ComfyUI Node: Ollama VL → Prompt
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
prompt/ollama
Inputs
preset
- SDXL
- Inpainting (Preserve Context)
- Anime / Illustration
- Caption (Neutral)
- Qwen Image Edit 2511
- NSFW
- SFW
user_hint STRING
model
- No model detected
keep_alive FLOAT
combine_all_images
- True
- False
image1 IMAGE
image2 IMAGE
image3 IMAGE
Outputs
STRING
Extension: comfyui_ollama_vl_prompt
A custom ComfyUI node that uses Ollama vision-language models to generate or refine prompts from multiple input images and text.
Authored by JuanBerta
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.