SandyZL1 @SandyZLSmith

also...some of this is real footage.... 😀

@

57 years ago

0 0 0 0 0

My Popeye short film went from 10K to 60K overnight! Thanks to everyone who watched, commented, and shared. The comments keep saying “consistent” and “doesn’t look AI.” I’ll take it! 🔥

JSFILMZ @JSFILMZ0412

4 days ago

Pro Tip: Someone asked how I pulled off a kissing scene in my new Seedance 2.5 short film. It’s easier than you think. Use a proxy object.

26 14 202 350K 175

Perfect finger sync 👌 · Suno for the music · Three.js in a single HTML file to turn MIDI into 3D · One for the images · Seedance 2.5 for the video conversion All the prompts, including the HTML, right here 👇

TechHalla @techhalla

a day ago

fingers finally hit the notes with AI here's the Magnific workflow I'm using for this 👇

8 7 81 11K 46

98% OFF. Just $0.29 for your first month of Dreamina Basic. We’ve teamed up with 1,000+ creators to bring you our lowest price ever. Start creating with Seedance. Limited time only. #DreaminaOnly29Cents #DreaminaPartner #DreaminaAI #Seedance25 #Seedance2

could you think of a better way to celebrate 41 new followers from a 1,700,000 view video?

seeksteve @seeksteve

6 days ago

okay, i'm listening

106 2K 25K 1.6M 6K

Still buzzing from the Austin @austinaifilm ! 🎬 We were honored to join as the presenting partner and team up with the brilliant @PJaccetturo to host a masterclass on pushing the boundaries of cinematic video with Dreamina AI. PJ’s deep dive into Nexus—our Dreamina original series—showcased exactly what our platform can do when placed in the hands of a true visionary. From seamless prompting to cinematic consistency, the future of storytelling was on full display. Huge thanks to the festival organizers and the incredible creators who packed the room. We can't wait to connect with the future of filmmaking!. ⚡️

keyboard_arrow_left Previous keyboard_arrow_right Next

okay, i'm listening

Science girl @sciencegirl

6 days ago

This robotic mouth physically recreates human speech using an air pump for lungs and moving silicone parts instead of digital audio or text-to-speech software

489 233 4K 3.1M 1K

Roadster x.com/i/broadcasts/1…

krea 3 just dropped and it is the best all-around image model on the market today. i had early access and feel that is has a rare combination of everything ai creators love about other top models: - world understanding of GPT Image 2.5 - soul and creativity of midjourney - image editing power of nano banana pro the images attached were run on Krea 3 Fast. there are two qualities levels above that: high and ultra. the fact that this prompt generate those two images shows you how well this new Krea model can reason multiple competing concepts into one cohesive output. big shout out to the @krea_ai team! i ran some other tests that i'll post here soon. one is especially helpful for ai video storyboarding. > krea 3 fast prompt: "1970s movie still at the secret meeting, nostalgia, reptilians run the town, memories, ominous, criminal activity, dreamcore, liminal, indoors, charleston sc, kinetic energy. gritty realism"

keyboard_arrow_left Previous keyboard_arrow_right Next

Krea @krea_ai

a week ago

today we open the beta for Krea 3, a new frontier for image editing. - end-to-end 2k edits in under 8s. - matches Nano Banana Pro or GPT Image 2.5 quality. - bounding box control and precise multi-turn edits. learn and get access 👇

217 233 2K 524K 1K

"Church bells are ringin' a sweet new sound..."🔔🔊

Heavy Pulp @heavypulp

2 weeks ago

Kinda Wild - Fragments from a forgotten American history 🇺🇸

255 764 3K 219K 930

구글 제미나이 4 아르곤(Gemini 4 Argon) 출시되자마자 모션 그래픽 생성으로 성능 테스트를 해봄. (결과물은 위 20초 영상 참고) bgm, 모션 그래픽 전부 제미나이4 argon 으로 만듬. 기존 플래그십 모델들(솔 6.1, 아스트라 6, 페이블 5.1, 오퍼스 5.5, 제미나이 3.8)과 비교해 보며 굴려본 솔직한 체감 후기 1. 체감 티어 비교 - 이전 세대인 제미나이 3.8보다는 확실히 체감될 정도로 좋아짐. - 솔(Sol) 6.1보다도 한 단계 우위에 있는 느낌. - 아스트라(Astra) 6, 페이블(Fable) 5.1과는 이제 거의 비등비등한 수준까지 바짝 따라붙었음. - 다만 여전히 넘사벽인 오퍼스(Opus) 5.5급의 정교함까지는 아직 도달하지 못한 느낌. 2. 'AI 슬롭' 극복이 관건 그냥 일반적인 프롬프트로 대충 뽑아달라고 하면 특유의 뻔한 AI 슬롭(양산형 느낌)이 강하게 남. 연출 의도, 모션의 가감속(Easing), 비주얼 디테일을 빡빡하게 지정해 줘야 비로소 영상처럼 제대로 된 완성도가 나옴. 프롬프트 디테일 의존도가 꽤 있는 편. 3. 속도와 개발 활용도 일단 생성 및 응답 속도가 상당히 빠름. 개발 성능도 테스트해 보니 기대 이상으로 준수해서, 최고난도의 복잡한 아키텍처 설계가 아니라면 일상적인 코딩 작업이나 프로토타이핑 개발 용도로는 가성비 좋게 굴리기 충분해 보임. 더 여러 환경에서 굴려봐야겠지만, 속도 빠르고 개발·제작 보조용으로 밸런스를 꽤 잘 뽑아낸 모델임. 일단 지금 gpt 너무 느려터지고 성능도 떨어진 거 같아서 취소하고 제미나이를 업그레이해서 쓸까 생각중.

10,000. July of last year, after almost a decade stuck under 1,000, I wrote that your support meant everything to me. Today there are ten thousand of you. My Imaginary Beasts, I need you to know what this number carries. It carries 3 a.m. prompts and mornings I didn't feel like an artist at all. It carries the doubt. Every post, every single time. It carries the hardest months of my life. And every one of those days, you were here. With a reply. With a piece in a challenge. With a message I didn't expect. I still don't know if I'm good enough. But I know this isn't a following anymore. It's a friendship, a confidant, a family. I'm not making a living from my art yet. But I dream of telling my stories and providing for my little one by doing what I love, and 10,000 of you feels like a real step toward it. Thank you. All 10,000 of you. I'm not stopping. One day, one piece at a time. -Toshi 🧡

Claude Next Model :) its over for image/video gen , if you are not impressed with this wait for two image gen output that will look that it was shot on camera but purely coded never thought ai will get replaced by ai

Chetaslua @chetaslua

2 weeks ago

🚨 Claude Next is being tested on claude code and i thought it will take a month to make image and video gen model obsolete i was wrong Behold the supremacy , fully coded ,this akes even Opus 5.5 look primitive I will upload more test different types its SOTA in every f#ing

66 73 2K 512K 790

Claude has Taste , anthropic has cracked something internally this use images and music not coded and everything else is coded and also entire art direction , video everything was claude choice Time : 2.5 hours, Research : it was free to do its own research

someone found the footage of what actually happened to Kelly Clarkson and that mechanical bird inside the Brooklyn small business

Kelly Clarkson @kellyclarkson

2 weeks ago

Cool, cool. Sure, it wasn’t for sale. That’s the narrative Art of Play is gonna go with 👍 so the whole conversation we had when I asked you if it was for sale whilst pointing to the price tag hanging on the wall with the title Singing Bird didn’t happen as you elevator eyed me

11K 9K 173K 11.7M 8K

Kinda Wild - Fragments from a forgotten American history 🇺🇸

Just want to do another shout out to the lovely people and platform that is @AskVenice which I’ve been recently using as my main go to generate the visuals for these latest pieces. Many times, the moderation/prompt refusal is not from the model itself, but instead the platform you are using and the extra moderation layers they've added between you and the model. Pretty eye opening really. @AskVenice lets me actually go “Kinda Wild” and freely create without battling against extra layers of moderation. Been really enjoying it!

Heavy Pulp @heavypulp

2 weeks ago

Kinda Wild - Fragments from a forgotten American history 🇺🇸

255 764 3K 219K 930

Tired of wasting Seedance 2.5 credits? Here is the ultimate workflow to save your credits in Seedance 2.5. By using TopView AI 3D Builder, you can lock in your exact camera movements in a 3D clay draft first, letting you completely "one-shot" your text-to-video prompts. No more guessing the camera movement. Just perfect previs. 🎥🔥 Watch the full tutorial below.

TopviewAI @TopviewAIhq

3 weeks ago

Introducing 3D Builder in Topview Film Studio. Turn one sentence or one reference image into an editable 3D previs scene, adjust the set, control camera angles and animation, then generate your AI video with more direction and fewer wasted attempts. #TopviewAI

19 7 67 11K 26

Dreamina Originals Projects Are Rolling Out As Dreamina AI's first professional film and series content label, Dreamina Originals provides creators with computing power, technical support, AI creative tools, and premium distribution resources. Recently, projects under Dreamina Originals have been rolling out across both film and series formats, with more creator collaborations set to launch on multiple platforms in the coming weeks: LEXIKON @chaospharmacy Project Andromeda @SoCalJeepDude Miss Holmes @roshxmachines BACKYARD GALAXY @Cinemadrien TINKUY @ARCANOCLUB3 The Last Necromancer @SpellFilms No Wrong Answers @ Jimmy Woolley Run Rabbit @ Brad Minnich Black Vein Rising @ Allan Dogheon @ Michael Fisk. We look forward to joining hands with creators to shape outstanding content and great IP for the AI era. #dreaminaoriginals #dreaminaai #AIGC

keyboard_arrow_left Previous keyboard_arrow_right Next

when a local remodeling company says they don’t care about the design, i submit this for approval in 8k 😂