newslounge.co · April 18, 2024

Good Morning. 

This is newslounge, We’re like your morning coffee - essential, energizing, and slightly addictive.

On Today’s menu:

• Brands in Movie Financing

• Steerable Motion and Fake Depth in ComfyUI

• IPAdapter Plus - Style Transfer

• Mixing AI With CG in Innovative Ad Solutions

-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! 😎

HOLLYWOOD PITCHES BRANDS ON MOVIE-TV FINANCING

🚨HOLLYWOOD TO PITCH BRANDS ON FINANCING MOVIES AND TV SHOWS IN NEW UPFRONT

Michael Sugar, the award-winning producer behind titles like Spotlight and The Knick, is spearheading an upfront that focuses on arranging financing for projects rather than securing advertising or product placements. While most brands will probably invest in specific projects, the possibility that some might use these upfronts to set up their own studio branches and create a series of films is intriguing.
With LVMH's recent launch of 22 Montaigne, their entertainment division, and brands like Nike aiming for greater involvement in Hollywood, it's clear that more major brands are poised to leave a larger imprint on the entertainment industry.

What happened?
Brands are reevaluating their advertising expenditures. Instead of just placing products in films and shows, which offers vague outcomes, they're now aiming to take on roles as producers and financiers. This shift in strategy is logical.

The most obvious:
Developing original IP remains costly and risky, creating the same challenges for these new entrants. High production costs and low success rates of projects could perpetuate the flawed industry model, making it unlikely to succeed. Sound familiar?

-NL

CASE STUDY

STEERABLE MOTION AND FAKE DEPTH IN COMFYUI

🚨This post covers two topics I've been eager to discuss for some time.

What is Steerable Motion?
The first part is about the Steerable Motion Workflow by Peter O'Malley (POM).
This is by far the best image interpolation workflow I've worked with.

By determining the number of frames between each still image and selecting one of the three motion LoRAs, you can achieve a smooth interpolation that resembles a complete AnimateDiff animation. For instance, you'll notice that hair moves naturally and ocean waves animate realistically. Additionally, you can use Ostris' Composition IPA to add structure to the generation.

Depth LoRA:
Another technique I've been experimenting with in my creative explorations is generating depth maps within ComfyUI for various effects and transitions. One method I'm showcasing here uses the Depth Map LoRA to convert your prompt into a depth map with AnimateDiff.

👽my text prompt:
spinning - overlapping boxes, 4k
Depth map, black background, high contrast

Then you can use it as the source for your ControlNet in other workflows, which is much faster than relying solely on 3D applications to generate masks. Additionally, you can use your 3D scene as a ControlNet to give more direction to the output.

IPADAPTER PLUS - STYLE TRANSFER

IPAdapter Plus - Style Transfer is truly amazing; here’s a quick demo of how I incorporate it into my workflow. This technique is amazing when I develop concepts based on my CG designs.

🔺I started off with my regular SDXL Refiner workflow. Initially, I generate an image that integrates my text prompt and a reference image using the advanced IPAdapter.

🔺In the second stage, I take the image from the first part and use a WD14 Tagger to extract its text prompts. I then enhance these prompts with additional complementary ones.

You could also use LLM models in ComfyUI via Ollama to provide a more detailed description of your image.

✨check out my demo here: Link 

This is where the magic happens:
Using the SDXL IPAdapter Style Transfer, you can generate many unique images, each reflecting the style of the original.

🚨Additionally, You can completely change the composition of the image by using a totally different image with ControlNets.

💥One more thing: Please use the poll section below to share your feedback on this case study.

We are seeking:
full-stack software engineer
copywriter
web developer

[email protected]

SNIPPETS

😲Autodesk: Interesting AI tools are coming to Autodesk Maya and they are looking awesome.

👟Nike designed these wild Air sneakers with a little help from AI

🌎The Sphere: The world’s biggest canvas, How Sphere’s pixel power brings art to the masses.

🤖OpenAI plans to open its first office in Asia in Tokyo, and will launch a new GPT-4 model designed for Japanese speakers.

When using AI for innovative advertising, it's crucial to balance AI capabilities with human expertise. AI excels at analyzing data, identifying patterns, and generating initial content ideas. Moreover, AI is set to revolutionize content creation, particularly for immersive e-commerce and AR/VR experiences, topics we will explore in future issues.

🚀 All videos were created with ComfyUI, blending CG with AI-generated imagery from my videos of two models.

🤿 Quick workflow:

• Animated Nike sneakers using Houdini.

• Developed basic concepts with CG elements via the SDXL workflow, animated in Nuke, and refined in ComfyUI.

• I created multiple ControlNets using the videos I shot on set, which guided the movement and composition of the scenes.

• Extensive use of masking and compositing in ComfyUI for background removal and transition effects.

✨ Animation Workflows:

• AnimateDiff Evolved (Video to Video)

• AnimateDiff Evolved (Image to Video) using SparseRGB controlNet.

• Stable Video Diffusion for simple camera movements.

-NL

WANT TO BUILD A NEW AD CAMPAIGN?

REPLY TO THIS EMAIL TO SCHEDULE A CALL!!

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”