ComfyUI Node
Iris Sampler (Simple)
Iris-3B sampler with presets. Use the Advanced sampler for exact sizes and solver settings.
Iris Sampler (Simple)
- model
- conditioning
- image
- IMAGE
◄modetext to image►
◄resolution1:1 square (1024x1024)►
◄qualityfast (30 steps)►
◄prompt_adherencenormal (cfg 3)►
◄image_strengthmedium (denoise 0.5)►
◄seed0►
◄batch_size1►
CategoryIris-3B
Inputs (10)
| Name | Type | Default | Description |
|---|---|---|---|
| model | IRIS_MODEL | — | |
| conditioning | IRIS_CONDITIONING | — | |
| mode | COMBO | text to image | image to image starts from the connected image instead of pure noise |
| resolution | COMBO | 1:1 square (1024x1024) | in image to image the input is cropped to this size, or keeps its own aspect ratio with match input image |
| quality | COMBO | fast (30 steps) | 100 steps is the model card default, about 3x slower than fast |
| prompt_adherence | COMBO | normal (cfg 3) | how strictly the image follows the prompt |
| image_strength | COMBO | medium (denoise 0.5) | image to image only: how much the image may change |
| seed | INT | 00–18446744073709550000 | — |
| batch_size | INT | 11–8 | images per run |
| imageopt | IMAGE | source for image to image (ignored in text to image) |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| IMAGE | IMAGE | — |