[PR #2658] [CLOSED] Add ComfyUI GLM-OCR #2667

New issue

Closed

opened 2026-10-28 21:11:39 +00:00 by bsakaguchi · 0 comments

bsakaguchi commented

2026-10-28 21:11:39 +00:00

Owner

📋 Pull Request Information

Original PR: https://github.com/Comfy-Org/ComfyUI-Manager/pull/2658
Author: @Dangocan
Created: 3/2/2026
Status: ❌ Closed

Base: main ← Head: add-comfyui-glm-ocr

📝 Commits (1)

d769149 Add ComfyUI GLM-OCR node

📊 Changes

1 file changed (+761 additions, -504 deletions)

View changed files

📝 custom-node-list.json (+761 -504)

📄 Description

New custom node: ComfyUI GLM-OCR

Repo: https://github.com/Dangocan/comfyui_glm_ocr

Adds loader and inference nodes for GLM-OCR (zai-org/GLM-OCR), a 0.9B vision-language model for document understanding.

Nodes added:

GLM-OCR Model Loader — scans all registered ComfyUI checkpoint directories for HuggingFace model folders
GLM-OCR Run — runs inference with task prompt selection (text, formula, table, description) and custom prompt support

Requirements:

transformers >= 5.3.0 (install from git until next stable release includes glm_ocr architecture)
PyTorch + CUDA recommended

_{🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.}

## 📋 Pull Request Information **Original PR:** https://github.com/Comfy-Org/ComfyUI-Manager/pull/2658 **Author:** [@Dangocan](https://github.com/Dangocan) **Created:** 3/2/2026 **Status:** ❌ Closed **Base:** `main` ← **Head:** `add-comfyui-glm-ocr` --- ### 📝 Commits (1) - [`d769149`](https://github.com/Comfy-Org/ComfyUI-Manager/commit/d7691498d2a87eca5227c06518935b18bcd087ea) Add ComfyUI GLM-OCR node ### 📊 Changes **1 file changed** (+761 additions, -504 deletions) <details> <summary>View changed files</summary> 📝 `custom-node-list.json` (+761 -504) </details> ### 📄 Description ## New custom node: ComfyUI GLM-OCR **Repo:** https://github.com/Dangocan/comfyui_glm_ocr Adds loader and inference nodes for [GLM-OCR](https://huggingface.co/zai-org/GLM-OCR) (zai-org/GLM-OCR), a 0.9B vision-language model for document understanding. **Nodes added:** - `GLM-OCR Model Loader` — scans all registered ComfyUI checkpoint directories for HuggingFace model folders - `GLM-OCR Run` — runs inference with task prompt selection (text, formula, table, description) and custom prompt support **Requirements:** - `transformers >= 5.3.0` (install from git until next stable release includes glm_ocr architecture) - PyTorch + CUDA recommended --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>

bsakaguchi

2026-10-28 21:11:39 +00:00