Ai Reposts

[A.I.Warper @AIWarper]

LTX vid2vid not to be slept on either

Crazy thing here is this is 149 frames and the entire render took 20 seconds locally on a 4090

For low motion zero camera movement - LTX slaps and its soooooooooooo fast

[A.I.Warper @AIWarper]

🚨SOUND ON 🔊

This was really fun to make....🤣

Will post a breakdown on how I made this later this week.

If you like this content please kindly like and share as it helps support my growth and motivates these creative tests 🩵

[sid @immasiddx]

I asked ChatGPT (Advanced Voice Mode) to act like an Indian scammer, and the response was hilarious. 😂

[Safety Marc @S4f3ty_Marc]

You can relight your images with SD on your computer using A1111, Forge, or ComfyUI.

"Ic-light" was released last month as an open source project. Many thanks to all the open source devs for giving us these brilliant tools.

Links to the original repo and extensions in comments.

[Wes Roth @WesRoth]

Devin was just the beginning...

@FactoryAI drops 'Droids' to bring autonomy to software engineering.

I believe this concept/idea is coming to EVERYTHING...

[Gradio @Gradio]

⚡Flash Diffusion: FlashSD3⚡

- Flash Diffusion, a diffusion distillation
- Accelerate any conditional diffusion model for Few-steps Image Gen
- 90.4M LoRA distilled version of SD3
- Can generate 1024x1024 images in 4 steps

[dadabots @dadabots]

🥳 Announcing Stable Audio Open 1.0
WE GOT MODEL WEIGHTS OUT 🏁😅
- text2audio diffusion, T5 DiT
- 47s
- pre-trained on sfx/samples from FreeSound
- good for making samples for your music
- fine-tune it
- build upon it (controlnet, etc)
https://t.co/EdYlPWjgPr

[青龍聖者 @bdsqlsz]

https://t.co/QRT9AbDP8B

[Gradio @Gradio]

⚡𝐅𝐥𝐚𝐬𝐡 𝐃𝐢𝐟𝐟𝐮𝐬𝐢𝐨𝐧, a diffusion distillation method.
⚗️ A 66.5M LoRA model, which is a distilled version of the famous Pixart-α model.
🖼️ Capable of generating 1024x1024 images in just 4 steps💪

[Ibn Hayal @helpfulai]

Forget 2024!

This website feels like it's from 2050.

(You HAVE to see this)

[Massimo @Rainmaker1973]

How mountains are created

[📹 Caltech]
https://t.co/kqG3N2nlhb

[cocktail peanut @cocktailpeanut]

Edit Images with NOTHING but prompts, locally, with 1 Click.

Differential Diffusion lets you edit images with nothing but prompts.

And I made a Dedicated Gradio Web UI and a 1 click launcher to make it as easy as drag&drop.

Runs LOCALLY on Windows, Mac, Linux.

[Sanjeev Sharma @sanjeevs_iitr]

Autonomous driving through tight, dynamic, stochastic, and adversarial traffic-dynamics on sub-urban roads in India, as well as through partially unstructured environments.

This demos showcases the robustness of our motion planning and decision making algorithmic frameworks in enabling #autonomousdriving through seamlessly through such traffic and environmental scenarios. The vehicle starts from a generic open environment at the temple, where there are no traffic-rules to abide by. It then exits the region and assumes a generic autonomous navigation behaviour, negotiating complex traffic scenes.

At various points it can be seen that the other vehicles (bikes, autos, bicyclists, and cars) didn't abide by any traffic-rule and moved in crisscross fashion, presenting adversarial scenarios, challenging our autonomous vehicle at @swaayatt to take care of the collision avoidance.

This classical motion planning and decision making algorithmic framework is being further scaled up with deep #reinforcementlearning, which will practically solve the sub-urban traffic-dynamics and environment negotiation for #autonomousvehicles in India and throughout the world as well.

This demo was done at the Kankali Kali Mata mandir in the city of Bhopal. This demo was a culmination of our prior works and demos: off-roads, on-roads, bidirectional traffic negotiation in single lane roads, and toll-plaza navigation.

We have taken up the arduous task of solving the Level-4 autonomous driving by the end of 2024, globally.

#machinelearning #deeplearning

[Ziwei Liu @liuziwei7]

🔥MoCap Anybody🔥

#NeurIPS2023 We propose *SMPLer-X*, the first generalist foundation model for 3D/4D human motion capture from monocular inputs.

- Project: https://t.co/c9Ee60UUyk
- Paper: https://t.co/84iGK1wmVg
- Code: https://t.co/VWcxxhh3Gt
- Demo: https://t.co/aLV4l4WsoX

[Yam Peleg @Yampeleg]

I just finished reading

"Fuck You, Show Me The Prompt."
by @HamelHusain

This is a M-U-S-T.
Every single word is pure gold.

Most LLM frameworks are not only unnecessary but are actively crippling you and slowing you.

Their only value is their prompts

https://t.co/nKpVkppaYi

[Min Choi @minchoi]

Ok, Sora is wild.

New videos dropped by the OpenAI team, and they are mind blowing.

100% AI from text (minus sound)🤯

5 insane examples:🧵👇

1. PROMPT: "an alien blending in naturally with new york city, paranoia thriller style, 35mm film"

[Min Choi @minchoi]

This is mind blowing.

This AI can make single image sing, talk, and rap from any audio file expressively! 🤯

Introducing EMO: Emote Portrait Alive by Alibaba.

10 wild examples: 🧵👇

1. AI Lady from Sora singing Dua Lipa

[AK @_akhaliq]

Mistral AI announces Mistral Large

top-tier reasoning capacities, is multi-lingual by design, has native function calling capacities and a 32k model.

The pre-trained model has 81.2% accuracy on MMLU

[Jenny @jennyAI]

The first Skynet drones just dropped

[Min Choi @minchoi]

New Sora videos just dropped on TikTok by OpenAI team and people are going crazy.

Nothing in this video is real🤯

6 wild new examples: 🧵👇

1. Labrador Hacker