ComfyUI Node
1. WorkflowGenerator
Step 1 - Generates a workflow diagram from natural language instructions. This is the first stage of the pipeline, converting text to a structured plan.
1. WorkflowGenerator
- workflow_edges
- instruction
◄instruction—►
◄model_pathworkflow-generator-q8_0.gguf►
◄dtypeauto►
◄device_preferenceauto►
◄attn_implementationauto►
◄auto_gpu_layerstrue►
◄n_gpu_layers-1►
◄max_new_tokens8192►
◄context_size4096►
◄use_mmaptrue►
◄use_mlockfalse►
◄n_batch512►
◄n_threadsAuto►
◄temperature0.95►
◄top_p0.70►
◄allow_primitive_nodesfalse►
◄seed0►
CategoryWorkflowGenerator
Inputs (17)
| Name | Type | Default | Description |
|---|---|---|---|
| instruction | STRING | Description of the desired ComfyUI workflow. | |
| model_path | COMBO | workflow-generator-q8_0.gguf | Model file (GGUF) or directory (HuggingFace). |
| dtype | COMBO | auto | Data type (HuggingFace only). |
| device_preference | COMBO | auto | Device preference (cuda/cpu). |
| attn_implementation | COMBO | auto | Attention implementation (HuggingFace). |
| auto_gpu_layers | BOOLEAN | true | Auto-calculate GPU layers based on available VRAM (prevents OOM errors) (GGUF). |
| n_gpu_layers | INT | -1-1–1000 | Number of GPU layers (GGUF). -1 for all. |
| max_new_tokens | INT | 81921–32768 | Max tokens to generate. |
| context_size | INT | 4096512–131072 | Context window size (GGUF). |
| use_mmap | BOOLEAN | true | Use memory-mapped loading (GGUF). |
| use_mlock | BOOLEAN | false | Lock memory to prevent swapping (GGUF). |
| n_batch | INT | 51232–2048 | Batch size for prompt processing (GGUF). |
| n_threads | COMBO | Auto | CPU threads for inference (GGUF). |
| temperature | FLOAT | 0.950–2 | Sampling temperature. |
| top_p | FLOAT | 0.700–1 | Top-p sampling. |
| allow_primitive_nodes | BOOLEAN | false | Include primitive nodes in diagram. False (recommended) removes them for cleaner workflows. |
| seed | INT | 00–4294967295 | Random seed. |
Outputs (2)
| Name | Type | Description |
|---|---|---|
| workflow_edges | STRING | Generated workflow diagram (JSON). |
| instruction | STRING | Original instruction text (pass to Step 2). |