ComfyUI Node
RealRestorer Sampler
Restores a degraded image using RealRestorer. Select a Task Preset for common restoration tasks, or choose 'Custom' and write your own instruction. Paper defaults: 28 steps, guidance 3.0, size 1024, seed 42.
RealRestorer Sampler
- RR_Model
- image
- image
◄task_presetGeneral Restore►
◄instruction►
◄seed42►
◄steps28►
◄guidance_scale3.0►
◄size_level1024►
◄device_strategyauto►
CategoryRealRestorer
Inputs (9)
| Name | Type | Default | Description |
|---|---|---|---|
| RR_Model | RR_MODEL | — | |
| image | IMAGE | — | |
| task_preset | COMBO | General Restore | Select a restoration task. Each preset uses the prompt recommended in the RealRestorer paper for that degradation type. Choose 'Custom' to write your own instruction below. |
| instruction | STRING | Custom restoration instruction. Only used when Task Preset is set to 'Custom'. For all other presets, the paper-recommended prompt is used automatically. | |
| seed | INT | 420–18446744073709550000 | Random seed. Paper default: 42. |
| steps | INT | 2812–100 | Number of denoising steps. Paper default: 28. The official demo allows 12-40. Lower = faster but less detail. |
| guidance_scale | FLOAT | 3.01–6 | CFG guidance scale. Paper default: 3.0. The official demo allows 1.0-6.0. Higher values follow the prompt more strongly. |
| size_level | INT | 1024256–4096 | Target resolution for processing. Paper default: 1024. The input image is resized so its total pixel area is roughly size_level x size_level (preserving aspect ratio), processed at that resolution, then resized back to original dimensions. Higher = better quality but more VRAM (~34GB at 1024). |
| device_strategy | COMBO | auto | How to manage GPU memory. - auto: Uses full_gpu if >40GB VRAM, offload_to_cpu if >26GB, otherwise sequential_offload. - full_gpu: All components stay on GPU. Fastest. ~34GB at size 1024. - offload_to_cpu: Components move to CPU when not in use. Slower but ~24GB peak (the transformer weight size). - sequential_offload: Pre-loads as many transformer blocks to GPU as VRAM allows, streams the rest from CPU. On a 24GB card most blocks stay on GPU with only ~12 streaming. Enables cards that can't fit the full transformer. |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| image | IMAGE | — |