Introducing AuraFace: Open-Source Face Recognition and Identity Preservation Models
•
37
Batuhan PRO
isidentical
AI & ML interests
Fast ML inference, 100% GPU utilization, HBM3e and fast memory
Recent Activity
liked
a model
17 days ago
tencent/HunyuanVideo
Articles
Organizations
isidentical's activity
reacted to
their
post with 🚀🔥
4 months ago
Post
3148
Introducing
fal/AuraFace-v1: Commercially available & open source identity encoder model for next generation one shot personalization. Read more about it here: https://huggingface.co/blog/isidentical/auraface
posted
an
update
4 months ago
Post
3148
Introducing
fal/AuraFace-v1: Commercially available & open source identity encoder model for next generation one shot personalization. Read more about it here: https://huggingface.co/blog/isidentical/auraface
posted
an
update
4 months ago
Post
611
Added FLUX.1 pro/dev/schnell and AuraFlow v0.2 to
fal/imgsys !!! Go play with it and get us some votez
reacted to
their
post with ❤️🔥
4 months ago
Post
1788
fal/AuraFlow-v0.3 is now here with support for different aspect resolutions (w/h up to 1536px!) and much nicer aesthetics! Make sure to install the latest diffusers to get support for it.
posted
an
update
4 months ago
Post
1788
fal/AuraFlow-v0.3 is now here with support for different aspect resolutions (w/h up to 1536px!) and much nicer aesthetics! Make sure to install the latest diffusers to get support for it.
posted
an
update
6 months ago
Post
4022
Announcing the second open model in our Aura series of media models at
@fal
:
fal/AuraFlow
Try it using diffusers or ComfyUI from publicly available weights, and read more about it in our blog https://blog.fal.ai/auraflow.
Try it using diffusers or ComfyUI from publicly available weights, and read more about it in our blog https://blog.fal.ai/auraflow.
- 3 replies
posted
an
update
6 months ago
Post
1511
It is time for some Aura.
First in our series of fully open sourced / commercially available models by @fal-ai : AuraSR - a 600M parameter upscaler based on GigaGAN.
Blog: https://blog.fal.ai/introducing-aurasr-an-open-reproduction-of-the-gigagan-upscaler-2/
HF: https://huggingface.co/fal-ai/AuraSR
Code: https://github.com/fal-ai/aura-sr
Playground: https://fal.ai/models/fal-ai/aura-sr/playground
What other models would you like to see open-sourced and commercially available? :)
First in our series of fully open sourced / commercially available models by @fal-ai : AuraSR - a 600M parameter upscaler based on GigaGAN.
Blog: https://blog.fal.ai/introducing-aurasr-an-open-reproduction-of-the-gigagan-upscaler-2/
HF: https://huggingface.co/fal-ai/AuraSR
Code: https://github.com/fal-ai/aura-sr
Playground: https://fal.ai/models/fal-ai/aura-sr/playground
What other models would you like to see open-sourced and commercially available? :)
posted
an
update
7 months ago
Post
1246
One shot evaluations is hard. That is honestly what I learnt throughout the last couple of weeks trying to make imgsys.org data more and more relevant. There is just so much diversity in these models that saying one is better than other one even at a particular domain is impossible.
If you have any suggestions on how we can make the testing easier for one shot, single question image model testing; please give your suggestions under this thread so we can provide a more meaningful data point to the community!
If you have any suggestions on how we can make the testing easier for one shot, single question image model testing; please give your suggestions under this thread so we can provide a more meaningful data point to the community!
reacted to
ehristoforu's
post with 🔥
7 months ago
Post
1818
Fluently XL v4 took 4th place in the arena leaderboard imgsys.org, yay!
Model: fluently/Fluently-XL-v4
Playground with this model: fluently/Fluently-Playground
Model: fluently/Fluently-XL-v4
Playground with this model: fluently/Fluently-Playground
- 10 replies
reacted to
not-lain's
post with 👍
7 months ago
Post
1533
If you're a researcher or developing your own model 👀 you might need to take a look at huggingface's ModelHubMixin classes.
They are used to seamlessly integrate your AI model with huggingface and to save/ load your model easily 🚀
1️⃣ make sure you're using the appropriate library version
2️⃣ inherit from the appropriate class
4️⃣ push the model to the hub (or use save_pretrained method to save locally)
5️⃣ Load and initialize the model from the hub using the original class
They are used to seamlessly integrate your AI model with huggingface and to save/ load your model easily 🚀
1️⃣ make sure you're using the appropriate library version
pip install -qU "huggingface_hub>=0.22"2️⃣ inherit from the appropriate class
from huggingface_hub import PyTorchModelHubMixin
from torch import nn
class MyModel(nn.Module,PyTorchModelHubMixin):
def __init__(self, a, b):
super().__init__()
self.layer = nn.Linear(a,b)
def forward(self,inputs):
return self.layer(inputs)
first_model = MyModel(3,1)4️⃣ push the model to the hub (or use save_pretrained method to save locally)
first_model.push_to_hub("not-lain/test")5️⃣ Load and initialize the model from the hub using the original class
pretrained_model = MyModel.from_pretrained("not-lain/test")
reacted to
vikhyatk's
post with ❤️
8 months ago
Post
1757
Cool new dataset from
@isidentical
-
isidentical/moondream2-coyo-5M-captions
The VeCLIP paper showed a +3% gain while only using 14% of the data by synthetically captioning like this. You get diversity from the alt text (middle column) without having to deal with all of the noise.
The VeCLIP paper showed a +3% gain while only using 14% of the data by synthetically captioning like this. You get diversity from the alt text (middle column) without having to deal with all of the noise.
- 1 reply
reacted to
Fizzarolli's
post with 👍
8 months ago
Post
2339
Is anyone looking into some sort of decentralized/federated dataset generation or classification by humans instead of synthetically?
From my experience with trying models, a *lot* of modern finetunes are trained on what amounts to, in essence, GPT-4 generated slop that makes everything sound like a rip-off GPT-4 (refer to i.e. the Dolphin finetunes). I have a feeling that this is a lot of the reason people haven't been quite as successful as Meta's instruct tunes of Llama 3.
From my experience with trying models, a *lot* of modern finetunes are trained on what amounts to, in essence, GPT-4 generated slop that makes everything sound like a rip-off GPT-4 (refer to i.e. the Dolphin finetunes). I have a feeling that this is a lot of the reason people haven't been quite as successful as Meta's instruct tunes of Llama 3.
posted
an
update
8 months ago
Post
2105
Happy to announce https://imgsys.org -- a sister project to Chatbot Arena by lmsys -- for comparing different text guided image generation models models. Try it natively on HuggingFace: https://huggingface.co/spaces/fal-ai/imgsys
- 1 reply
posted
an
update
11 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?
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?
- 10 replies