Katsumend

AI is an exploding area and the openness of the community has been amazing. I am happy to answer any questions as this is a hobby of mine and I want to post some of the work I enjoy creating. It wouldn't be possible without such an amazing open source community.

Here's a quick QA for commonly asked questions!

What tools do you use?

I use Stable Diffusion 1.5 and AnimateDiff to create animations with ComfyUI, and for still images I will use Stable Diffusion SDXL with Automatic1111. I process everything locally on a used and happily undervolted 3090 GPU.

Update 08/2024: Have started using Flux by Black Forest Labs and it blows everything out of the water. I am having to do a lot of photobashing with photoshop after the base generation (initial models pretty censored) but it is incredibly coherent.

Can you share your animation workflow?

Sure! I have everything posted on my CivitAI account for now:  https://civitai.com/models/254494?modelVersionId=603785

Do you take commissions?

I am doing this strictly as a hobby I enjoy with no strings attached, but I am open to any suggestions for content and let me know what you would like to see more of! I do have a few of the animations listed for $1-$2, so if you want to support content of one type or another or just want to support my DA Core account (required for posting mp4 videos here) feel free to check these out.

Can I repost/repurpose any of your content?

Absolutely! I'd appreciate a link to the original content but would love for you to share.

Got ideas for me or LORA requests? Would love to hear from you.