ComfyUI Node
HSWQ Sampler
A ComfyUI node in sampling with 12 inputs and 1 output.
HSWQ Sampler
- model
- positive
- negative
- latent_image
- LATENT
◄seed0►
◄steps20►
◄cfg8.0►
◄sampler_name▾►
◄scheduler▾►
◄denoise1.00►
◄clip_perfect_offload (Krea2 only)false►
◄tensor_boostfalse►
Categorysampling
Inputs (12)
| Name | Type | Default | Description |
|---|---|---|---|
| model | MODEL | — | |
| seed | INT | 00–18446744073709550000 | — |
| steps | INT | 201–10000 | — |
| cfg | FLOAT | 8.00–100 | — |
| sampler_name | COMBO | 44 options: euler, euler_cfg_pp, euler_ancestral, euler_ancestral_cfg_pp, heun, heunpp2, +38 | |
| scheduler | COMBO | 9 options: simple, sgm_uniform, karras, exponential, ddim_uniform, beta, +3 | |
| positive | CONDITIONING | — | |
| negative | CONDITIONING | — | |
| latent_image | LATENT | — | |
| denoise | FLOAT | 1.000–1 | — |
| clip_perfect_offload (Krea2 only)opt | BOOLEAN | false | Krea2 only. Frees the Krea2 text encoder before sampling. Ignored for every other architecture. |
| tensor_boostopt | BOOLEAN | false | Enable Blackwell Per-Weight CUDA Graph Tensor Boost during sampling. ON raises VRAM by several GB (CUDA Graph arenas). |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| LATENT | LATENT | — |