Open to work · VFX & experiments

45 of 3,062 videos

Instead of checking my phone first thing, I set up an agent to make a "morning newspaper". It prints while I sleep. I used grokbot @bot to pull from my calendar and email I made it available if you wanna try it 👇

Karen X. Cheng1MX

up next fabric/organic material experiments with Astra stay tuned

Fable 5.1 v GPT- 6 Astra im v impressed

Testing Veo 3- Looping prompt below 👇

🎥👩‍🎨⚗ In studio Paranormal - We are developing pipeline for use of AI in movies and games. If you want to help us build these future techniques, let us know! We don't accept any betatesting now, but we are open for investment or development collab🤗

Jakub Javora172KX

Testing Veo 3- Transitions pushing the limits of Veo 3 and i think i may have found an edge case!! I'm having a hard time getting the woman to actually hit the ball without disappearing behind it... so so close though will share the prompt and JSON shortly

Not a single weak character 😭 Made with Pollo Recast by @itsPolloAI

Ciri60.1KX

fun experiment creating my Ai stylist, Sally👚✨ i used Codex + @VivixLabs_HQ to bring her to life from a character image, then asked her to style me for an event very interesting to see how it's able to reliably communicate what outfits i should go with test it here ⬇️

Made this from just 2 photos using Seedance 2.0. Will post full tutorial tomorrow @openart_ai

Karen X. Cheng41.9KX

The fancams are saved. The bias moments are bookmarked. So why is that edit STILL not finished? 😭 The CapCut plugin is coming soon to ChatGPT. CapCut World brought leading creators and OpenAI together to explore new AI-powered video creation workflows.

Ciri38.1KX

Swapped the Raindance trend characters for Denji and Reze and honestly, this goes hard. 🔥 Made with Pollo Recast @itsPolloAI same video, totally different vibe.

Ciri37.2KX

Full video here: Hat girl - new result from our research of Paranormal's animation/rotoscopy/stylization solutions. We are gradually improving our pipeline for this purpose 🧑‍🔬

Jakub Javora36.5KX

Seedance 2.5 neck isolation expression test

Zeto36.4KX

AI video creation just got more interesting 👀🔥 Story Cutz is now open to everyone, giving creators a new way to turn simple prompts into scroll-stopping videos. Built around prompt engineering and what makes content engaging, it’s designed to help bring your creative ideas to life. One prompt cou

Ciri18.5KX

Seedance 2.5 in 1080p is now available at 50% OFF exclusively on Pollo AI. Prompt: SCENE CONTEXT A first dragon flight. A nervous first-time girl rider in white-silver armor, sits in the saddle of a colossal opalescent dragon perched at the cliff's edge. She barely finishes her nervous little spe

You don’t have to be on camera to have your own online persona. 👀 Create a character with Pollo AI Influencer on @itsPolloAI and bring it into trending videos with Pollo Recast. A little imagination can go a long way. 🔥

One tiny change in character design can completely change the vibe of your scene. 👀🎬 Experimenting with @flovaai’s High-End Character Face Design Skill to create AI characters that actually feel like movie leads. The character sheets are a nice touch, too. ✨

Ciri11.5KX

I've been playing with Krea's new image model, Krea 3, and I'm loving how fast it is! For me, the faster I can experiment, the more ideas I can explore. But of course, quality matters just as much. Love having both!

Gizem Akdag10.3KX

This new model is so sweet! Just tried fal's new post-trained video model, FLUX 3 Max. It's incredibly fast and the quality compares to Seedance 2.5! 10 seconds of video generated in just around 12 seconds.

Gizem Akdag8.8KX

Omni Flash is dangerously close to becoming the model you outgrow before you master it. And I say that as someone who just burned a ridiculous amount of credits pushing it way past what I thought it could do. I wanted to see if I could use Omni Flash to build a realistic UGC-style beard grooming v

Chuzzy‼️| AI Creative Director8.3KX

Iris had a destination in the storyboard, but the Cloud Observatory was missing a scene reference. Flova 1.5 spots the gap and generates a shared location image featuring a copper-and-glass dome, connected platform, entrance, and clouds. Now you can preview how everything fits together before gene

Prince of Persia gameplay concept with Seedance 2.5 on @itsPolloAI Prompt: Third-person fantasy action-adventure RPG. Parkour, traversal, environmental puzzles, cinematic combat, Sands of Time abilities. Seamless playable gameplay — not a movie trailer. QUALITY LOCK (highest priority): Look like a

quick experiment w/seedance 2.5

Seedance 2.5 vs Kling 4.0 Flash dance test