AI RECAP: Meta 3D, Perplexity AI, Krea Style Transfer, & More

WTH they will realease a better version of stable diffusion 3 AND finally gave a good license so we can finetune and build loras and so on??? heell yeah! so in a few months we should see some community trained models then 🙂 NSFW please? we should find the best people who contributed to sdxl finetunes (pony and juggernaut) and crowdfund gpu for them!

Google Photos actually has the option to search its photos based on what it sees in the photo with any prompt. No special software needed. I find it super handy.

Tried Runway for putting motion to my Photoshop edited Ideogram / Midjourney images for use in my restaurants.. aaand useless. Waiting it out further

15:23 it's linking to their GitHub page.. the code has been there several days.

Im so tired of AI content creators bringing up SORA, it WILL NEVER! be released. It massively over-promised/lied, each SORA video took a massive compute budget to create, its not viable for a mass market. Its why Kling, Gen3, and Luma are all massively downscaled versions of Sora.

perplexity was started to kill the google search engine

Adobe did a free AI voice filter like that 1 year ago, and I think it's still better.
It doesn't just remove the background noise, but it reconstruct the voice wave.
I fixed some very badly recorded telephove calls from the 80s with that, it's incredible, you should try it.

A million dollars per LLC. Glad that my Stability issue has stabilized. I just hope as they continue to grow they "keep" listening. We have enough Adobes and Oracles already. GenAu sounds good enough for layered bg audio 😉

I would highly caution anybody here against a Perplexity Pro subscription.

The platform itself is so-so. The models are often unable to retain context past a single search despite having ample context in the model itself, due to cost control. This means it’s difficult to ask followup questions without the model forgetting the original inquiry. More importantly they consistently advertise features as being available that aren’t, they do not acknowledge limitations or deceptive advertising even when they’re pointed out by the community, and seeking a resolution to any issues is met with hostility in my experience. If the platform is useful to you, I would recommend keeping it as a free service or using open-source alternatives for needs that the pro-search might meet.

I am far from the only person who has had these issues with poor treatment, specifically with respect to perplexity pro. Their service is fine for free users, but if you’re considering pro I would advise you to carefully check which features are available, which are likely to remain available, and be prepared for hostility if you ever need to seek support with an issue encountered.

The video covers the latest advancements in AI technology and products, focusing on key updates in AI video generators, model comparisons, and tools for content creators. Highlights include:

– *Runway Gen 3 AI Video Generator:* Compared to OpenAI's Sora, it provides good video generation, though opinions on its quality differ.

– *AI Model Comparisons:* Stresses the need to try different models for specific tasks, as performance can vary.

– *InVideo AI:* A tool that makes video creation easier with text prompts and various features, boosting creativity and efficiency.

– *Perplexity Pro Search:* An upgraded search tool that uses AI to offer detailed, accurate results for complex questions.

– *Pixel Screenshots:* An AI tool that organizes and analyzes screenshots on Pixel phones, making them easy to search.

– *Meta's 3D Gen:* A tool for creating and retexturing 3D objects with AI, offering different styles and practical uses.

– *Voice Isolator by 11 Labs:* Cleans up noisy audio, making recordings usable even in loud environments.

– *Stable Diffusion 3 Licensing:* Stability AI has clarified the terms for using Stable Diffusion 3, addressing community concerns and improving the model.

– *Video Outpainting:* AI that fills in cropped video scenes, keeping them consistent with the original content.

– *Jenau for Audio Generation:* A new tool for generating ambient sounds and sound effects, with room for improvement.

The video ends by encouraging viewers to stay informed about AI developments, noting the fast pace of advancements. Thank you for watching, and stay tuned for more updates.

Krea "scene transfer" is just ip adapter + relight , these websites arent creating anything they are implementing comfyui workflows that have been out for months and then act like they created these features . Meta 3d Gen didnt release anything except for a paper and renders , no code , no weights , it is not "released"

6:13 So about 66% of rode island state (3,144 km2). Now you just need the hydrogravity batteries to store the power for night use.

Not local? Not real.

I’m here for the crazy hair 💇‍♂️💇

Now back to the video 🚫
back to your regularly scheduled content ✅

Genuinely, thank you for finally consistently adding chapter markers.

The model we can use is the best model.

You should first very quickly clearly explain any terms that might be unfamiliar to your viewers. I had to figure out what you meant by "Video Outpainting" – your explanation was incomplete

Yes nasty reaction to any stupid "feature" that thinks trading all your privacy is worth something we have never needed – All capture-all-your-data features should be local open source software completely under your control only. If I want to place all my photos in a directory on my computer and have a local AI inquire on them then that's my prerogative. It should not be pre-implemented. Do not ever promote such things

I like what stability AI did there.