The camera motion in Imagine is insanely next-level...woah! I've... been exploring a few prompts with the token 'image sequence'show more

AI generated QR codes have been on fire lately.... But AI QR codes combined with augmented reality is next level. Try scanning the image in the next tweet 🤯show more

Blade Under Moon Midjourney + Nano Banana Pro +... GPT Image 2 + Seedance 2.0 Created the character image in Midjourney, made a few edits with Nano Banana Pro, generated the storyboard with GPT Image 2 and finally brought it to life in Seedance 2.0 You can find the prompts in the comments.show more

💃AI Dance Motion Reference Sheet Turn a single image... into a complete dance sequence with AI. Prompt in comments 👇show more

So how is the winter storm where you are?... I’m in Kitty Hawk. Been here for a few hurricanes but this is next level wow.show more

🇨🇳 Another great Chinese Model, OmniHuman-1.5 from ByteDance Turns... 1 image plus a voice track into expressive avatar video by pairing a System 1 and System 2 inspired planner with a Diffusion Transformer, Produces coherent motion for over 1 minute with moving camera and multi character scenes. Most avatar models move to the beat of the audio but miss meaning, so gestures feel generic and emotions feel shallow. The fix here is a Multimodal LLM planner that listens to the speech and drafts a structured plan describing intent, emotions, beats, and high level actions, which gives the motion engine clear semantic targets instead of only rhythm. The motion engine is a Multimodal Diffusion Transformer that fuses the plan with audio, the single reference image, and optional text prompts, then synthesizes continuous body, face, and head motion that matches both words and tone. A key trick is a Pseudo Last Frame, a synthetic target that summarizes the next expected state, which stabilizes fusion across modalities and keeps motion consistent over long spans. From just 1 image and speech, the system outputs speaking avatars with synchronized lips, context aware gestures, and continuous camera movement, and it also supports multi character interactions without manual choreography. Reported results show strong lip sync accuracy, high video quality, natural motion, and close match to text prompts, and the same setup works on nonhuman characters too.show more

Posted a full preview of this in my discord,... here's a snippet! This is the culmination of all the stuff I've been learning the last few months. There's a Daz3d model in there being driven by motion capture data, with a physics driven hair rig and some basic jiggle on the boobs.show more

ok, this is crazy. LumaLabs AI just unveiled Ray... 2, a new AI video model, the motion and camera work are incredible. Here are 15 Raw clips with prompts👇:show more

This video was created entirely within Gemini CLI... ...... in under 10 prompts 🪄 With a few detailed prompts you can create high quality motion videos thanks to the Remotion Agent Skill. 👇Give Agent Skills a try today in Gemini CLI!show more

Amazing animation created entirely with @Grok Imagine. No other... AI delivers this level of video quality in just 20 seconds. Grok Imagine is the worlds fastest AI image and video generator.show more

Bleu: one continuous shot anime action with dynamic camera... movements. Character: Midjourney v8.2 preview Storyboard: GPT Image 2 Video: Seedance 2.0 You can find the prompts in the replies.show more

This is what happens when a pocket-sized camera takes... car shots to the next level. 🚗⚡ The Osmo Pocket 3 delivers smooth motion, crisp details, and cinematic framing 📹: daniel._.gtshow more

This is what happens when a pocket-sized camera takes... car shots to the next level. 🚗⚡ The Osmo Pocket 3 delivers smooth motion, crisp details, and cinematic framing 📹: daniel._.gtshow more

What if her next opponent was much stronger? Midjourney... v8.2 + Gpt Image 2 + Seedance 2.0 Prompts in the replies.show more

AI is going to take your job pt. ii... I made this entire motion graphics sequence in 6 hours only using After Effects. Over 100 layers. 4-5 prompts. Vibe video editing is the future.show more

Woah! Imagine if this is what cinema looks like... in the future 🤯show more

After Effects to the next-next level is possible. Learn... advanced Expressions and code with ChatGPT. Develop Responsive Motion Graphics Systems. Learn to design and problem-solve when developing Responsive Solutions. Link in the next comment.show more

the AI slop era is officially over Kling 3.0... in Arcads reads prompts like a human director-> minimal text turns into complete scenes with perfect camera work, lighting, depth (The realism is scary good) Tutorial below + prompts:show more