ComfyUI Node: MiniCPM-V GGUF (Advanced)

Authored by 1038lab

Created

Updated

144 stars

Category

🧪AILab/📝MiniCPM

Inputs

image IMAGE
video VIDEO
model
  • MiniCPM-V-4 (Q4_0)
  • MiniCPM-V-4 (Q4_1)
  • MiniCPM-V-4 (Q4_K_M)
  • MiniCPM-V-4 (Q4_K_S)
  • MiniCPM-V-4 (Q5_0)
  • MiniCPM-V-4 (Q5_1)
  • MiniCPM-V-4 (Q5_K_M)
  • MiniCPM-V-4 (Q5_K_S)
  • MiniCPM-V-4 (Q6_K)
  • MiniCPM-V-4 (Q8_0)
preset_prompt
  • Describe
  • Caption
  • Analyze
  • Identify
  • Explain
  • List
  • Scene
  • Details
  • Summarize
  • Emotion
  • Style
  • Location
  • Question
  • Creative
  • Video Describe
  • Video Analyze
  • Video Identify
  • Video Explain
  • Video List
  • Video Scene
  • Video Details
custom_prompt STRING
system_prompt STRING
max_new_tokens INT
temperature FLOAT
top_p FLOAT
top_k INT
repetition_penalty FLOAT
video_max_num_frames INT
video_max_slice_nums INT
device
  • Auto
  • GPU
  • CPU
memory_management
  • Keep in Memory
  • Clear After Run
  • Global Cache
seed INT

Outputs

STRING

STRING

Extension: ComfyUI-MiniCPM

A ComfyUI custom node for MiniCPM vision-language models, enabling high-quality image captioning and analysis.

Authored by 1038lab

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