ComfyUI Node
Qwen Chat (Multi-turn)
A ComfyUI node in MiniMax H3 with 14 inputs and 2 outputs.
Qwen Chat (Multi-turn)
- response
- history
◄model▾►
◄mmprojNone►
◄chat_handlerQwen3.5►
◄n_ctx8192►
◄user_input►
◄system_prompt►
◄max_turns10►
◄clear_historyfalse►
◄enable_thinkingfalse►
◄seed0►
◄max_tokens1024►
◄temperature0.80►
◄top_p0.90►
◄top_k30►
CategoryMiniMax H3
Inputs (14)
| Name | Type | Default | Description |
|---|---|---|---|
| model | COMBO | 1 options: （未找到模型，请检查 models/LLM 目录） | |
| mmproj | COMBO | None | 1 options: None |
| chat_handler | COMBO | Qwen3.5 | 20 options: None, LLaVA-1.5, LLaVA-1.6, Moondream2, nanoLLaVA, llama3-Vision-Alpha, +14 |
| n_ctx | INT | 81921024–327680 | 上下文长度限制 |
| user_input | STRING | — | |
| system_prompt | STRING | — | |
| max_turns | INT | 101–50 | 保留的最近对话轮数，超过后自动丢弃最早的内容 |
| clear_history | BOOLEAN | false | 勾选后运行一次以清空该节点的对话历史 |
| enable_thinking | BOOLEAN | false | 关闭思考可大幅加速回答，开启思考质量更好（Qwen3.5 等 thinking 模型生效） |
| seed | INT | 00–18446744073709550000 | — |
| max_tokens | INT | 10240–8192 | — |
| temperature | FLOAT | 0.800–2 | — |
| top_p | FLOAT | 0.900–1 | — |
| top_k | INT | 300–1000 | — |
Outputs (2)
| Name | Type | Description |
|---|---|---|
| response | STRING | — |
| history | STRING | — |