Nodes Browser
ComfyDeploy: How Recognize Anything Model (RAM) for ComfyUI works in ComfyUI?
What is Recognize Anything Model (RAM) for ComfyUI?
This is an image recognition node for ComfyUI based on the RAM++ model from [a/xinyu1205](https://huggingface.co/xinyu1205). This node outputs a string of tags with all the recognized objects and elements in the image in English or Chinese language. For image tagging and captioning.
How to install it in ComfyDeploy?
Head over to the machine page
- Click on the "Create a new machine" button
- Select the
Edit
build steps - Add a new step -> Custom Node
- Search for
Recognize Anything Model (RAM) for ComfyUI
and select it - Close the build step dialig and then click on the "Save" button to rebuild the machine
Recognize Anything Model (RAM++) for ComfyUI
Image Tagging and Captioning
The counterpart to Segment Anything Model (SAM)
This is an image recognition node for ComfyUI based on the RAM++ model from xinyu1205.
- https://huggingface.co/xinyu1205/recognize-anything-plus-model
- https://github.com/xinyu1205/recognize-anything
- This node outputs a string of tags with all the recognized objects and elements in the image
- 3 different models.
- RAM and RAM++ outputs tags in English and Chinese language:
- tag2text outputs image tags and an image caption at the same time. It also takes user specified tags to be considered in the output:
Installation
Git clone this repository inside the custom_nodes folder or use ComfyUI-Manager and search for "RAM".
ℹ️ In order to make this node work, the "ram" package need to be installed. To do so, open a terminal inside the python_embedded folder within your ComfyUI installation:
python.exe -m pip install git+https://github.com/Hangover3832/recognize-anything.git
Furthermore you need to download the RAM, RAM++ and tag2text models and place it in the /ComfyUI/models/rams/ folder or use the ComfyUI-Manager model downloader. You can also configure the location in 'extra_model_paths.yaml' in the Confyui folder.
Updates
- Added RAM and tag2text models.
- Support for the 'extra_model_paths.yaml' configuration.