ComfyUI Node: MiniCPM VQA Polished
Category
Comfyui_MiniCPM-V-2_6-int4
Inputs
text STRING
model
- MiniCPM-V-2_6-int4
- MiniCPM-Llama3-V-2_5-int4
keep_model_loaded BOOLEAN
top_p FLOAT
top_k INT
temperature FLOAT
repetition_penalty FLOAT
max_new_tokens INT
video_max_num_frames INT
video_max_slice_nums INT
seed INT
source_video_path PATH
source_image_path IMAGE
Outputs
STRING
Extension: ComfyUI_MiniCPM-V-2_6-int4
This is an implementation of a/MiniCPM-V-2_6-int4 by a/ComfyUI, including support for text-based queries, video queries, single-image queries, and multi-image queries to generate captions or responses.
Authored by IuvenisSapiens
Run ComfyUI workflows in the Cloud!
No downloads or installs are required. Pay only for active GPU usage, not idle time. No complex setups and dependency issues
Learn more