ComfyUI Node: PVL Gemini with fallback Multi
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
PVL/LLM
Inputs
model
- gemini-3-pro-preview
- gemini-3-flash-preview
- gemini-2.5-pro
- gemini-2.5-flash
- gemini-2.5-flash-lite
tries INT
timeout INT
temperature FLOAT
top_p FLOAT
top_k STRING
thinking_level
- off
- minimal
- low
- medium
- high
- 0
- 1
- 2
- 3
- 4
batch INT
delimiter STRING
append_variation_tag BOOLEAN
debug BOOLEAN
instructions STRING
prompt STRING
seed INT
image1 IMAGE
image2 IMAGE
image3 IMAGE
image4 IMAGE
image5 IMAGE
image6 IMAGE
api_key STRING
openai_fallback BOOLEAN
force_openai BOOLEAN
openai_model
- GPT-5.1
- GPT-5 pro
- GPT-5 mini
- GPT-5 nano
openai_api_key STRING
Outputs
STRING
Extension: ComfyUI Assistant Node
A custom ComfyUI node that integrates with the OpenAI Assistants API.
Authored by pvlprk
Looking for a different node?
More nodes in ComfyUI Assistant 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.