wangbo/ComfyUI-Manager
1
0
Fork 0
mirror of https://github.com/Comfy-Org/ComfyUI-Manager.git synced 2026-04-06 08:36:41 +08:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity

Adding 'comfy-vllm' custom node

Browse Source
This commit is contained in:
t 2026-03-20 15:00:16 -06:00
parent be5e019ec5
commit 96ffcbd0be
1 changed files with 10 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
custom-node-list.json
View File

@ -36243,6 +36243,16 @@
"install_type": "git-clone",
"description": "ComfyUI integration for Meta's SAM3 model enabling open-vocabulary image segmentation using natural language text prompts, with automatic model download, geometric refinement, and flexible confidence thresholds."
},
{
"author": "oathstudio",
"title": "Local vLLM Prompt Node",
"reference": "https://github.com/OATH-Studio/comfy-vLLM",
"files": [
"https://raw.githubusercontent.com/OATH-Studio/comfy-vLLM/refs/heads/main/vllm_node.py"
],
"install_type": "git-clone",
"description": "https://www.theoath.studio/projects/comfy-vllm-node Generates Stable Diffusion prompts using a locally running vLLM server. Supports {wild|card} expansion, a prefix field for quality tags, auto model detection via /v1/models, live preview on the node face, and configurable retry logic. No API keys or internet connection required. Wire the single output directly into CLIPTextEncode."
},
{
"author": "pznodes",
"title": "ComfyUI-SAM3DBody",