ComfyUI Node
Local LLM Chat (GGUF)
A ComfyUI node in Kinburg-Nodes/LLM with 9 inputs and 2 outputs.
Local LLM Chat (GGUF)
- persona_1
- image
- persona_2
- persona_3
- persona_4
- persona_5
- persona_6
- text
- help
◄unload_on_approvetrue►
◄chat_state►
CategoryKinburg-Nodes/LLM
Inputs (9)
| Name | Type | Default | Description |
|---|---|---|---|
| persona_1 | KINBURG_LLM_CONFIG | Persona #1: wire a whole 'Local LLM Settings (GGUF)' here — its system prompt, model and sampling become the config for every turn this persona speaks. A chip for it appears in the chat as soon as a second persona is wired. Keep the loader fields (model, n_ctx, n_gpu_layers, flash_attn, kv_cache_type) identical across personas and switching between them costs no model reload. This one is also the node's default config. | |
| imageopt | IMAGE | Optional image for vision, attached to every turn while it stays connected. Prefer pasting or dropping a picture straight into the chat window instead — that attaches it to ONE turn and doesn't re-run this branch on every message. Needs an mmproj on the active Settings node either way. | |
| persona_2opt | KINBURG_LLM_CONFIG | Persona #2: wire a whole 'Local LLM Settings (GGUF)' here — its system prompt, model and sampling become the config for every turn this persona speaks. A chip for it appears in the chat as soon as a second persona is wired. Keep the loader fields (model, n_ctx, n_gpu_layers, flash_attn, kv_cache_type) identical across personas and switching between them costs no model reload. | |
| persona_3opt | KINBURG_LLM_CONFIG | Persona #3: wire a whole 'Local LLM Settings (GGUF)' here — its system prompt, model and sampling become the config for every turn this persona speaks. A chip for it appears in the chat as soon as a second persona is wired. Keep the loader fields (model, n_ctx, n_gpu_layers, flash_attn, kv_cache_type) identical across personas and switching between them costs no model reload. | |
| persona_4opt | KINBURG_LLM_CONFIG | Persona #4: wire a whole 'Local LLM Settings (GGUF)' here — its system prompt, model and sampling become the config for every turn this persona speaks. A chip for it appears in the chat as soon as a second persona is wired. Keep the loader fields (model, n_ctx, n_gpu_layers, flash_attn, kv_cache_type) identical across personas and switching between them costs no model reload. | |
| persona_5opt | KINBURG_LLM_CONFIG | Persona #5: wire a whole 'Local LLM Settings (GGUF)' here — its system prompt, model and sampling become the config for every turn this persona speaks. A chip for it appears in the chat as soon as a second persona is wired. Keep the loader fields (model, n_ctx, n_gpu_layers, flash_attn, kv_cache_type) identical across personas and switching between them costs no model reload. | |
| persona_6opt | KINBURG_LLM_CONFIG | Persona #6: wire a whole 'Local LLM Settings (GGUF)' here — its system prompt, model and sampling become the config for every turn this persona speaks. A chip for it appears in the chat as soon as a second persona is wired. Keep the loader fields (model, n_ctx, n_gpu_layers, flash_attn, kv_cache_type) identical across personas and switching between them costs no model reload. | |
| unload_on_approveopt | BOOLEAN | true | Free the LLM from VRAM when you press ✅ Approve, so the image model downstream has room. Turn off to keep chatting at full speed when nothing heavy follows. |
| chat_stateopt | STRING | The conversation, managed by the chat window. You don't edit this directly. |
Outputs (2)
| Name | Type | Description |
|---|---|---|
| text | STRING | — |
| help | STRING | — |