A major missing piece in the ComfyUI interface has been the in-ability to easily manage multiple workflows as you work. Until now I had been running two tabs in my browser, normal tab and incognito tab which allowed me to have two workflows open so I could test and update the other. There was no easy way to manage this until now with Comfyspace ComfyUI Workflow Manager. It let’s you seamlessly switch between multiple different workflows with easy. Create new workspace and load your ComfyUI Workflows, give them a name so you can easily locate when you want to switch. Access and switch between ..read more

Stable Video Diffusion as I covered in an earlier post about its release (Stable Video Diffusion using ComfyUI) is rapidly taking over the internet but not just that also my workflow. I find myself playing around with various Image-to-Video setups and so far one of my favourite is a modified version from Nuralunk. The workflow uses SVD + SDXL model combined with LCM LoRA which you can download (Latent Consistency Model (LCM) SDXL and LCM LoRAs) and use it to create animated GIFs or Video outputs. There some Custom Nodes utilised so if you get an error, just install the Custom Nodes using Comfy ..read more

Magnific.AI has quickly become one of my favourite image upscalers thats super easy to use. There are a few settings you can tweak and start upscaling your images. If you are wondering how to get started then check out my earlier post Magnific.AI Upscaler where I walk through the interface and show a few samples. I also posted a video on this which got a lot of comments: many people don’t like that its paid service and does not offer trial. However, I can understand with the uptake in GPU usage (Nvidia shares sky-rocketing) it may be a sure way to run out of money if you are starting a service ..read more

Incredible developments in the AI space in the last few weeks. I cannot find enough hours in my day to try new things and write about them. However Magnific.ai is one of those tools that I’m super excited about and have been playing around with it for a few days. Magnific is romanian word for Magnificient, is truly fitting of this AI based Image upscaler. UX of the Magnific Upscaler – EditorMagnific.AI User Interface The UX is very clean and well designed, not complicated jargon or technical sliders that you’d need PHD to understand. The interface is very intuitive to use. It is called the Edi ..read more

Last week’s hottest news other than the drama unfolding at Open.AI with Sam, this was a very positive news when Stability.AI announced that they have released Stable Video Diffusion (21st November 2023). A few days later the first two models are available for experimental/evaluation use (ie. Non-commercial), so of course then we wait for the community to take this to next level and make it usable on your own PC. We have two models available: Stable Video Diffusion – As its referred to as SVD, its able to produce short video clips from an image at 14 frames at resolution of 576×1024 or 1024×57 ..read more

Oddly enough seeing a lot of live LCM popping up everywhere especially Krea.Ai which has implemented it already got me further curious and I somehow discovered Krita as a result. Krita is an standalone open source image editing software, so its free and feature rich as I’m exploring, it also has a plug-in called Krita AI Diffusion. This plug-in is awesome as its super easy to get it working. I was able to set this up with my existing ComfyUI installation and use it to generate images. Setup Download and install Krita from krita.org Next grab the Kirta AI Diffusion and download the zip file ont ..read more

If you are new or even have been using ComfyUI you might have seen or wondered how to manage or make the noodles (technically called links) in our workflow appear neater. OCD part of your break might like to nicely organise the workflow of ComfyUI so it looks neat and clean and well balanced. Well until you know you don’t know, so let’s see how to manage those noodles (aka links) in your ComfyUI interface. First thing you need to do is go to your settings via ⚙️icon (assuming ComfyUI is up and running) . Next scroll down the list of options (you may have many if you have custom nodes installe ..read more

Latent Consistency Model (LCM) have recently exploded over the internet and all the rage right now is about getting closer to real-time image generation where the image is generated and re-generated as you update your prompt. Recent releases has come out with LCM models and LoRAs which you can use for creating images that only require as little as 4 steps to create. This means that your images are produced much faster and in my case I have seen them appear in under one second. If you want to learn more about my custom PC setup check out my post on this. Models LCM SDXL – Full weight for Latent ..read more

Midjourney just release their latest Upscaler for v5 images that can take your standard (1:1) 1024px image to 2x and 4x resolution while maintaining the details and creating artifacts. Well that’s the concept so one needs to explore this and see what is the big difference and it it really good? The PNG files produced a certainly much larger. Now to ensure your retrieve the full size PNG and not the one Discord will show you make you click that Open in Browser link that will load the full size PNG which you can download. For the sample image that I analysed the following were the file sizes, ce ..read more

In this post I would like to share some of the keywords that I have used and found influence the composition which comprises of the Camera Position (distance of camera from subject) and the Camera Angle (where the camera is place relative to the subject). Although this post is solely focusing on Stable Diffusion XL (SDXL) the same can be applied to Stable Diffusion (SD), Midjourney, Adobe Firefly, or Leonardo.ai Firstly to source the keywords we search the web to find a good resource and the site I found most useful was https://www.studiobinder.com/blog/ultimate-guide-to-camera-shots/ and vari ..read more