_avg_pool2d►
◄ca_downscale_factor2.0►
◄two_stage_upscale_modedisabled►
◄yaml_parameters—►
Categorymodel_patches/unet
Inputs (16)
| Name | Type | Default | Description |
|---|---|---|---|
| model | MODEL | Model to be patched with the RAUNet effect. | |
| input_blocks | STRING | 3 | Comma-separated list of input Downsample blocks. Default is for SD 1.5. The corresponding valid block from output_blocks must be set along with input. Valid blocks for SD1.5: 3, 6, 9 Valid blocks for SDXL: 3, 6. Original Hidiffusion implementation uses 6 for SDXL. |
| output_blocks | STRING | 8 | Comma-separated list of output Upsample blocks. Default is for SD 1.5. The corresponding valid block from input_blocks must be set along with output. Valid blocks for SD1.5: 8, 5, 2 Valid blocks for SDXL: 5, 2. Original Hidiffusion implementation uses 2 for SDXL. |
| time_mode | COMBO | percent | Time mode controls how to interpret the values in start_time and end_time. |
| start_time | FLOAT | 0.000–999 | Time normal RAUNet effects start applying - value is inclusive. |
| end_time | FLOAT | 0.450–999 | Time normal RAUNet effects end - value is inclusive. |
| upscale_mode | COMBO | Method used when upscaling latents in output Upscale blocks. | |
| ca_start_time | FLOAT | 0.000–999 | Time normal cross-attention effects start applying - value is inclusive.. |
| ca_end_time | FLOAT | 0.300–999 | Time normal cross-attention effects end - value is inclusive. |
| ca_input_blocks | STRING | 4 | Comma separated list of input cross-attention blocks. Default is for SD1.x, for SDXL you can try using 5 (or just disable it). |
| ca_output_blocks | STRING | 8 | Comma-separated list of output cross-attention blocks. Default is for SD1.x, for SDXL you can try using 4 (or just disable it). |
| ca_upscale_mode | COMBO | Mode used when upscaling latents in output cross-attention blocks. | |
| ca_downscale_mode | COMBO | adaptive_avg_pool2d | Mode used when downscaling latents in output cross-attention blocks (use avg_pool2d for normal Hidiffusion behavior). adaptive_avg_pool2d should be the same and also supports fractional scales. |
| ca_downscale_factor | FLOAT | 2.0 | Factor to downscale with in cross-attention, 2.0 means downscale to half size. Must be an integer when using ca_downscale_mode avg_pool2d. |
| two_stage_upscale_mode | COMBO | disabled | When upscaling in output Upscale blocks (non-NA), do half the upscale with this mode and half with the normal upscale mode. May produce a different effect, isn't necessarily better. |
| yaml_parametersopt | STRING | Allows specifying custom parameters via YAML. You can also override any of the normal parameters by key. See main README for possible options. Note: When specifying paramaters this way, there is very little error checking. |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| MODEL | MODEL | Model patched with the RAUNet effect. |