This workflow can make images in high definition and magnify it by 8 times without any prompts.

Thanks for the great workflows of @Mad4BBQ( https://openart.ai/workflows/profile/mad4bbq?sort=latest )

I just combine his two magnification workflows together and make some minor adjustments to achieved a good result, as well as what Magnific Ai does.

How to use:  https://www.youtube.com/watch?v=t1_Yv5ny7rU

Node required:

Please go to your 'ComfyUI\custom_nodes' directory, open a CMD prompt, then type "git clone   https://github.com/Arthurzhangsheng/Comfyui-StableSR.git " ，because it‘s not in manager now.

Models required:

Download the ckpt from HuggingFace https://huggingface.co/Iceclear/StableSR/

• Put the StableSR webui_786v_139.ckpt model into Comyfui/models/stablesr/
• Put the StableSR stablesr_768v_000139.ckpt model into Comyfui/models/checkpoints/

Basemodel:  https://civitai.com/models/4201/realistic-vision-v60-b1

Other required:

I use Gemini to read your illustration and guess the prompt word. You should have your api of gemini to make it work.Please install this node from manager.(https://github.com/ZHO-ZHO-ZHO/ComfyUI-Gemini)

First: Install Comfyui-Gemini from manager

Second: apply the api: https://makersuite.google.com/app/apikey

Third: add your Gemini api into config.json(which is in the comfyui_gemini folder),and save it.

Then restart your comfyui.