ComfyUI Node
ToriiGate Captioner
A ComfyUI node in ToriiGate with 12 inputs and 1 output.
ToriiGate Captioner
- image
- caption
◄model_pathMinthy/ToriiGate-0.5►
◄devicecuda►
◄dtypebfloat16►
◄max_pixels_mp1.0►
◄keep_model_alivefalse►
◄prompt►
◄max_new_tokens512►
◄temperature0.50►
◄decodinggreedy_fast►
◄show_generation_progressfalse►
◄seed0►
CategoryToriiGate
Inputs (12)
| Name | Type | Default | Description |
|---|---|---|---|
| image | IMAGE | ComfyUI image tensor. The node uses only the first image in the batch and converts it to RGB before captioning. | |
| model_pathopt | STRING | Minthy/ToriiGate-0.5 | Model path. Use Minthy/ToriiGate-0.5 to download from Hugging Face, or a local path for an already downloaded copy. |
| deviceopt | COMBO | cuda | Where to run the model. auto uses CUDA when available; cuda is recommended for speed; cpu works, but will be very slow. |
| dtypeopt | COMBO | bfloat16 | Weight precision. bfloat16 is the native/recommended format; float16 may save VRAM on some GPUs; float32 uses more memory and is usually slower. |
| max_pixels_mpopt | FLOAT | 1.00.1–8 | Resolution limit sent to the model, in megapixels. 1.0 MP is recommended; higher values may improve detail, but increase VRAM use and runtime. |
| keep_model_aliveopt | BOOLEAN | false | Keeps the model loaded in VRAM/cache after generation. Enable for repeated captions; disable to free VRAM after each run. |
| promptopt | STRING | Optional prompt. You can connect the text output from the ToriiGate Grounding Builder here, or type your own. | |
| max_new_tokensopt | INT | 51264–4096 | Maximum generated tokens. Lower this for speed: 256-512 for quick captions; 1024+ for fuller long_thoughts formats. |
| temperatureopt | FLOAT | 0.500.01–2 | Generation randomness in sample mode. Lower values are more consistent; higher values are more creative, but may invent details. |
| decodingopt | COMBO | greedy_fast | sample uses temperature-based sampling and can vary more; greedy_fast chooses deterministic tokens and is usually faster and more stable. |
| show_generation_progressopt | BOOLEAN | false | Shows a progress bar and tokens/s in the console during generation. Disable to reduce overhead and gain a little speed. |
| seedopt | INT | 00–18446744073709550000 | Seed for reproducibility. Use 0 for a random seed; use a fixed value to repeat results in sample mode. |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| caption | STRING | — |