PatchFusion was just released. Compared to ZoeDepth, it predicts... depth maps with much finer details, just look at the comparison below! 🤯 Its main contribution is a new Global-to-Local module and Consistency-Aware Training. More examples below (with code) ⬇️⬇️show more

Google just revealed an ABSOLUTE depth estimation model 🤯... As opposed to recent depth models (Marigold, PatchFusion) which aim for maximum details, DMD aims to estimate the ABSOLUTE depth (in meters) within the image More details below ⬇️⬇️show more

Upscale-A-Video was just released and it's so good! 🤯... It's a temporal-consistent Diffusion Model for video Super-Resolution, and has some of the best results I've ever seen, look at how sharp those lines become! More details below ⬇️⬇️show more

This is literally magic 🤯 FMA-Net is a new... AI method for video deblurring! It uses complex motion representation learning for spatio-temporally-variant restoration with kernels that are aware of motion trajectories. More info below ⬇️⬇️show more

And boom, just like that, the new version of... SeamlessM4T has already been integrated into 🤗 transformers! Hugging Face AI at Meta Use it right now with minimal installation and just a few lines of code! Links below ⬇️show more

Today we are launching new, more powerful models with... increased context windows on Poe, including the just-released Claude 2 with its 100k-token window length, along with a set of new tools to help everyone take advantage of them. (thread below)show more

This is wild. Hailuo AI just completely changed the... character consistency game with "Subject Reference" Just from a single image🤯 10 wild examples:show more

So IT IS TRUE. Men training Legs twice a... week are living a much healthier and happier life compared with Men training it just once or not training it.show more

New Grok Style: Deep Cosmic Beauty This one is... so much fun to play with, just change the subject and enjoy! Prompt below ↓show more

Replace a person from a video with any character... using a single picture 🤯 This new paper from Alibaba is called MIMO: Controllable Character Video Synthesis withSpatial Decomposed Modeling More below ⬇️⬇️show more

🤠 GANGS REWORK UPDATE 🤠 We have just updated... with a rework to Gangs and Anubis! Check out details about what's changed below ⬇️ NEW CODES: (must be lvl 25, expires in 2 weeks) 218K GANGGANG ANOOBIS Game:show more

🤯 Depth videos perfectly solve false flags on reference... videos — and can perfectly recreate both martial arts and dance! Turned a Guan Dao martial arts clip into a Depth motion reference, swapped the fighter for a market auntie, and moved the scene to a T-junction inside a local market 🤣 🌟 Workflow: 1. Pick a reference clip under 15 seconds 2. Convert it to Depth with Depth Anything V2 3. Generate a new character + scene 4. Feed everything into Seedance with the prompt below 🌟 Depth video conversion: You can build a local Depth converter with Codex — prompt in the comments. This goes way beyond trending dances. Martial arts, polearms, and other complex movements can all be transferred cleanly with Depth! Workflow + Prompt below 👇show more

The OpenSea Claw is coming! 🌊 OpenSea has partnered... up with Beezie to bolster their rewards program with a Claw experience. More below ⬇️show more

Seedance 2.0 is dropping soon I'm calling it, it... will break the internet, 100%. It will be SOTA, with Kling 3.0 just released, this will leap yet another step forward. This is the official threshold, the point of no return. More examples below 👇show more

The new GPT Engineer is insane. I just wrote... a single sentence and it created me a landing page for a SaaS business! It outputs the code, allows you to modify anything and publish it with just one click 🤯show more

Just got early access to Magnific AI, and it's... easily the best AI image upscaler I've ever seen. The detail that it adds to images is SERIOUSLY impressive! More examples below:show more

🤯 I didn’t expect Depth to track rooftop parkour... this cleanly! Used a fast climbing clip as the motion reference, then swapped in a student with twin tails and a backpack on a coastal school rooftop. The running path, wall contact, jumps, landings, and full-body continuity all hold together surprisingly well. 🌟 Workflow: 1. Pick a reference clip under 15 seconds 2. Convert it to Depth with Depth Anything V2 3. Generate a new character + scene 4. Feed everything into Seedance with the prompt below 🌟 Depth video conversion: You can build a local Depth converter with Codex — prompt in the comments. Depth opens up a lot more possibilities for parkour, climbing, martial arts, dance, and other complex full-body motion. Workflow + Prompt below 👇show more

Grok Imagine's new video tools just hit Replicate! Extend... your clips with seamless audio using Video Extension, or build a full scene from 7 images with Reference to Video. See below for more examples 👇show more

Don't forget: Open Training is on at IKON Park... on Saturday 31 May! Register and find out more below ⬇️show more