ComfyUI Node
🤖 V2 Text Generation
A ComfyUI node in 🤖 GGUF-VLM/v2/Text with 8 inputs and 2 outputs.
🤖 V2 Text Generation
- model
- context
- thinking
◄max_tokens512►
◄temperature0.7►
◄top_p0.90►
◄top_k40►
◄repetition_penalty1.1►
◄enable_thinkingfalse►
◄promptHello, how are you?►
Category🤖 GGUF-VLM/v2/Text
Inputs (8)
| Name | Type | Default | Description |
|---|---|---|---|
| model | TEXT_MODEL | 文本模型配置 | |
| max_tokens | INT | 5121–8192 | 最大生成 token 数 |
| temperature | FLOAT | 0.70–2 | 温度参数（越高越随机） |
| top_p | FLOAT | 0.900–1 | Top-p 采样 |
| top_k | INT | 400–100 | Top-k 采样 |
| repetition_penalty | FLOAT | 1.11–2 | 重复惩罚 |
| enable_thinking | BOOLEAN | false | 启用思考模式（支持 DeepSeek-R1, Qwen3-Thinking 等模型） |
| prompt | STRING | Hello, how are you? | 输入提示词 |
Outputs (2)
| Name | Type | Description |
|---|---|---|
| context | STRING | — |
| thinking | STRING | — |