Nodes/ComfyUI GLM-4 Wrapper/GLM-4 Inferencing
ComfyUI Node

GLM-4 Inferencing

A ComfyUI node in GLM4Wrapper with 11 inputs and 1 output.

By Nojahhh·Created 2 years ago·Updated about a year ago· 30
GLM-4 Inferencing
  • GLMPipeline
  • image
  • output_text
system_prompt
user_prompt
max_new_tokens250
temperature0.70
top_k50
top_p1.00
repetition_penalty1.00
seed42
unload_modelfalse
CategoryGLM4Wrapper

Inputs (11)

NameTypeDefaultDescription
GLMPipelineGLMPipelineProvide a GLM-4 pipeline.
system_promptSTRINGProvide a system prompt for inferencing. (Instructions for the model)
user_promptSTRINGProvide a user prompt for inferencing
max_new_tokensINT250Limit the number of output tokens
temperatureFLOAT0.70Temperature parameter for sampling
top_kINT50Top-k parameter for sampling
top_pFLOAT1.00Top-p parameter for sampling
repetition_penaltyFLOAT1.00Repetition penalty for sampling
seedINT420–4294967295
imageoptIMAGEProvide an image to use as input for inferencing. Only supported for glm-4v-9b, glm-4v-9b-gptq-4bit and glm-4v-9b-gptq-3bit models.
unload_modeloptBOOLEANfalseUnload the model after use to free up memory

Outputs (1)

NameTypeDescription
output_textSTRING