The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Back to feedPost
:Legal Document Summarization | NLP & AI Project
Developed an AI-powered legal document summarization system using NLP and transformer-based models. The project focuses on generating concise and meaningful summaries from complex legal documents using BART and T5.
Tech Stack: Python, Hugging Face Transformers, PyTorch, Pandas, NLP, ROUGE Evaluation.
Key Focus: Text preprocessing, model fine-tuning, summarization, evaluation, and improving readability of legal documents.
The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Trending
retrofuturism
Share your favorite designs from the past exploring the distant future. Or your own take on the aesthetic 🚀
halftone
Dots. Texture. Grain. Let's see your designs using the halftone technique.
Midjourney
Creatives are showing off what they're making with Midjourney.
colorgrade
Video editors sound off: How do you enhance the mood of your video in color grading?
Related posts
Yesterday, I said I was cooking… 👀
Here’s what came out of the kitchen.
For this one, I created a fictional sneaker brand called VOLT and turned it into a full AI UGC-style commercial — from the initial concept all the way to the final video and voiceover.
The workflow:
ChatGPT → concept + creative direction
Google Flow → visuals + video
ElevenLabs → voiceover
No physical product. No actors. No traditional production.
What do you think?
#Day8 #CreatingWithAI #AIUGC #AIVideo #AICreator #GenerativeAI #ChatGPT #GoogleFlow #ElevenLabs
AI Video ProductionChatGPTaivideoaivideocreationugccreatorAI Content CreationGraphic DesignElevenLabsGoogle Flow
Nice work
A single continuous one-take FPV aerial sequence made with Seedance 2.5 and refined in CapCut Video Studio.
I built a 30s bioluminescent aerial war piece that follows a lead rider through a living jungle canopy into a high-stakes mid-air engagement, the goal was to show continuous camera choreography, consistent character/mount design, and cinematic lighting while keeping the shot physically believable (no cuts).
This entry highlights Seedance’s ability to maintain visual continuity across complex motion, and was polished with sound design and color grading to maximize emotional payoff and social engagement.
Is that Avatar?
This is cool 😎
Which would perform better? 🍩
I created both of these visuals with AI for a client project, and I’m curious what the Contra community thinks.
The goal is not necessarily to choose the “prettier” image, but the one that would be more effective for a food/dessert brand on social media.
A: Lifestyle-focused, with the product being consumed + an Instagram/social proof element B: More playful and product-focused, using the donuts as the main visual hook
If you were choosing one for a paid social campaign or organic Instagram content, which one would you bet on?
And if you have second, I’d love to know why. Is it the composition, visual hook, product appetite appeal, storytelling, or something else?
Both are AI-generated, so I’m also curious whether that affects your perception of the creative.
32 voted
67%
16 voted
33%
48 votes
Closed
Option A is a total winner for paid ad performance! Lifestyle storytelling combined with a social proof hook instantly builds trust and drives conversions, whereas Option B is great for top of funnel organic feeds. Both look amazingly seamless for AI visuals 🍩✨