Who the F cares‽ It is the collection of clips edited together and the ability to just enjoy the “entire” clip for what is intended, “humor” that is what is germane! And I do not GAF if it was created with: • AI •Stable Video Diffusion •OpenAI Sora •Luma Dream Machine •Kaiber •Pika •Runway Gen-2 •Midjourney •Deforum •Stable Diffusion •EbSynth •Disco Diffusion •OpenAI DALL·E •OpenAI CLIP •D-ID •Reface •Synthesia •DeepFaceLab •Runway ML •StyleGAN •GAN-based Face Reenactment •DeepFake Autoencoders •IBM Watson Trailer AI •LSTM Script Generators •DeepDream •DALL·E •Midjourney •Stable Diffusion •Adobe Firefly •Runway •Processing •p5.js •TouchDesigner •Max/MSP/Jitter •Blender •Adobe Photoshop •Adobe Illustrator •CorelDRAW •Painter •Procreate •MacPaint •Deluxe Paint •Paintbrush •Amiga HAM graphics modes •Sketchpad •Pen plotter art (HP, CalComp) •Oscilloscope vector art •Early CAD systems adapted for art •ASCII art •FORTRAN /BASIC/ALGOL graphics routines •Line-printer art •Fractals (Mandelbrot sets) •L-systems •Cellular automata I just want to laugh, cry, be shocked or inspired, be amazed at technique, reminisce, and enjoy creativity. What I do not want is self-appointed “𝕏 POLICE” chest thumpers, proclaiming every artisticly created, co- mingled post in the negative, as if it matters for the reason I like them. So please, stay out of feeds with that illiterate, inexperienced nonsense and let those that appreciate them, appreciate them! (And YES! I have used them all of the above! I started my “computing career” with the following…

CVPR DAY TWO/THREE Dance, Regardless — The Sixth Step — CVPR Art Gallery @CVPR Single continuous takes — no cuts. Created in-cAImera using Deforum and bespoke parameter settings. What appears as dance is actually persistence — a body negotiating time after disruption. Movement dissolves and reassembles; gestures echo through temporal slippage, evoking memory and fragility. Curator: Luba Elliot @elluba

Yes Deforum was so fun. Thanks G! Happy to be building together.

Bro I remember watching this when it came out. You’re a trailblazer. Shout out to Deforum!

A trip down memory lane... This is "Another." This film was made with early Comfy, Stable Diffusion, Warp Fusion, Deforum and early Runway Gen 1 and 2. Probably one of the first hybrid AI Live Action films ever made. I was in production in the summer of 2023. Most of my industry filmmaker friends were more open and curious on how AI could be infused. It wasn't mainstream, and most people didn't even understand how AI could be used in film production. Just new tools that could help small teams produce their vision. I have always been resourceful, and when I discovered the possibilities of these tools, I was instantly hooked. The R&D we all have done over the years is proving fruitful and AI is finally ready for primetime. Pretty soon we will be back to focusing on just stories. The tools will fade away, and all that will remain is you and your vision. So here is a remastered 4K version of a time capsuled look at a time where filmmakers could just cook without people worrying about how something was made. Keep tinkering my friends. We are right on time.

When and how did you first start experimenting with AI in your art? How has AI evolved your artistic process? i first started working with ai with dalle and photoshop neural filters, but this was more just experimentation. the first time i got truly excited about it was while i was working as a marketer, video ai models first came out. i was immediately obsessed. id spend most of the day in my office playing with deforum, and going home and leaving the computer generating all night. it was absolutely mind blowing to me. then when runway first came out i dropped deforum for that, and again most of my day at work id just be generating videos. ai started making things much easier for marketing too, especially as photoshop started integrating ai. no more hours of lassoing, i was super grateful for that lol. i basically shifted very quickly to working with my hands to working with the computer way more often. eventually i left the job after pushing back an assignment a million times since id just be making ai all day anyway.

And if you need a deforum to use then give @S4f3ty_Marc a shout and he can give you the low down on making one on @deforum_art And heres the kicker, on there you can make an audio reactive deforum using your own track Audio reactive deforum background in an sd2 animation?

Or you could have a deforum scrolling left to right in the background as your sd2 character walks in profile on the spot to give the illusion of the character walking in a deforum world. That character could be a character sheet of yourself

Interesting experiment. I have a backlog archive of Deforum videos created on @deforum_art I wondered if I uploaded a deforum video to Seedance 2 if i could have the Deforum playing in the background with me dancing badly in the foreground I'll call that a win

【LTX-2.3専用Deforum LoRAで動画生成が激変！】 👉 x.com/S4f3ty_Marc/status/204… 動画生成AI「LTX-2.3」のクオリティを劇的に高める新しいLoRAが登場しました！ 不自然なテクスチャが解消され、実写に近いリアルな質感が手に入ります。さらに最初・中間・最後のフレームを固定する「3点フレーム」手法により、ガタつきのない滑らかなアニメーション制作が可能です。 シネマティックな映像や高品質なプロモーション動画の制作に、即戦力として役立つこと間違いなしです！🚀 #動画生成AI #LTX2

This is a new real time graphics app i've been making that is able to achieve realtime warp-fusion and deforum style effects! It runs SDXL faster than any other implementation. It also has a modular vibe codable node system kinda like comfyui meets touchdesigner

Another test with my updated Deforum LoRA for LTX-2.3! Huge leap forward thanks to LTX-2.3’s improved image-to-video quality better sound. Using it with a first, middle and last frame workflow helps it morph super smoothly, and everything looks way less plasticky than the lora I made for ltx2

Testing my updated ltx-2.3 Deforum Lora with First, Middle, Last frame

I'm training an updated Deforum Lora for LTX-2.3 Has less of the plastic look from what I've seen so far.

My video entry for the Arcadian competition from @banodoco @peterom! 🎬 I love mixing old tools with new ones, so of course I had to combine Deforum LTX-2.3 — bridged together with the custom Deforum LoRA I made for @ltx_model Music from Ace-step, enhanced with some of my own audio. 🎵 Open-source models are the best way to use AI! 🚀 If you’ve got time, check out the other entries and vote for the ones you like — there’s some seriously impressive work pushing the limits of open-source. Links below ⬇️

I'd like a double deforum burger with a pint of your secret sauce poured all over it please dude.

For those that know me always knew I was a deforum fan, but I find that the most beautiful animations out there are the ones where I just sit and watch without thinking how it was done. Just watch, mind devoid of all thought.

I really want it....I have no idea how he's doing it or what it is but I want some. I said from day 1 that Deforum was never gonna die, it was always gonna morph into a more beautiful form of Deforum

This is really nice. its like Deforum on mescaline

Mixing and funperimenting with an old Deforum {d} piece with @higgsfield mixed media feature.