krita-ai-diffusion

Plugin for Krita I use: https://github.com/Acly/krita-ai-diffusion App I recommend to download models and manage UIs: https://github.com/LykosAI/StabilityMatrix (1) Download Krita (2) Download and install the Krita AI diffusion plugin (3) Run comfy UI using StabilityMatrix Docs for using the Krita AI plugin: https://docs.interstice.cloud/basics/ It's a really fun plugin to use!

I'm not sure I understand the request. https://github.com/Acly/krita-ai-diffusion ?

We found running a recent Intel pen tablet is nice for some applications like the full blender plugin ecosystem support, commercial and free offerings. Some treasure: https://github.com/wonderunit/storyboarder/releases https://krita.org/en/ Avoid in commercial use-case: https://github.com/Acly/krita-ai-diffusion Seems ridiculous, but the 2nd paid seat you get works well for portable non-intensive tasks: https://www.blackmagicdesign.com/products/davinciresolve The perpetual CSP or CS/EX license for iPad/MS Surface/Wacom is pretty much a necessity for the users, as in a commercial setting it is the only practical option for many use-cases (Wacom often included a free 2 year trial): https://www.clipstudio.net/en/dl/ --- Blender plugins: "Blob fusion" similar to ZSpheres with Metaballs/SDFs: https://bartoszstyperek.gumroad.com/l/ahwvli 3D Nor

Using the kontext models in Fal.ai shows you a nice slider of the before and after edits and has a button that lets you set the edited image as the new source so you can continue to make changes. Now that BFL has released a dev model, I'd love to see a Kontext plugin for Krita given that it already has one for Stable Diffusion though! https://github.com/Acly/krita-ai-diffusion

this is semi-relevant -- and I do love how technically amazing this all is, but a massive caveat for someone who's been dabbling hard in this space, (images+video) -- I cannot emphasize enough how draining text-2-<whatever> is. even when a result comes out that's kind of cool, I feel nothing because it wasn't really me who did it. I would say 97% of the time, the results are not what I want (and of course that's the case, it's just textual input) and so I change the text slightly, and a whole new thing comes out that is once again incorrect, and then I sit there for 5minutes while some new slop churns out of the slop factory. All of this back and forth drains not only my wallet/credits, but my patience and my soul. I really don't know how these "tools" are ever supposed to help creatives, short of generating short form ad content that few

The reason that Adobe can do AI gen "out of the box" is because you're paying for it (Firefly). If GIMP were to implement it, they'd probably have to go the same route as Krita and either spin up or call out to a running instance of Automatic1111 or ComfyUI. https://github.com/Acly/krita-ai-diffusion MCP would be cool, but it would be significantly harder than Blender which can represent the "world" as a formal set of expressions. MCP for GIMP would be dealing with layers of rasterized data which would mean integrating with YOLO/LLava/etc in order to make sense of it. It would be neat, but it'd be a daunting integration and potentially VERY VERY slow.

For your first point, I'd recommend using Krita (https://krita.org/) and its generative AI plugin: https://github.com/Acly/krita-ai-diffusion / https://www.interstice.cloud/

Yes, these are largely prototyping tools. I'm not fond of Invoke's "professional" pitch in particular, this workflow would feel alien for any actual creative. However AI CGI is more like 3D CGI in the sense that you have to get technical and understand what you're doing. There are a bit more competent tools in this busted-tool world if you want to get things done, e.g.: https://github.com/Acly/krita-ai-diffusion . It still a nerdy tool and has way more friction than necessary, with all this python hell (it uses Comfy as a backend, although it's somewhat automated). It's far from being as easy as Adobe's Firefly.

Are you talking about this? https://github.com/Acly/krita-ai-diffusion I tried using that but didn't have much luck. That is, I could get it to generate whole images, but none of the other tools seemed to work. I'll have to take another crack at it some time, because that looks like a workflow that I would really enjoy.

I run a pretty similar setup on an m2-max - 96gb. Just for AI image generation i would rather recommend krita with the https://github.com/Acly/krita-ai-diffusion plugin.

Me either. Acly's krita add-on takes a bit of the pain out of it for me personally: https://github.com/Acly/krita-ai-diffusion (I have not and would not try FLUX however -I don't have the hardware).

Just install Krita /s No seriously, krita has made huge improvements over the last years. Just for example there is a AI plugin that is probably the best open source tool to do ai supported graphic design (if there are better ones i'd love to hear). https://github.com/Acly/krita-ai-diffusion

I drag around a 60MB portable version of CS3 that does 99% of anything I'd need to do. I've found myself missing out on the generative AI fill train but recently discovered Krita AI diffusion, not too difficult to set up and use from a PS diehard, and pretty magical. https://github.com/Acly/krita-ai-diffusion