ComfyUI Node
Universal Input Hub by Steve Lasmin
A ComfyUI node in utils with 15 inputs and 20 outputs.
Universal Input Hub by Steve Lasmin
- model
- clip
- width
- height
- preview
- seed
- noise
- steps
- cfg
- sampler_name
- sampler
- scheduler_name
- sigmas
- flux_sigmas
- model
- prompt
- prompt_with_triggers
- negative_prompt
- trigger_words
- positive
- negative
- help
◄max_size1024►
◄aspect_ratiocustom►
◄width_ratio2►
◄height_ratio3►
◄multiplier32►
◄seed777►
◄steps20►
◄cfg4.0►
◄samplereuler►
◄schedulernormal►
◄prompt►
◄trigger_words►
◄negative_prompt►
Categoryutils
Inputs (15)
| Name | Type | Default | Description |
|---|---|---|---|
| max_size | INT | 102432–4096 | Maximum dimension in pixels. The longest side of the image will match this value. |
| aspect_ratio | COMBO | custom | Select a preset aspect ratio, or choose 'custom' to define your own via width_ratio and height_ratio. |
| width_ratio | INT | 21–999999 | Custom width component of the aspect ratio. Only used when aspect_ratio is set to 'custom'. |
| height_ratio | INT | 31–999999 | Custom height component of the aspect ratio. Only used when aspect_ratio is set to 'custom'. |
| multiplier | COMBO | 32 | Round width and height to be divisible by this value. Use 64 for SD 1.5, 32 for SDXL, 16 for Flux. |
| seed | INT | 7770–18446744073709550000 | Random seed for noise generation. Use 'control after generate' to randomize, increment, or keep fixed. |
| steps | INT | 201–10000 | Number of sampling steps. Higher values = more detail but slower generation. |
| cfg | FLOAT | 4.00–100 | Classifier-Free Guidance scale. Higher = stronger prompt adherence. Flux works well at 1.0-4.0, SDXL at 7.0-8.0. |
| sampler | COMBO | euler | Sampling algorithm. 'euler' is fast and reliable. 'dpmpp_2m' is higher quality. |
| scheduler | COMBO | normal | Noise schedule. 'normal' is standard. 'simple' works well with Flux. 'karras' for SDXL. |
| model | MODEL | The diffusion model. Required for standard sigmas calculation and model passthrough. | |
| clip | CLIP | The CLIP text encoder. Required to convert text prompts into conditioning tensors. | |
| prompt | STRING | Main positive prompt describing what you want to generate. | |
| trigger_words | STRING | Trigger words prepended to the prompt with '. ' separator. Leave empty to use prompt only. | |
| negative_prompt | STRING | Negative prompt describing what you want to exclude from the image. |
Outputs (20)
| Name | Type | Description |
|---|---|---|
| width | INT | — |
| height | INT | — |
| preview | STRING | — |
| seed | INT | — |
| noise | NOISE | — |
| steps | INT | — |
| cfg | FLOAT | — |
| sampler_name | STRING | — |
| sampler | SAMPLER | — |
| scheduler_name | STRING | — |
| sigmas | SIGMAS | — |
| flux_sigmas | SIGMAS | — |
| model | MODEL | — |
| prompt | STRING | — |
| prompt_with_triggers | STRING | — |
| negative_prompt | STRING | — |
| trigger_words | STRING | — |
| positive | CONDITIONING | — |
| negative | CONDITIONING | — |
| help | STRING | — |