openAI suite, String suite, Latent Tools, Image Tools: These custom nodes provide expanded functionality for image and string processing, latent processing, as well as the ability to interface with models such as ChatGPT/DallE-2. NOTE: Currently, this extension does not support the new OpenAI API, leading to compatibility issues.
Kindly tell me if the problems are fixed now
Extra nodes to be used in ComfyUI, including a new ChatGPT node for generating natural language responses.
ComfyUI is an advanced node-based UI that utilizes Stable Diffusion, allowing you to create customized workflows such as image post-processing or conversions.
Download the zip file. Extract to ..\ComfyUI\custom_nodes. Restart ComfyUI if it was running (reloading the web is not enough). You will find my nodes under the new group O/....
{ "autoUpdate": true, "branch": "main", "openAI_API_Key": "sk-#################################" }
config.json
set "autoUpdate": falseThis node harnesses the power of chatGPT, an advanced language model that can generate detailed image descriptions from a small input.
config.json
fileThis set of nodes adds support for string manipulation and includes a tool to generate an image from text.
This node generates an image based on text, which can be used with ControlNet to add text to the image. The tool supports various fonts; you can add the font you want in the fonts folder. If you load the example image in ComfyUI, the workflow that generated it will be loaded.
"node soup" which is a collection of different values categorized under different terminologies that you can use to generate new prompts easily
this node allow you to select 1 latent image from image batch for example if you generate 4 images, it allow you to select 1 of them to do further processing on it or you can use it to process them sequentially
This node is a variant of the original LatentUpscale tool, but instead of using width and height, you use a multiply number. For example, if the original image dimensions are (512,512) and the mul values are (2,2), the result image will be (1024,1024). You can also use it to downscale by using fractions, e.g., (512,512) mul (.5,.5) → (256,256).
This node is a variant of the original LatentUpscale tool, but instead of using width and height, you use a multiply number. For example, if the original image dimensions are (512,512) and the mul values are (2,2), the result image will be (1024,1024). You can also use it to downscale by using fractions, e.g., (512,512) mul (.5,.5) → (256,256).