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
Can AI understand your rough sketches?
ChatGPT just added a new sketch feature to its new Images 2.5 model, so I tried it with extremely simple sketches and short prompts to see how well it could understand my intention.
And honestly, I actually like it!
This can be helpful especially when you already have a specific pose or composition in mind and want to quickly turn that rough idea into something more refined.
If you’re curious, I included a quick process video in the comments.
Do you think this new feature could be useful in your workflow?
Turning a rough pose sketch into a refined image without losing the original composition is the actual killer use case here, going to try this on some old thumbnails.
The sketch-to-image consistency is impressivethe simple gesture keeps the composition open while the lighting and palette carry through beautifully.
Wooooah!
This is a game changer for bridging the gap between rough ideation and client-ready comps. Skipping the back-and-forth prompt engineering just to get a specific angle or composition saved will shave hours off early visual development. Impressive test!
The jump from that basic sketch to the final image is wild! This is a massive time-saver for storyboarding and quickly communicating art direction before a build.
Oh, cool! I am going to try this today!
Wow, really nice.
It will be very useful
Huge for rapid storyboarding. Turning a stick figure straight into composition saves hours of fighting with prompts.
So cool
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?
Challenges
View all
Related posts
This project started with a very specific idea for how a static product visual should move.
The base artwork was created with ChatGPT and Nano Banana, but before generating the final animation, I spent time refining the prompt and defining the exact movement, camera behavior and energy we wanted.
I tested the direction with different models, including Kling 2.5, using those iterations to improve the prompt before producing the final sequence with Seedance 2.5.
The result was extremely close to what we had planned, including the animation and even the sound effect that completed the motion.
For me, this is where AI production gets interesting: the real work is not simply generating. It is art direction, prompt design, testing and refinement until the model delivers the intended result.
That line about the real work being art direction and refinement rather than generation is something I don't think most clients grasp yet, they still see 'AI made it' as the whole story. Did you end up walking the client through that process, or did they only care about the final result?
AI draft → my direction 🌿
I gave Figma Agent the content, structure, and references to create a quick starting point, then redesigned it in my own visual direction.
AI for speed. Creative decisions by me.
Before or after? 👀
Beautiful
30-sec UGC ad for VELORA, a fictional shampoo brand, from concept to visuals, including the model, product design, scenes, dialogue, and final commercial direction.
Prompt in the comments.
What do you think?
