Post
28
Are you an AI Researcher, Enthusiast, Founder or else and live in or close by to Zürich? Drop in for an Aperol Spritz and Euromaxx on our Balcony on the 14th of August.
- 1 reply
AI & ML interests
RLHF, Model Evaluation, Benchmarks, Data Labeling, Human Feedback, Computer Vision, Image Generation, Video Generation, LLMs, Translations
Recent Activity
View all activity
jasoncorkill
posted an update about 5 hours ago
maalber
published a
dataset 14 days ago
eliasteikari
updated a
dataset 24 days ago
maalber
updated a
dataset 28 days ago
eliasteikari
published a
dataset 29 days ago
seedance 2.0 data
1
#1 opened 3 months ago
by 
orsond
What is the License of data?
1
#3 opened 6 months ago
by 
qinrongcui
LinoGiger
published a
dataset 7 months ago
LinoGiger
updated a
dataset 7 months ago
LinoGiger
published a
dataset 8 months ago
LinoGiger
updated a
dataset 8 months ago
maalber
updated a
dataset 8 months ago
LinoGiger
published a
dataset 8 months ago
LinoGiger
updated a
dataset 8 months ago
RapidataAI
published a
dataset 8 months ago
LinoGiger
updated a
dataset 8 months ago
jasoncorkill
posted an update 8 months ago
Post
4747
Do you remember https://thispersondoesnotexist.com/ ? It was one of the first cases where the future of generative media really hit us. Humans are incredibly good at recognizing and analyzing faces, so they are a very good litmus test for any generative image model.
But none of the current benchmarks measure the ability of models to generate humans independently. So we built our own. We measure the models ability to generate a diverse set of human faces and using over 20'000 human annotations we ranked all of the major models on their ability to generate faces. Find the full ranking here:
https://app.rapidata.ai/mri/benchmarks/68af24ae74482280b62f7596
We have release the full underlying data publicly here on huggingface: Rapidata/Face_Generation_Benchmark
But none of the current benchmarks measure the ability of models to generate humans independently. So we built our own. We measure the models ability to generate a diverse set of human faces and using over 20'000 human annotations we ranked all of the major models on their ability to generate faces. Find the full ranking here:
https://app.rapidata.ai/mri/benchmarks/68af24ae74482280b62f7596
We have release the full underlying data publicly here on huggingface: Rapidata/Face_Generation_Benchmark
LinoGiger
updated a
dataset 9 months ago
jasoncorkill
updated a
dataset 9 months ago
jasoncorkill
published a
dataset 9 months ago