CoffeeVectors's profile picture. AI Filmmaker & Digital Artist

CoffeeVectors

@CoffeeVectors

AI Filmmaker & Digital Artist

Pinned

brain rotting, but the thoughts still racing // Testing img2vid lipsyncing with the InfiniteTalk model on @wavespeed_ai and a song I made in @suno v5. Love how it handles images with multiple faces and how it animates even when it doesn’t see a mouth. Quick tutorial in 🧵👇 (1/6)


CoffeeVectors reposted

Google just dropped "Attention is all you need (V2)" This paper could solve AI's biggest problem: Catastrophic forgetting. When AI models learn something new, they tend to forget what they previously learned. Humans don't work this way, and now Google Research has a solution.…

akshay_pachaar's tweet image. Google just dropped "Attention is all you need (V2)"

This paper could solve AI's biggest problem:

Catastrophic forgetting.

When AI models learn something new, they tend to forget what they previously learned. Humans don't work this way, and now Google Research has a solution.…

CoffeeVectors reposted

Agibot A2 wins a Guinness World Record for traveling 106.3km (~66 miles) Suzhou to Shangai - using battery hot-swapping. 2026 will be the year of robotics.


CoffeeVectors reposted

Can’t stop watching the time lapse videos of “construction” from the AI interior design accounts (from inspiringdesignsnet)


CoffeeVectors reposted

🚀 Gaussian Splatting Performance Breakthrough Achieved 6M photorealistic splats rendering at 60-80 FPS in real-time in Unity. Mixamo character conversion + GPU compute shader skinning = photorealistic animated characters. Key optimizations: ✅ GPU compute shader skinning ✅…


As the tools improve, I suspect we’ll see direct animation of entire mood boards. Instead of single renders, put several alts and frames in one 4k image and animate the whole thing, then select the best nodes for upscale. Fishing net the latent space for first drafts.


CoffeeVectors reposted

QwenEdit-2509 Character Turnaround Sheet LoRA: creates a composite image of a character from multiple angles, slightly improving the base model's rotation ability. huggingface.co/tarn59/charact…

wildmindai's tweet image. QwenEdit-2509 Character Turnaround Sheet LoRA: creates a composite image of a character from multiple angles, slightly improving the base model's rotation ability.
huggingface.co/tarn59/charact…
wildmindai's tweet image. QwenEdit-2509 Character Turnaround Sheet LoRA: creates a composite image of a character from multiple angles, slightly improving the base model's rotation ability.
huggingface.co/tarn59/charact…

CoffeeVectors reposted

🤯🍌🤯 Gemini 3.0 can convert a 2D blueprint into a 3D-rendered visualization - at 4K resolution. Just paste your 2D plan and add the prompt (in ALT). Absolutely insane for architects or interior design workflows.

emmanuel_2m's tweet image. 🤯🍌🤯

Gemini 3.0 can convert a 2D blueprint into a 3D-rendered visualization - at 4K resolution.

Just paste your 2D plan and add the prompt (in ALT).

Absolutely insane for architects or interior design workflows.
emmanuel_2m's tweet image. 🤯🍌🤯

Gemini 3.0 can convert a 2D blueprint into a 3D-rendered visualization - at 4K resolution.

Just paste your 2D plan and add the prompt (in ALT).

Absolutely insane for architects or interior design workflows.

CoffeeVectors reposted

Solved nano banana's mushy pixels and inconsistency! Releasing tooling soon on Retro Diffusion so you can animate any 64x64 pixel art! Sorry for the horrors... 👀

RealAstropulse's tweet image. Solved nano banana's mushy pixels and inconsistency!

Releasing tooling soon on Retro Diffusion so you can animate any 64x64 pixel art!

Sorry for the horrors... 👀

CoffeeVectors reposted

NanobananaPro→Marbleで作った大学生の部屋 存在していないのが信じられん…marble.worldlabs.ai/world/c2ddc49f…


CoffeeVectors reposted

Fun & likely unintended use case for #NanoBananaPro: image→3D point cloud Prompt: This is a rendering of a 3D model of a person. Make an accurate image of the corresponding normal map. Then I run Poisson-based normals→3D Pretty amazing for a general-purpose 2D image model 🤩


CoffeeVectors reposted
spiritform's tweet image.

CoffeeVectors reposted

One more vintage animation test using @Artedeingenio Midjourney sref code. Image created in MJ, then changed in Nano Banana Pro, then animated with @grok Imagine.


CoffeeVectors reposted

This AI paper just solved Google Earth's biggest problem. Satellites look down. Humans look across. That perspective gap is why 3D maps are limited to cities you can blanket with aerial flyovers. Skyfall-GS bridges the gap by synthesizing the views we never captured -…


CoffeeVectors reposted

Nano Banana Pro might have just erased the need to train a LoRA for FLUX or Qwen. The 14-image context window lets you one-shot entire datasets with zero training. Prompt below

angrypenguinPNG's tweet image. Nano Banana Pro might have just erased the need to train a LoRA for FLUX or Qwen.

The 14-image context window lets you one-shot entire datasets with zero training. Prompt below
angrypenguinPNG's tweet image. Nano Banana Pro might have just erased the need to train a LoRA for FLUX or Qwen.

The 14-image context window lets you one-shot entire datasets with zero training. Prompt below

CoffeeVectors reposted

We’ve spent tens of hours researching the best fighting prompts. I’m pretty sure we created the best prompt library so you could build insane fight scenes. It’s going to be part of the course, and it’s going to be amazing. Join the waitlist 👇


CoffeeVectors reposted

"Generate an image in the style of this moodboard" Solved by nano banana pro

mitch0z's tweet image. "Generate an image in the style of this moodboard"

Solved by nano banana pro
mitch0z's tweet image. "Generate an image in the style of this moodboard"

Solved by nano banana pro
mitch0z's tweet image. "Generate an image in the style of this moodboard"

Solved by nano banana pro
mitch0z's tweet image. "Generate an image in the style of this moodboard"

Solved by nano banana pro

CoffeeVectors reposted

I uploaded a script and let Nano Banana Pro adapt it into a manga, an anime, and a live-action movie. Nano Banana Pro did it all. This model is on another level.

WuxiaRocks's tweet image. I uploaded a script and let Nano Banana Pro adapt it into a manga, an anime, and a live-action movie. Nano Banana Pro did it all. This model is on another level.
WuxiaRocks's tweet image. I uploaded a script and let Nano Banana Pro adapt it into a manga, an anime, and a live-action movie. Nano Banana Pro did it all. This model is on another level.
WuxiaRocks's tweet image. I uploaded a script and let Nano Banana Pro adapt it into a manga, an anime, and a live-action movie. Nano Banana Pro did it all. This model is on another level.
WuxiaRocks's tweet image. I uploaded a script and let Nano Banana Pro adapt it into a manga, an anime, and a live-action movie. Nano Banana Pro did it all. This model is on another level.

CoffeeVectors reposted

@NanoBanana Is truly impressive. Full animation sheets in a single render. Im impressed.


CoffeeVectors reposted

AKIRA + NANO BANANA PRO 🤯 This has been a dream of mine since I was a kid.


CoffeeVectors reposted

Google Nano Banana Pro is incredible. Stronger character consistency. Image perspective changes. Better image modification. All at incredible speed.


Loading...

Something went wrong.


Something went wrong.