ComfyUI Node
Ideogram 4 FlashAttention (CRT)
Patches Ideogram 4 attention to use FlashAttention 2, including its padding mask through the variable-length kernel. Optionally swaps the last transformer blocks between CPU and GPU to reduce VRAM use.
Ideogram 4 FlashAttention (CRT)
- model
- MODEL
◄blocks_to_swap0►
CategoryCRT/Model Patches
Inputs (2)
| Name | Type | Default | Description |
|---|---|---|---|
| model | MODEL | — | |
| blocks_to_swap | INT | 00–34 | Number of trailing Ideogram transformer blocks to keep on CPU and load one at a time during inference. |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| MODEL | MODEL | — |