AI

202 votes, 100 comments. Link to the article (New Yorker): Why A.I. Isn’t Going to Make Art - “To create a novel or a painting, an artist makes…

Creatives are producing mind-blowing videos and shorts using AI tools like Kling, Runway's Gen-3, and Luma Dream Machine. Major breakthrough. 10 jaw-dropping examples: — Jamian Gerard (@JamianMedia)

I think there's a widespread misunderstanding about the role of AI in art - and what an "AI artist" is. I've been in the center of the firestorm this week. To break down some of the arguments I've heard 👇 — Justine Moore (@venturetwins)

I fucking LOVE AI, but here are 10 reasons I absolutely fucking hate it now, a 🧵 ... — Chris Alvino (@ChrisAlvino)

— Scott Manley (@DJSnM)

— Neb | 🏳️‍🌈 (@NebsGoodTakes)

MusePose is a pose driven image2video framework for virtual human generation Link to comfyui node in post below: — Allen T. (@Mr_AllenT)

In this video I show you the entire process from provisioning a Runpod GPU to installing and running Dough (tool for crafting videos with AI). I share my sample generations and what I have learned in the past few weeks. Its a long but thorough video so make sure you follow along and ask me questions in the comments below. Get RunPod.io - https://gabha.me/runpod Dough Repo - https://github.com/banodoco/Dough

Filmmakers, Designers, Artists, Listen up!!!People are HOOKED on Magnific AI but almost NOBODY is using it properly.In this tutorial I'm going to teach you one simple way to turn your storyboard into cinematic images with one reference image using Magnific Style Transfer. pic.twitter.com/RCN8T1gF0X— Ellenor Argyropoulos (@_Ellenor) April 9, 2024

⚡ Generative AI TutorialFrom Hand Sketches (drawn by the great Rafael Martín) to Video Game Map in Less than 5 Minutes with AI 🤯Step by step tutorial👇 pic.twitter.com/oazphqetas— Javi Lopez ⛩️ (@javilopen) April 9, 2024

Why nothing In AI is every dead.Zero shot and EBsynth come together for a revival for a new vid2vid tool.Will be testing this today to see if maybe, just maybe, we have something that can do lips.Code below. pic.twitter.com/fmc62dowha— AmliArt (@amli_art) March 20, 2024

MIDJOURNEY V6: CINEMATIC GUIDE (PART 1)In this guide, you will get the detailed prompt structure along with proper examples. Discussion on - Action and motion, - Camera angles and shot types, - Film stocks and period films,- Cameras and cinematic cameras,- Lighting-… pic.twitter.com/FAi8AdlvLT— AI Verse (@AI_Vision_Verse) December 29, 2023

Finally! Real-time Stable Diffusion !Here’s some experimenting with an audio reactive setup using #StreamDiffusion + Touchdesigner. #procedural #generative #art pic.twitter.com/nsCn0yEECx— Lyell (@dotsimulate) December 28, 2023

DiffMorpher demo is outUnleashing the Capability of Diffusion Models for Image Morphingdemo: https://t.co/0WLDi0VYqBGiven two input images, approach can generate a smooth and natural transition video between them.This is achieved purely by leveraging the prior knowledge of… pic.twitter.com/E7d7UVs9MV— AK (@_akhaliq) December 24, 2023

Official implementation of DreaMoving. Contribute to dreamoving/dreamoving-project development by creating an account on GitHub.

Experiments with prompts for NovelAIs text-to-image generator.

FineControlNet: Fine-level Text Control for Image Generation with Spatially Aligned Text Control Injectionpaper page: https://t.co/HyM3AunFpYRecently introduced ControlNet has the ability to steer the text-driven image generation process with geometric input such as human 2D… pic.twitter.com/dYUAmZRTmk— AK (@_akhaliq) December 15, 2023

Explore this post and more from the StableDiffusion community

Open AI released a great Prompt Engineering guide (link in comments). Here is a summary of their 6 strategies for getting better results when prompting GPT-4 pic.twitter.com/QiBASsbOHD— MindBranches (@MindBranches) December 15, 2023

Resemble AI just released a Speech Super Resolution AI Model 🗣️Enhance is an open-source speech enhancement model that transforms noisy audio into noteworthy speechvideo showcasing Enhance improving a classic Robert Feynman lecture pic.twitter.com/NcNmdNBRVy— AK (@_akhaliq) December 15, 2023

Playing around with attn masks with IP-Adapter and AnimateDiff some more. I managed to get a 6 image input sequence working. 😎There are some similar clips but with different masks below so you can see how drastic a difference attn masks can make. Also a link to a tutorial🧵 pic.twitter.com/75qxAyx7gj— noodlecake.ai (@noodlecakeai) December 14, 2023

Segment Anything Model (SAM) now runs at 30 FPS on an iPhone! 🤯EdgeSAM is the first SAM variant that can run at over 30 FPS on an iPhone 14 with good quality. Low how accurately it segments tiny vegetables!Code and @HuggingFace demo below! ⬇️⬇️ pic.twitter.com/tEQqysbXHa— Alex Carlier (@alexcarliera) December 13, 2023

From comfyui workflow to web app, in seconds. Contribute to xingren23/ComfyFlowApp development by creating an account on GitHub.

An exploration of Stable Diffusion and its applications

Explore this post and more from the comfyui community

1. Cassette AICassette is your co-pilot for AI music generation. pic.twitter.com/04qAvbATNe— Zumer (@zumersultana) December 9, 2023

MotionDirector: Motion Customization of Text-to-Video Diffusion Models. - GitHub - showlab/MotionDirector: MotionDirector: Motion Customization of Text-to-Video Diffusion Models.