Nodes/ComfyUI VicNodes/Ollama Chat (Local)
ComfyUI Node

Ollama Chat (Local)

Run a local Ollama model with a text prompt and optional image batch/list. Connect Response to any STRING-compatible node. Use Edit > Ollama: Refresh Models after downloading a new model.

By VictorDmAlves·Created 21 days ago·Updated 4 days ago· 0
Ollama Chat (Local)
  • images
  • Response
◄ollama_urlhttp://localhost:11434►
◄model▾►
◄prompt►
◄seed0►
◄temperature0.70►
◄max_tokens512►
◄context_size4096►
◄system_prompt►
◄thinking▾►
◄keep_alive▾►
◄image_format▾►
◄image_max_side1024►
◄jpeg_quality90►
◄max_images8►
◄timeout_seconds300►
◄cache_mode▾►
CategoryVicNodes/Ollama Bridge

Inputs (17)

NameTypeDefaultDescription
ollama_urlSTRINGhttp://localhost:11434Address of the Ollama service as seen by the ComfyUI backend.
modelCOMBOLocally downloaded Ollama model. Refresh via ComfyUI Edit > Ollama: Refresh Models.
promptSTRINGMessage sent directly to the model. Also accepts images connected below.
seedINT00–2147483647Ollama sampling seed. ComfyUI provides fixed/increment/decrement/randomize.
temperatureFLOAT0.700–2Lower is more focused, higher is more varied.
max_tokensINT5121–16384Maximum generated tokens (Ollama num_predict).
context_sizeINT4096512–131072Context window (Ollama num_ctx). Larger sizes use more memory.
system_promptSTRINGOptional system instruction; leave blank to use the model's normal behavior.
thinkingCOMBOOverride thinking for models that support Ollama's think option.
keep_aliveCOMBOHow long Ollama keeps the model in memory. 0 unloads; -1 keeps indefinitely.
image_formatCOMBOJPEG sends less data; PNG preserves exact text and fine details.
image_max_sideINT1024256–4096Resize large reference images before sending them to Ollama.
jpeg_qualityINT9050–100JPEG quality only; ignored in PNG mode.
max_imagesINT81–32Safety limit across all images, including batches and lists.
timeout_secondsINT30010–3600Maximum wait time for Ollama to generate its answer.
cache_modeCOMBOUse ComfyUI caching for speed, or force an Ollama call on every queue.
imagesoptIMAGEOptional Load Image, IMAGE batch, or IMAGE list. Requires a vision model.

Outputs (1)

NameTypeDescription
ResponseSTRING—