Dreaming Tulpa 🥓👑

@dreamingtulpa • 54,918 subscribers

creative coder and ai whisperer | @needlefm | søl/max | 🇨🇭 https://t.co/DpsJ5tSi8L (my music) https://t.co/JjX7INV1K5 (4'700+ readers) https://t.co/6AOraP48HO (my prompts)

Live Cam

Dreaming Tulpa 🥓👑

Shorts

Sorry guys, this time it's so over for real 💀

not what i had in mind but i'll take it

The Stable Video Diffusion model just dropped 🔥 The new model supports: – Text-to-Video – Image-to-Video – 14 or 25 frames at 576 x 1024 – Multi-View Generation – Frame Interpolation – 3D Scene Understanding – Camera Control via LoRA Paper: Code: SVD model: SVD-XT model:

KEEP can enhance video face super-resolution by maintaining consistency across frames! It uses Kalman filtering to improve facial details, working well on both synthetic and real-world videos. Links ⬇️

SPARK can create high-quality 3D face avatars from regular videos and track expressions and poses in real time. It improves the accuracy of 3D face reconstructions for tasks like aging, face swapping, and digital makeup. 6 examples:

i don't believe you all are ready for what's to come

Soon anybody can be animated everywhere! En3D can generating 3D humans either from text or images and animate them!

Live deep fakes are a thing now btw

seedance is great at bringing cursed midjourney to life

218/383 scenes completed

A lot of you wondered how I created my Claire Silver "motion" contest submission: LIVE.DIE.REPEAT. So I shall deliver. Here's a quick breakdown 👇

there is a new gaussian splat method that can create high-quality 3D scenes from long videos without needing camera positions:

gen alpha is gonna be so cooked 💀 &gt; Y2K aesthetic, wide-leg jeans, shiny jackets, baby tees, and velour tracksuits, wide angle, found webcam picture of a Super cute brown haired American woman in the early 2000s on the porch of a house leaning towards camera to kiss

OSDFace is a new face restoration method that can restore low-quality face images in one step! Always blows my mind how this stuff like this is possible now.

Meta published VertexRegen! a new method to generate 3D meshes:

DreamCraft3D++ can generate animatable high-quality 3D assets from an image in 10 minutes! Yes, it supports meshes 🔥 Links ⬇️

me and my horse when a new ai model drops

NVIDIA published UniRelight! a new method that can relight single images or videos by estimating surface color (albedo) and creating realistic lighting effects in one step

there is a new high-quality lip-sync model called KeySync 🔥

Videos

Watch Anya Live

High quality AI generated human videos are coming! Animate Anyone can generate videos of anyone with a single image and a bit of pose guidance 🤯

RIP TikTokers 💀

Smart glasses make it possible to unknowingly record people's faces and gather publicly available data like name, home address, phone number, relatives and more all automatically 💀

oh btw ai can now generate high-quality classical sheet music and it sounds absolutely insanely good

This doesn't just work with realistic humans, also with cartoon/anime characters.

google deepmind is working on braindance tech

it's so over you can't even comprehend it this is new "research" from bytedance 100% artificial podcasters will soon exist 7 crazy examples:

i'm still amazed that this is even possible

High quality AI generated talking heads are coming! GAIA can generate talking avatars from a single portrait image and speech clip. It even supports text prompts like `sad`, `open mouth` or `surprise` to guide video generation. Crazy times ahead 🤯

bytedance just released BAGEL! an open-source multimodal alternative to gpt-4o and gemini flash it supports: &gt; image reasoning &gt; image editing &gt; video generation &gt; style transfer (ghiblify anyone?) &gt; 3d rotation &gt; outpainting &gt; navigation

after 1.5 months of countless midnight hours, it's finally done 🙌 i present to you OMW – a journey through 384 universes crafted from visuals by me and 69 beautiful minds from the community, animated with Grok a little history of how it came to be below 👇

look at me, i'm the 3d artist now! ai can now create 3d meshes from sketches a child could draw

Thanks to AI, so many amazing new possibilities are emerging. Oh, what I would give to be a kid again. Our imagination will truly be the limit.

KEEP can enhance video face super-resolution by maintaining consistency across frames! It uses Kalman filtering to improve facial details, working well on both synthetic and real-world videos. Links ⬇️

not long now before we can simply drag and drop an image into an editor to create a 3D scene! the scenes below are generated from the image on the left 👀

wake up babe, a new upscale method just dropped

Adobe is entering the image-to-3D game! Their new method, LRM, can create high-fidelity 3D meshes from a single image in just 5 seconds 🔥 It's trained on 1 million objects and is able to generate objects from real-world images and generative AI models.

forget about physical camera stabilizations why don't we reconstruct the world in 4d and rerecord the footage:

Nvidia presents EdgeRunner! The method can generate high-quality 3D meshes with up to 4,000 faces at a spatial resolution of 512 from images and point-clouds.

adobe is cooking a new method to generate sound from vocal imitations 👀

gen alpha is gonna be so cooked 💀 > Y2K aesthetic, wide-leg jeans, shiny jackets, baby tees, and velour tracksuits, wide angle, found webcam picture of a Super cute brown haired American woman in the early 2000s on the porch of a house leaning towards camera to kiss

bytedance just released BAGEL! an open-source multimodal alternative to gpt-4o and gemini flash it supports: > image reasoning > image editing > video generation > style transfer (ghiblify anyone?) > 3d rotation > outpainting > navigation