ComfyUI Node: 🔐 Qwen Prompt Expander
Run ComfyUI workflows without the setup
No installs, no CUDA version roulette, no GPU sitting idle on your bill. Bring a workflow and run it in the browser.
Category
🔐 Private AI
Inputs
model_source
- Preset Models
- Custom HuggingFace ID
- Local Path
preset_model
- HuggingFaceTB/SmolLM2-1.7B-Instruct (~1.7B - Recommended)
- Qwen/Qwen2.5-0.5B-Instruct (~0.5B - Ultra Light)
- Qwen/Qwen2.5-1.5B-Instruct (~1.5B - Balanced)
- cognitivecomputations/dolphin-2.9.4-qwen2.5-1.5b (~1.5B - Uncensored)
- TinyLlama/TinyLlama-1.1B-Chat-v1.0 (~1.1B - Fast)
- microsoft/Phi-3-mini-4k-instruct (~3.8B - Quality, needs 12GB VRAM)
- meta-llama/Llama-3.2-1B-Instruct (~1B - Meta)
custom_model_id STRING
precision
- fp16 (Standard)
- 8-bit (Fast)
- 4-bit (Ultra Light)
subject STRING
negative_prompt_text STRING
style
- Disabled
- Photorealistic
- Cyberpunk
- Dark Fantasy
- Anime
- Oil Painting
- Cinematic
- Vintage Photo
lighting
- Disabled
- Cinematic Lighting
- Studio Softbox
- Golden Hour
- Neon Lights
- Dark & Moody
quality
- Disabled
- 8k, Masterpiece
- RAW Photo
- Unreal Engine 5
- Sharp Focus
max_tokens INT
emb_positive
- None
emb_negative
- None
device_mode
- GPU (Fast)
- CPU (Safe Mode)
translator_device
- CPU (Stable)
- GPU (Faster)
use_translator_PL_EN BOOLEAN
unload_model BOOLEAN
add_negative BOOLEAN
seed INT
Outputs
STRING
STRING
Extension: ComfyUI Qwen Prompt Expander
Local AI prompt generator using Qwen/SmolLM2 models. 100% offline and private. Supports 4-bit/8-bit quantization. Runs on 6GB VRAM GPUs alongside Stable Diffusion. Smart token management, Polish-English translation, embedding support, OOM protection.
Authored by AnonBOTpl
Looking for a different node?
More nodes in ComfyUI Qwen Prompt Expander
Run ComfyUI workflows without the setup
No installs, no CUDA version roulette, no GPU sitting idle on your bill. Bring a workflow and run it in the browser.