ComfyUI Node: VLM Prompt Advanced (GGUF)
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
VLMPrompt
Inputs
model_name
- Gemma4-E4B-uncensored-Q4_K_M
- Qwen3-VL-8B-abliterated-Q4_K_M
- Qwen3.5-4B-Uncensored-HauhauCS-Q4_K_M
- Qwen3.5-9B-Uncensored-HauhauCS-Q4_K_M
device
- auto
- cpu
preset_prompt
- NSFW I2V Tease
- Wan I2V Prompt
- Describe for Video
- Annotate Image
- Enhance Prompt
- 🖼️ Tags
- 🖼️ Simple Description
- 🖼️ Detailed Description
- 🖼️ Ultra Detailed Description
- 🎬 Cinematic Description
- 🖼️ Detailed Analysis
- 📹 Video Summary
- 📖 Short Story
- 🪄 Prompt Refine & Expand
- 📝 Enhance
- 📝 Refine
- 📝 Creative Rewrite
- 📝 Detailed Visual
- 📝 Artistic Style
- 📝 Technical Specs
- 🗣️ Dialogue for TTS
- 🎬 Prompt Relay - Music Video (4 beats)
- 🎬 Prompt Relay - Music Video (5 beats, 8s)
- 📖 Prompt Relay - Short Story (4 beats, 10s)
- 💃 Prompt Relay - Action/Dance (6 beats)
- 🗣️ Prompt Relay - Talking Head (3 beats)
- Custom
system_prompt STRING
custom_prompt STRING
max_tokens INT
temperature FLOAT
top_p FLOAT
repetition_penalty FLOAT
frame_count INT
ctx INT
n_batch INT
gpu_layers INT
image_max_tokens INT
top_k INT
pool_size INT
keep_model_loaded BOOLEAN
seed INT
image IMAGE
video IMAGE
Outputs
STRING
Extension: ComfyUI-VLMPrompt
ComfyUI custom nodes for local VLM prompt generation with GGUF and Hugging Face backends.
Authored by mexxmillion
Looking for a different node?
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.