New Stable Diffusion XL! All you need to know!

Рет қаралды 7,947

Жыл бұрын

Stability AI has just released Stable Diffusion XL 0.9, the ultimate leap forward in AI image generation! Join me in this video as we explore the incredible features of the new release and witness its mind-blowing capabilities.
SDXL 0.9 is a powerful text-to-image model that pushes the boundaries of AI creativity. With its impressive resolution and compatibility with consumer GPUs, it's easier than ever to create stunning and realistic images.
But that's not all! SDXL 0.9 introduces advanced functionalities like image-to-image prompting, inpainting, and outpainting, unlocking new possibilities for creative expression.
Starting June 26th, SDXL 0.9 is available on the Clipdrop platform for select customers. Don't miss out on this exclusive opportunity to experience the future of AI image generation!
Join me as we compare SDXL 0.9 with its predecessor and witness the incredible progress made in AI image generation.
Watch now and be part of the AI revolution!
The link to try SDXL 0.9 - clipdrop.co/stable-diffusion
Prompts used in this video:
1. Woman standing in front of a window with her hair blowing, modern anime, highly detailed, digital drawing, perfect composition, light atmosphere, evening light
2. portrait of a young woman, blue eyes, cinematic
3. a cartoon of a glowing smiling fish with blue eyes, cinematic
4. Two hands silhouettes reaching to the sky reaching the clouds
5. noodle stand in neo tokyo, 2040, diorama, tilt-shift.
Generated Images credits:
@icreatelife, @PurzBeats
#ainews
#stablediffusion
#sdxl
#ai

Пікірлер: 18

@marat_ai 6 ай бұрын

𝐆𝐮𝐲𝐬, 𝐚𝐥𝐥 𝐜𝐮𝐫𝐫𝐞𝐧𝐭𝐥𝐲 𝐬𝐮𝐩𝐩𝐨𝐫𝐭𝐞𝐝 𝐧𝐨𝐭𝐞𝐛𝐨𝐨𝐤𝐬 𝐚𝐫𝐞 𝐚𝐯𝐚𝐢𝐥𝐚𝐛𝐥𝐞 𝐨𝐧 𝐏𝐚𝐭𝐫𝐞𝐨𝐧 (AI, Stable Diffusion, DeepFakes etc.) with the majority of them being free. Donations through Ko-fi are not operational, but file downloads are available. You can support me on Patreon. Thank you! 👉 www.patreon.com/marat_ai

@jusankz Жыл бұрын

2:47 Cool comparison and SD’s great progress. Can’t believe it’s free.

@Nicolas2009Best Жыл бұрын

Completely solved the problem with a hands. At least partially solved the problem (c) LOL

@buddy2665 Жыл бұрын

Can you make a video about how to use vae in your Google colab setup that I'm using?

@marat_ai Жыл бұрын

Ok, I work on that, I add lora, controlnet base models and vae

@zzz9556 Жыл бұрын

Good morning, are the images generated in the stable diffusion installation for commercial use? Or do I have to pay a subscription to be able to use them?

@marat_ai Жыл бұрын

Hi! SD comes with a permissive license. So yes, any commercial use is allowed.

@RealShinpin Жыл бұрын

When do you tink the weights will be made available so we can use it with auto?

@marat_ai Жыл бұрын

I very hope in one month

@marat_ai Жыл бұрын

I would be glad if you rate my new video about Stable Diffusion Lora models in 1 click. kzfaq.info/get/bejne/bKdmlKSl1a3dpmg.html

@user-og6yf4vs1e Жыл бұрын

so it only requires 12 gb of vram, rtx 3060 is the best bang for buck?

@marat_ai Жыл бұрын

idk because as a mac user I prefer cloud solutions like google colab or kaggle

@rewixx69420 Жыл бұрын

better than Midjourney it can generate text

@marat_ai Жыл бұрын

as others diffusion models SD still has problem with text, for text tasks transformers models are needed

@jopansmark Жыл бұрын

10X times better than Midjourney, it can generate Xi Jinping

@ItsBrody 8 ай бұрын

is that his real voice? mouth hardily moves. but it does sound like he talks with his lips never touching

@marat_ai 8 ай бұрын

Yes, both the real voice and video. In my native language, there isn't as strong articulation as in English, but I'm working on it. You can check out the latest videos and make sure that I'm real:) And yes, the sound quality here isn't great