Here's a brief demonstration of #stablediffusion's ability to transform initial images. I sketched up the imgs on the left and then used them as input images along with prompts that described the scene I wanted, including some modifiers. The imgs on the right were the output.

RT @proximasan: ye olde sdxl lora ??

Introducing Grok Imagine.

RT @sureailabs: Happy 2nd birthday Disco Diffusion studies! 🎂.

RT @juliewdesign_: ✨✨✨. midjourney + magnific + lightroom

RT @pika_labs: Introducing Pika 1.0, the idea-to-video platform that brings your creativity to life. Create and edit your videos with AI.….

RT @proximasan: asked chatgpt to make some posthuman memes for lain-pilled teens

RT @RisingSayak: With SDXL's tremendous quality improvements, we started training a couple of ControlNets internally 🔥. Today, we're excite….

RT @DrJimFan: The famed Stanford Smallville is officially open-source!. 25 AI agents inhabit a digital Westworld, unaware that they are liv….

RT @sureailabs: "post-collage scientific diagram landscapecore" - @EErratica

RT @sureailabs: if someone can decode what im trying to achieve here that would be wonderful

RT @MetaAI: Today we're sharing details on AudioCraft, a new family of generative AI models built for generating high-quality, realistic au….

RT @sureailabs: sharpness. gradients. vibrancy. texture.

RT @proximasan: redoing these with sdxl 1.0 ✨. also added a little friend to this page. something might or might not happen when you click….

RT @proximasan: i did it my vae.

RT @krea_ai: SDXL 1.0 is available for free to all current KREA users. And, of course, it integrates seamlessly with all the rest of KREA….

RT @proximasan: how i prompt

RT @sureailabs: blending flags svgs with prompts is a good idea

RT @proximasan: sdxl, some wip lora + runwayml gen-2

this is what a thriving, fully functioning platform looks like

RT @Artbreeder: Magically blend together images with Mixer.a new tool from Artbreeder! 🪄🎉. Try it now with any image ⬇️..

RT @nerijs: Oh boy, this is amazing. Basically, SDXL can extrapolate well to 768x768 and 512x512 even with LoRa. But the thing is, it's….