- NewsLounge
- Posts
- 🚀New Advanced Text-to-Video Models
🚀New Advanced Text-to-Video Models
newslounge.co · June 14, 2024
Good Morning.
Welcome to another edition of newslounge. If you're new here, every week I share what I find interesting in the world of VFX and AI. A little deep dive into what we’re working on, along with the new technologies and workflows. Lets get to it.
On today’s menu:
The Art of Infinite Displays
New Advanced Text-to-Video Models
ComfyUI Toolbox
Most Valuable Company in the World
Midjourney Personalized Feature
-Ardy
was this email forwarded to you? you can sign up here.
🚨Just a quick note: You can share this newsletter with your friends using the unique referral link at the bottom of this email. By doing so, you'll earn points that can be exchanged for some cool prizes. Let's spread the word! 😎
CASE STUDY
THE ART OF INFINITE DISPLAYS
I recently shared a project inspired by metro displays and city billboards, and I’m excited to dive into the workflows that bring these animations to life! Here are some key takeaways:
Workflow Overview: Combining tools like Photoshop, Houdini, Nuke, and ComfyUI for efficient mask and image compositing.
Animation Creation: Transforming a single image into dynamic animations using sparse controlNet models for motion and image interpolation.
Image Compositing: Techniques to precisely place and resize images using masks, enhancing the visual appeal of animations.
Advanced Settings & Models: Utilizing models like animate LCM and motion LoRA, along with IP adapter settings and controlNet adjustments for higher quality and consistent animations.
Segmentation & Light Interaction: Methods for accurate video segmentation and light interaction in compositing, employing grounding Dino Sam and segment anything models.
Credit: Ardy Ala
👾 ComfyUI Toolbox:
Comfyroll Studio: useful graphics and Utility nodes.
ComfyUI Layer Style: One node I cant live without is The MaskEdge Detail.
🚀Stay tuned for Part 2-
-Ardy
SNIPPET
🤖2024 GitHub Accelerator: Meet the 11 projects shaping open source AI
🚀NOVA-1, the advanced text-to-video world model that gives precise control over the look and feel of a piece of content.
🕵️♀️ Open-Sora, presents Open-Sora-Plan v1.1.0, which significantly improves video generation quality and duration.
👩💻Autodesk has acquired Wonder Dynamics, the creator of Wonder Studio, an AI tool that can automatically animate, light, and compose a 3D character model into a live-action scene.
😲Apple’s AI announcements helped it leap ahead of Microsoft to become the most valuable company in the world on Wednesday.
🎨Perplexity AI has launched a new tool, Perplexity Pages, which allows users to create comprehensive and visually appealing content on any topic.
🤗NVIDIA collaborates with Hugging Face to simplify generative AI model deployments.
TRENDING
💥This is WILD.
💡@LumaLabsAI is scary good!!
🚀I tested both the image2video and text2video features, and it's truly exciting in terms of quality and the complexity of motion!
🙋♂️The last two videos were made using concepts I created from CG elements in ComfyUI.— Ardy Ala (@ardiology)
10:00 PM • Jun 13, 2024
😎Midjourney now allows users to personalize their images using the --p parameter, based on image ratings they've provided on the MJ website.
Stable Diffusion 3 Drama:
The recent release of Stable Diffusion 3 (SD3) Medium by Stability AI has been met with significant criticism and derision from the AI art community. The model, which is comprised of 2 billion parameters, has been widely panned for its poor performance in generating accurate human anatomy, particularly in areas like hands and feet.
Many users have pointed out that the model's failures in depicting humans are likely due to Stability AI's decision to heavily filter out adult content, often referred to as "NSFW" content, from the SD3 training data. This heavy censorship has severely hampered the model's ability to generate accurate human anatomy, as evidenced by the numerous examples of distorted and unnatural-looking limbs and body parts generated by SD3 Medium.
😎BTW you can run SD3 locally now: Learn More [here]
-NL
🙋♂️WE NEED YOUR FEEDBACK…
What'd you think of today's edition? |
WANT TO BUILD A NEW AD CAMPAIGN OR LEARN ABOUT AI INTEGRATION?
REPLY TO THIS EMAIL TO SCHEDULE A CALL!!
😂😂That’s it for today, I’ll leave you with this!!
This is what product-market fit looks like
— Justine Moore (@venturetwins)
4:58 PM • Jun 4, 2024
-newslounge
BUT, WAIT! THAT’S NOT ALL! ⬇
🎁You can get free stuff for referring your friends!!
Earn free gifts 🎁
5 referrals - “Water Bottle Stickers” 🔺15 referrals - “Mystery Box”
25 referrals - “Water Bottle” 🔺 40 referrals - “Nuphy Desk Mat”
60 referrals - “Logitech Mouse”