AI fashion and beauty videos

25 of 3,062 videos

152 AI fashion and beauty videos, posted in public on X and Threads by the 14 creators who made them. Open any video to see who made it and what they used.

AI transforms middle-aged man into young woman

Hirokazu Yokohara1.1MX

AI virtual try-on from selfie and garment photos

Hirokazu Yokohara779KX

AI-only Blender desk scene test

Hirokazu Yokohara723KX

AI-modeled fantasy witch tower in Blender

Hirokazu Yokohara223KX

AI-made Blender office scene test, daytime

Hirokazu Yokohara190KX

🧵 One Image, Six Unique Videos: All with Text Prompts 🎥 One image. Six distinct stories. All by tweaking prompts. I've been loving the new Hailuo 02 video model, and its ability to follow instructions is mind-blowing. Check out these 6 examples ... 👇

AI-directed Houdini shirt-burning effect test

Hirokazu Yokohara23.3KX

experimenting, experimenting, experimentinggg midjourney + seedance in dreamina 💅

Julie W. Design21.7KX

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

AI video creation just got a serious upgrade. @pika_labs is taking AI filmmaking to the next level with Pika H3 Flex. Built for creators who want more than a good first generation, it offers up to 5 separate audio stems, support for 12 reference assets, precision editing, and 4K finishing. 15-sec

𝐍𝐚𝐯𝐞𝐞 𝐀𝐢9.8KX

OH OH, THAT'S NOT GOOD explorations continue: midjourney 8.2 preview + seedance

Julie W. Design9.2KX

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

Seedance 2.5 Optical Rack Focus Test Prompt: A high-tension optical rack focus with hard-flash illumination. The frame starts with shallow focus locked squarely on the sculptural kiss-curl and sharp eyeliner of the female model in the foreground. On beat, the focus violently racks to the background

Been playing with Pika H3 Flex, and it’s really nice for quickly testing ideas, exploring different directions, and still getting high-quality results. Here’s my little experiment!

Gizem Akdag3.7KX

🧵 One Image, Six Unique Videos: All with Text Prompts 🎥 One image. Six distinct stories. All by tweaking prompts. I've been testing the following video models, and their ability to follow instructions. - Grok Imagine 1.5 - Wan 3.0 Prime - Hailuo H3 Check out these 6 examples ... 👇

🧵 One Image, Six Unique Videos: All with Text Prompts 🎥 One image. Six distinct stories. All by tweaking prompts. I've been testing the following video models, and their ability to follow instructions. - Seedance 2.5 draft - Wan 3.0 Prime - Kling 4.0 - Hailuo H3 Check out these 6 examples ... 👇

Wan 3.0 Prime / Racing Sunbar Sweep Prompt One continuous shot, no cuts. 0-2s: hold the start frame as the woman crouches, breathing, eyes on the lens. 2-4s: the sun shifts impossibly fast: the bright rectangles of window light slide across the dusty floor toward her, dust motes rising in the beams

Seedance 2.5 Handheld Spin Test Prompt: 0-2s: a dancer in black lunges low across a white studio floor, long pale hair flung out horizontally, arms spread like wings. 2-5s: the camera is handheld and orbits with her as she spins, staying close at shoulder height, her hair whipping across the lens i

Same footage. Three completely different moods. I used the Tesseract skill from @trymirage in Codex to colour grade these PRMPT clips, then build a beat-synced sequence showing the before/afters. For me, the main appeal is being able to direct the look in plain English, with the grades, type and a

Hailuo H3 - Raw casting-tape staged as a couture test shoot Prompt: Chartreuse-yellow seamless paper, flat even studio light, locked-off camera at eye level with the faintest handheld breath, medium close-up, shallow depth of field. The performer: [📷 Image1] [📷 Image2] a Black male model in his

Playing with MP4 x Live ASCII x PRMPT

I've been a huge Magnific fan for a long time. So this result genuinely surprised & disappointed me at the same time. I tested the exact same image-to-video prompt using Kling 2.6 in both @magnific and Same image. Same prompt. Same model. The prompt: "Luxury beverage advertisem

Kanishkha AI | Creative AI Director516X

🧵 One Image, Six Unique Videos: All with Text Prompts 🎥 One image. Six distinct stories. All by tweaking prompts. I've been testing the following video models, and their ability to follow instructions. - Kling 4.0 - Seedance 2.5 draft - Wan 3.0 Prime Check out these 6 examples ... 👇

This anime workflow is amazing 🔥 ChatGPT Image 2.0 created the characters and cinematic scenes, then Kling 2.6 Pro turned them into a polished beautiful anime Ghibli short film - all inside @ImagineArt_X @imagineart_creo Full workflow + prompts: 👇

Kanishkha AI | Creative AI Director165X