ComfyUI Node
NeuralBooru Validator
A ComfyUI node in NeuralBooru with 11 inputs and 3 outputs.
NeuralBooru Validator
- prompt
- dropped_tags
- tags
◄tags►
◄prompt_templatemasterpiece, best quality, amazing quality, 4k, very aesthetic, high resolution, ultra-detailed, absurdres, newest, scenery, {prompt}, BREAK, depth of field, volumetric lighting►
◄is_fallbackfalse►
◄validate_tagstrue►
◄strict_tagstrue►
◄fuzzy_cutoff0.00►
◄min_post_count0►
◄max_tags0►
◄exclude_categories►
◄template_presetcustom►
◄sort_tagstrue►
CategoryNeuralBooru
Inputs (11)
| Name | Type | Default | Description |
|---|---|---|---|
| tags | STRING | Comma-separated tags to validate. From NeuralBooruLLM or typed manually. | |
| prompt_template | STRING | masterpiece, best quality, amazing quality, 4k, very aesthetic, high resolution, ultra-detailed, absurdres, newest, scenery, {prompt}, BREAK, depth of field, volumetric lighting | Final prompt wrapper; {prompt} is replaced with the validated tags. If {prompt} is missing, tags are appended. |
| is_fallbackopt | BOOLEAN | false | When True (set by NeuralBooruLLM on error), skip validation and pass tags through into the template. Reproduces the original node's use_input_text fallback. |
| validate_tagsopt | BOOLEAN | true | Check every tag against the real Danbooru vocabulary. |
| strict_tagsopt | BOOLEAN | true | Drop candidates that match no real tag. Off keeps them raw. |
| fuzzy_cutoffopt | FLOAT | 0.000–1 | Remap near-miss tags by similarity (0.8+ recommended). 0 disables fuzzy matching. |
| min_post_countopt | INT | 00–1000000 | Drop tags with fewer Danbooru posts than this. 0 keeps all. |
| max_tagsopt | INT | 00–200 | Keep at most this many tags. 0 means no limit. |
| exclude_categoriesopt | STRING | Tag categories to drop, comma-separated: artist, character, copyright, meta, general. | |
| template_presetopt | COMBO | custom | Quality-tag wrapper for common model families. custom uses the prompt_template field above. |
| sort_tagsopt | BOOLEAN | true | Reorder tags Danbooru-style: people counts, character, copyright, artist, general, meta. Booru-trained models respond to this order. |
Outputs (3)
| Name | Type | Description |
|---|---|---|
| prompt | STRING | Validated tags wrapped in the prompt template, for your CLIP encoder. |
| dropped_tags | STRING | Candidates that failed validation, comma-separated. |
| tags | STRING | The validated tags alone, without the template. |