From 96ffcbd0bef509ffb47a3f9404c2aa31256ae3e5 Mon Sep 17 00:00:00 2001 From: t Date: Fri, 20 Mar 2026 15:00:16 -0600 Subject: [PATCH 1/3] Adding 'comfy-vllm' custom node --- custom-node-list.json | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/custom-node-list.json b/custom-node-list.json index b86e95f9..e4ad951e 100644 --- a/custom-node-list.json +++ b/custom-node-list.json @@ -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", From b770f27099a391141c884ebe21d1fa49dd5cff99 Mon Sep 17 00:00:00 2001 From: t Date: Fri, 20 Mar 2026 15:02:05 -0600 Subject: [PATCH 2/3] Adding 'comfy-vllm' custom node, title update --- custom-node-list.json | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/custom-node-list.json b/custom-node-list.json index e4ad951e..c4f6fc7b 100644 --- a/custom-node-list.json +++ b/custom-node-list.json @@ -36245,7 +36245,7 @@ }, { "author": "oathstudio", - "title": "Local vLLM Prompt Node", + "title": "comfy-vllm", "reference": "https://github.com/OATH-Studio/comfy-vLLM", "files": [ "https://raw.githubusercontent.com/OATH-Studio/comfy-vLLM/refs/heads/main/vllm_node.py" From a2aace6a233c0a8ec98c16727e9cc92929e5f558 Mon Sep 17 00:00:00 2001 From: t Date: Sat, 21 Mar 2026 23:12:30 -0600 Subject: [PATCH 3/3] Adding comfy vllm, and comfy lora iterator nodes to custom node list --- custom-node-list.json | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) diff --git a/custom-node-list.json b/custom-node-list.json index c4f6fc7b..a612fa9d 100644 --- a/custom-node-list.json +++ b/custom-node-list.json @@ -36244,7 +36244,7 @@ "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", + "author": "oath-studio", "title": "comfy-vllm", "reference": "https://github.com/OATH-Studio/comfy-vLLM", "files": [ @@ -36253,6 +36253,16 @@ "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": "oath-studio", + "title": "comfy-lora-iterator", + "reference": "https://github.com/OATH-Studio/comfy-LoRA-iterator", + "files": [ + "https://raw.githubusercontent.com/OATH-Studio/comfy-LoRA-iterator/refs/heads/main/lora_iterator.py" + ], + "install_type": "git-clone", + "description": "https://www.theoath.studio/projects/comfy-lora-iterator A ComfyUI node that automatically steps through every LoRA in a directory on each generation run. Increment, decrement, randomize, or hold fixed. No rewiring. No manual switching. Queue and walk away." + }, { "author": "pznodes", "title": "ComfyUI-SAM3DBody",