ComfyUI Node
ThinkingLLM Prompt Enhancer (GGUF)
A ComfyUI node in ThinkingLLM with 17 inputs and 2 outputs.
ThinkingLLM Prompt Enhancer (GGUF)
- ENHANCED_OUTPUT
- RAW_TRACE
◄model_nameGoekdeniz-Guelmez.Josiefied-Qwen3-4B-Instruct-2507-gabliterated-v1.Q4_K_M.gguf [~2.4GB]►
◄prompt_text►
◄preset_system_prompt📝 Enhance►
◄custom_system_prompt►
◄max_tokens1024►
◄temperature0.70►
◄top_p0.90►
◄repetition_penalty1.10►
◄english_outputfalse►
◄deviceauto►
◄keep_model_loadedfalse►
◄seed1►
◄keep_last_promptfalse►
◄stream_tokens_to_terminalfalse►
◄enable_thinkingtrue►
◄auto_finalization_retryfalse►
◄hf_token►
CategoryThinkingLLM
Inputs (17)
| Name | Type | Default | Description |
|---|---|---|---|
| model_name | COMBO | Goekdeniz-Guelmez.Josiefied-Qwen3-4B-Instruct-2507-gabliterated-v1.Q4_K_M.gguf [~2.4GB] | GGUF text model from config or auto-detected local files. First run downloads the selected GGUF when it is not already on disk. |
| prompt_text | STRING | Prompt text to enhance. Leave blank to emit the selected preset instruction as the base prompt. | |
| preset_system_prompt | COMBO | 📝 Enhance | Preset enhancement style. Use Custom Only when you want custom_system_prompt to fully control the instruction. |
| custom_system_prompt | STRING | Optional extra instruction. Required when using Custom Only; otherwise it is prepended to the selected style. | |
| max_tokens | INT | 102432–16384 | Maximum new tokens for the enhanced prompt. Increase only when the model truncates useful detail. |
| temperature | FLOAT | 0.700.1–1 | Sampling randomness. Lower is more stable; higher is more varied. |
| top_p | FLOAT | 0.900–1 | Nucleus sampling cutoff. Lower values restrict token choice; 0.9 is a balanced default. |
| repetition_penalty | FLOAT | 1.100.5–2 | Values above 1.0 reduce repeated phrases in the enhanced prompt. |
| english_output | BOOLEAN | false | Ask the model to return the final enhanced prompt in English. |
| device | COMBO | auto | auto prefers GPU when available. If generation is unexpectedly slow, run tools/check_llama_backend.py to verify llama.cpp GPU offload. |
| keep_model_loaded | BOOLEAN | false | Keep the GGUF model in memory after generation so repeated prompt enhancement skips model loading. |
| seed | INT | 11–4294967295 | Sampling seed. Reusing it with identical inputs can reuse the saved prompt result. |
| keep_last_prompt | BOOLEAN | false | Return the saved per-node prompt instead of generating a new one when available. |
| stream_tokens_to_terminal | BOOLEAN | false | Show clean wrapped generated tokens in the ComfyUI terminal. Streaming bypasses fixed-seed reuse for a fresh run. |
| enable_thinking | BOOLEAN | true | Enable model reasoning/thinking when supported. The node still returns the cleaned final prompt, so reasoning may be hidden or empty. |
| auto_finalization_retry | BOOLEAN | false | If enabled, runs an extra LLM completion when the first output is empty or reasoning-only. Disabled by default so one node execution performs one generation pass. |
| hf_token | STRING | Optional Hugging Face access token for private or gated GGUF downloads. It is passed only to the download call, never logged or cached, and the in-memory copy is dropped after the download attempt. Clear this field before saving or sharing workflows. |
Outputs (2)
| Name | Type | Description |
|---|---|---|
| ENHANCED_OUTPUT | STRING | — |
| RAW_TRACE | STRING | — |