ComfyUI Node
Qwen 2.1 Prompt Enhancer Rewrite
A ComfyUI node in Qwen2.1 with 19 inputs and 4 outputs.
Qwen 2.1 Prompt Enhancer Rewrite
- qwen_pe_model
- image_1
- image_2
- image_3
- image_4
- image_5
- image_6
- image_7
- image_8
- image_9
- positive_prompt
- wh_ratio
- ratio_follow
- thinking
◄taskt2i►
◄system_prompt_file▾►
◄prompt—►
◄temperature1.00►
◄top_p0.95►
◄top_k20►
◄presence_penalty1.50►
◄max_new_tokens16256►
◄seed42►
CategoryQwen2.1
Inputs (19)
| Name | Type | Default | Description |
|---|---|---|---|
| qwen_pe_model | QWEN_PE_MODEL | Connect the loaded model from Qwen2.1 PE Loader. | |
| task | COMBO | t2i | Task type: 't2i' for text-to-image prompt expansion, 'edit' for image-based rewriting. |
| system_prompt_file | COMBO | System prompt template file located in ComfyUI/models/LLM/prompts/. | |
| prompt | STRING | Enter the short prompt or instruction you want to enhance. | |
| temperature | FLOAT | 1.000–2 | Controls randomness. Lower values make output more deterministic, higher values increase creativity. |
| top_p | FLOAT | 0.950–1 | Nucleus sampling threshold. Restricts the vocabulary selection range. |
| top_k | INT | 200–100 | Limits vocabulary to the top K most likely tokens. |
| presence_penalty | FLOAT | 1.500–2 | Penalizes repeated words. Higher values prevent the model from getting stuck in loops. |
| max_new_tokens | INT | 162561–32768 | Max generation length. Keep this large because the model outputs a long <think> reasoning process. |
| seed | INT | 420–18446744073709550000 | Random seed. Fixed seeds produce identical deterministic results. |
| image_1opt | IMAGE | — | |
| image_2opt | IMAGE | — | |
| image_3opt | IMAGE | — | |
| image_4opt | IMAGE | — | |
| image_5opt | IMAGE | — | |
| image_6opt | IMAGE | — | |
| image_7opt | IMAGE | — | |
| image_8opt | IMAGE | — | |
| image_9opt | IMAGE | — |
Outputs (4)
| Name | Type | Description |
|---|---|---|
| positive_prompt | STRING | — |
| wh_ratio | STRING | — |
| ratio_follow | STRING | — |
| thinking | STRING | — |