ComfyUI Node
ialhabbal VLLM Prompt Enhancer
A ComfyUI node in 🧪ialhabbal_VLLM with 14 inputs and 1 output.
ialhabbal VLLM Prompt Enhancer
- ENHANCED_OUTPUT
◄model_nameQwen3-0.6B►
◄quantizationNone (FP16)►
◄attention_modeauto►
◄use_torch_compilefalse►
◄deviceauto►
◄prompt_text►
◄enhancement_style📝 Enhance►
◄custom_system_prompt►
◄max_tokens256►
◄temperature0.70►
◄top_p0.90►
◄repetition_penalty1.10►
◄keep_model_loadedtrue►
◄seed1►
Category🧪ialhabbal_VLLM
Inputs (14)
| Name | Type | Default | Description |
|---|---|---|---|
| model_name | COMBO | Qwen3-0.6B | Pick the Qwen-VL checkpoint. First run downloads weights into models/LLM/Qwen-VL, so leave disk space. |
| quantization | COMBO | None (FP16) | Precision vs VRAM. FP16 gives the best quality if memory allows; 8-bit suits 8–16 GB GPUs; 4-bit fits 6 GB or lower but is slower. |
| attention_mode | COMBO | auto | auto tries flash-attn v2 when installed and falls back to SDPA. Only override when debugging attention backends. |
| use_torch_compile | BOOLEAN | false | Enable torch.compile('reduce-overhead') on supported CUDA/Torch 2.1+ builds for extra throughput after the first compile. |
| device | COMBO | auto | Choose where to run the model: auto, cpu, mps, or cuda:x for multi-GPU systems. |
| prompt_text | STRING | Prompt text to enhance. Leave blank to just emit the preset instruction. | |
| enhancement_style | COMBO | 📝 Enhance | 6 options: 📝 Enhance, 📝 Refine, 📝 Creative Rewrite, 📝 Detailed Visual, 📝 Artistic Style, 📝 Technical Specs |
| custom_system_prompt | STRING | — | |
| max_tokens | INT | 25632–1024 | — |
| temperature | FLOAT | 0.700.1–1 | — |
| top_p | FLOAT | 0.900–1 | — |
| repetition_penalty | FLOAT | 1.100.5–2 | — |
| keep_model_loaded | BOOLEAN | true | — |
| seed | INT | 11–4294967295 | — |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| ENHANCED_OUTPUT | STRING | — |