ComfyUI Node
GLM-4 Inferencing
A ComfyUI node in GLM4Wrapper with 11 inputs and 1 output.
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)
| Name | Type | Default | Description |
|---|---|---|---|
| GLMPipeline | GLMPipeline | Provide a GLM-4 pipeline. | |
| system_prompt | STRING | Provide a system prompt for inferencing. (Instructions for the model) | |
| user_prompt | STRING | Provide a user prompt for inferencing | |
| max_new_tokens | INT | 250 | Limit the number of output tokens |
| temperature | FLOAT | 0.70 | Temperature parameter for sampling |
| top_k | INT | 50 | Top-k parameter for sampling |
| top_p | FLOAT | 1.00 | Top-p parameter for sampling |
| repetition_penalty | FLOAT | 1.00 | Repetition penalty for sampling |
| seed | INT | 420–4294967295 | — |
| imageopt | IMAGE | Provide 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_modelopt | BOOLEAN | false | Unload the model after use to free up memory |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| output_text | STRING | — |