PerSAM (personalized Segment Anything) is now available @huggingface!
This (super cool) method allows for a Dreambooth-like personalization of SAM, able to quickly segment new things in images based on just a single (image, mask) example.🤗
Notebooks: https://t.co/Kl9PBfZW5B
This video was made almost entirely by AI.
I used ChatGPT to write a script, Midjourney to create reference images, Runway Gen-1 to apply the style of the images to my source video, and Boomy AI for the music.
Workflow breakdown w/ comparisons in thread.
🧵
"The Construction of a Neon City" 🌆
Supercharging a static Midjourney picture with Photoshop's Generative Fill, WORKFLOW
Time spent: 3 hours 10 minutes. Complexity 6/10
Sound On 🔊
If you’re stuck at $0 MRR..
DO NOT:
• Add dark mode
• Build more features
• Ask friends their opinion
DO the following:
• Send 100+ emails/day
• Create content showing the value you provide
• Hangout where your subscribers hangout
#buildinpublic
I'm feeling excited because my friends and I have finished working on PoC of https://t.co/uKlfttQemL - api for image creation powered by state-of-the-art AI models. In mid-June there will be an MVP launch.
#buildinpublic
@CreateWithEvan Do you validate your ideas somehow? Creating projects that will never be completed also teaches us a lot. But you will learn far more from projects that can be evaluated by clients.