I have a previous workflow for creating text effect images with ControlNet. It works well but takes quite some work. With the advance in Stable Diffusion, you can now generate text effects directly with text-to-image!
Here are a few samples.
You will get a downloadable ComfyUI workflow with a step-by-step guide to use it.
Can you please advise of the Colab setup for this, as I’m switching between local and Colab as I’m new to Colab setup routine. I need a set of instructions to get this workflow to work in Colab, I have it working locally. But lack the experience of setting up Colab ComfyUI, Thank You
My colab notebook should work. Let me know if you experience any issues.
Hello. I really love these text effects, I am a total novice when it comes to AI and have a few questions? Is Stable Diffusion a desktop app like Photoshop? Is Controlnet a plug-in for Stable Diffusion? Do I have to buy these to gain the results shown in this article?
Thanks for sharing.
Yes, SD is a desktop app. There are options to run it online too.
Yes, controlnet is an addon for SD. You don’t need to buy the software or addons. They are all free.
this is not exact. to generate Art with SD, you normally use an user interface in the browser. But with Automatic1111, ComfyUI and others, you start a local server. this is important to have in mind, in the browser you can controll everything, make the settings and so on. after you press the “Generate” Button (or “Queue Prompt” in ComfyUI), the browser sends the settings to the server and the server runs Stable Diffusion (it’s what you see in the console window)
The server will save the generated Images in a subfolder of the server, or you can download it, that works the same way as you download an image from the internet.
If you want, you could run those servers as a server for the internet, but every user would use your Hardware (GPU) to do the calculations and the images would be stored on your Harddrive.
Have you ever seen what sora video generation AI capable of where is the stable viddiosion 😁
Yes, very impression 🙂 Like an upgraded version of SVD.
Why do the pngs from the samples up not have the comfyUI workflow in it?
Modern CDN is so smart that it sometimes strips the meta info to save a few bytes.
Never saw that at comfyui. Only at Fooocus and on A111 if you turn it off.
Does stable cascade works with 8GB VRAM. I am able to follow 90% of workflows from the website or from opeart, but I haven’t tried stable cascade yet.
This workflow goes up to 12GB on my machine.
@Pradeep Kumar
Q: Does stable cascade works with 8GB VRAM.
A: I have a RTX 2070 super with 8GB VRAM and to my surprise it was generating images, I didn’t think it would.
In my case the answer is YES!
Are there any compatible controlnet for this specific model ? Is it possible to use AnimateDiff to generate animations ?
Thanks a lot !
Not that I know of currently.
Thank you for sharing. I would like to know if there is any way to modify the font or create Chinese characters.
You can try specifying the font in the prompt. If that doesn’t work, the following method with controlnet gives you more control and will work for chinese characters.
https://stable-diffusion-art.com/text-effect/