requests torch Pillow numpy


This is a custom node for ComfyUI that allows you to use the Recraft AI API. Recraft V3 (code-named red_panda) is a text-to-image model with the ability to generate long texts, images in a wide list of styles, including custom brand styles. It’s also possible to set up brand colors. As of today, it is SOTA in image generation, proven by Hugging Face’s industry-leading Text-to-Image Benchmark by Artificial Analysis.
Before using this node, you need to have a Recraft AI API key. To generate a key, log in to Recraft, and enter API page and hit ‘Generate’ (available only if your API units balance is above zero).
ComfyUI/custom_nodes directory.git clone https://github.com/recraft-ai/ComfyUI-RecraftAI.gitThe files should be located as ComfyUI/custom_nodes/ComfyUI-RecraftAI/*, where * represents all the files in this repo.
.\python_embeded\python.exe -m pip install -r ComfyUI\custom_nodes\ComfyUI-RecraftAI\requirements.txtcd ComfyUI-RecraftAI && pip install -r requirements.txtconfig.ini file and keep it empty in the node.This node is used to create a Recraft AI client.
This node is used to generate an image given a text prompt.
This node is used to transform an input image into an output image given a text prompt.
This node is used to remove background of an image.
This node is used to enhance an image using ‘crisp upscale’ tool, increasing image resolution, making the image sharper and cleaner.
This node is used to enhance an image using ‘creative upscale’ tool, boosting resolution with a focus on refining small details and faces.
This node is used to detect and replace background of an image according to a given text prompt.
This node is used to modify specific parts of an image according to mask and text prompt. You should use ComfyUI mask for an input mask. Note, that pixels with mask values >= 0.5 will be filled based on the prompt, while others will keep intact.
For more information about the Recraft AI API, follow the documentation.
For pricing, follow Recraft AI Pricing.