quantumcomputer (Manuel DE PALMA)

liked a model 2 months ago

stabilityai/stable-diffusion-xl-base-1.0

Text-to-Image • Updated Oct 30, 2023 • 1.98M • • 6.14k

liked a Space 2 months ago

Runtime error

1

📊

README

updated a Space 2 months ago

Runtime error

1

📊

Text To Image Bias

reacted to fdaudens's post with 👀 3 months ago

Post

2106

Want to supercharge your journalism with AI but don't know where to start? I've got you covered. 🚀

Ran two workshops at Media Party w/ Brown Institute for Media Innovation at Columbia University this week-end, packed with open-source AI tools for journalists. Thought you might find 'em useful too, so I'm open-sourcing my slides 😉

Here's a taste of what's in the beginner's deck (no-code tools focus):
- Scrape websites without coding
- Analyze bias in AI image generators
- Transcribe audio/video on your device
- Edit images with words
- Extract info from docs, websites, PDFs
- Analyze images, handwriting, videos
- Create custom AI assistants

Tons more in the deck.

👉 Full presentation link: https://docs.google.com/presentation/d/1Q887BhrcrDDgfi0O-Mbx2GI1De2H3GkIiXmd9MvmxYE/edit?usp=sharing

#AIinJournalism #MediaInnovation #OpenSourceAI #MediaParty

liked a Space 3 months ago

Running on Zero

1.48k

🔅

Diffusers Image Outpaint

Easily expand image boundaries

liked a model 6 months ago

meta-llama/Llama-3.1-8B-Instruct

Text Generation • Updated Sep 25, 2024 • 4.79M • • 3.39k

liked 2 datasets 6 months ago

cfahlgren1/us-ev-charging-locations

Viewer • Updated Jul 16, 2024 • 10.3k • 40 • 3

kraina/airbnb

Viewer • Updated Jun 3, 2023 • 103k • 179 • 6

liked a model 6 months ago

mistralai/Mathstral-7B-v0.1

Text Generation • Updated Jul 31, 2024 • 3.88M • 214

reacted to isidentical's post with ❤️ 12 months ago

Post

What is the current SOTA in terms of fast personalized image generation? Most of the techniques that produce great results (which is hard to objectively measure, but subject similarity index being close to 80-90%) take either too much time (full on DreamBooth fine-tuning the base model) or or loose on the auxilary properties (high rank LoRAs).

We have been also testing face embeddings, but even with multiple samples the quality is not anywhere close to what we expect. Even on the techniques that work, high quality (studio-level) pictures seem to be a must so another avenue that I'm curious is whether there is filter/segmentation of the input samples in an automatic way that people have looked in the past?