Share this page!

Enter URL or ID to Unroll

You can paste full URL like: https://x.com/threadreaderapp/status/1644127596119195649
or just the ID like: 1644127596119195649

How to get URL link on X (Twitter) App

  1. On the Twitter thread, click on or icon on the bottom
  2. Click again on or Share Via icon
  3. Click on Copy Link to Tweet
  4. Paste it above and click "Unroll Thread"!
  5. More info at Twitter Help
A.I.Warper Profile picture
A.I.Warper
@AIWarper
Creator of the viral Lil Yachty Walk Out Meme! 🇨🇦 Business Inquiries: aiwarperinc@gmail.com $WARPER 7JNdLsAgBMi2WZW26SeifhMNEt3LrLcfM8oBQVT7pump
Apr 9 • 8 tweets • 4 min read
If you need consistent, reoccurring scenes for your story it's never been easier.

A thread on how I go about blocking out a 3D scene that I can then use for any reoccurring environment shots.

As always - if this helps you please kindly like and share! 🩵

🧵BELOW 🧵 The first thing I chose to go with was using ChatGPT to extract tiled textures for the floor and the wallpaper.

You can see from the screenshots below how I did this.

Then, in Blender, I just used simple planes as the floor and walls and applied the texture. Image
Image
Image
Nov 21, 2024 • 5 tweets • 2 min read
Black Forest Labs FLUX released "Tools" 🚨

Fill = Inpainting / Outpainting ✅

Depth / Canny ✅

Redux (think Midjourney's Remix..... but better) ✅

All FULLY supported in ComfyUI on Day 1

Links and examples below 👇 Comfy Support with full workflows:
blog.comfy.org/day-1-support-…

BFL Blod post
blackforestlabs.ai/flux-1-tools/?…
Aug 30, 2024 • 6 tweets • 3 min read
It's never been easier to make an AI powered influencer now with FLUX 🧵

FAL just introduced an insane LORA training tool that is actually insane.

Meet Mei Trix (see what I did there?)

READ BELOW ON HOW I MADE HER WITH ONLY 4 IMAGES 👇 Image Step 1)
If you already have a dataset great you can skip this.

You can use whatever generator you want, but I used this FLUX playground w/ LoRa

"An X image grid of a quirky 30yr old asian woman. She has blue silver hair and is wearing hipster clothes"

Pro tip: inpaint or gen fill away stuff like that necklace. I made the mistake of not doing it and now she is wearing a necklace in every image I generate

Second tip: FLUX really wants to make clef chins. You can also inpaint that away before training
Image
Apr 8, 2024 • 9 tweets • 3 min read
Viggle AI Experiment 💙

This is an incredible tool for style transfer.

Details and link to Discord below 👇

As always, if you enjoy this content please kindly like and share! Firstly, I rotoscoped the subject using After effects. This isn’t necessary but I needed a mask for a later step anyways so - why not right?
Feb 23, 2024 • 19 tweets • 8 min read
🧵Small Thread on Anime LipSync🧵

My hope in sharing some of these results is that it sparks an idea for someone to figure this out in a more efficient workflow

Tools used:
ComfyUI
Adobe Animate 2024
Davinci Resolve

1/17 Disclaimer: This is more of a traditional animator pipeline. It involves pre-rendering the mouth shapes and then manually placing them in post (Will talk on this later).

This works best for fixed perspective shots which are present in the majority of anime.

2/17