ββMartin Calvino's AI-inspired art is such an evoking meta-narrative of "art imitating tech imitating art"
https://www.martincalvino.co/paintings
#ai #art #abstract
https://www.martincalvino.co/paintings
#ai #art #abstract
ββPhilosopher AI β website to generate text with #GPT3
Tool to generate text on different topics. Sensible topics such as sex, religion or even nationality are blocked.
Great way to spread the awareness on #ai and to show nontechnical friends that #Skynet is not a problem to be concerned with yet.
Website: https://philosopherai.com/philosopher/humanity-on-mars-73ac00
#nlu #nlp
Tool to generate text on different topics. Sensible topics such as sex, religion or even nationality are blocked.
Great way to spread the awareness on #ai and to show nontechnical friends that #Skynet is not a problem to be concerned with yet.
Website: https://philosopherai.com/philosopher/humanity-on-mars-73ac00
#nlu #nlp
State of AI Report 2022 - ONLINE.pdf
22.9 MB
State of AI Report 2022
TLDR: We are moving forward and effective international collaboration is the key to progress.
Major Themes:
* New independent research labs are rapidly open sourcing the closed source output of major labs
* Safety is gaining awareness among major AI research entities
* The China-US AI research gap has continued to widen
* AI-driven scientific research continues to lead to breakthroughs
Website: https://www.stateof.ai
#report #stateofai #AI
TLDR: We are moving forward and effective international collaboration is the key to progress.
Major Themes:
* New independent research labs are rapidly open sourcing the closed source output of major labs
* Safety is gaining awareness among major AI research entities
* The China-US AI research gap has continued to widen
* AI-driven scientific research continues to lead to breakthroughs
Website: https://www.stateof.ai
#report #stateofai #AI
Forwarded from Kirill from TOP
Some might have wondered what application will #Midjourney and #ChatGPT have.
What products will creators to build with them?
Here is one of examples of such human-AI collaboration β short illustrated story on TikTok having millions of views.
https://vt.tiktok.com/ZS8MENP51/
#AI_tools
What products will creators to build with them?
Here is one of examples of such human-AI collaboration β short illustrated story on TikTok having millions of views.
https://vt.tiktok.com/ZS8MENP51/
#AI_tools
Left picture is one generated by #Midjourney with a
Right one was generated with a
Looks like Midjourney is not aware of concept of distributions yet.
#AI #AGI #vizualization
bell curve with mu = 18 sigma = 4
request.Right one was generated with a
bell curve with mu = 18 sigma = 1
request.Looks like Midjourney is not aware of concept of distributions yet.
#AI #AGI #vizualization
Forwarded from Kirill from TOP
GPT-3 for self-therapy
Just came across an interesting article about using #GPT-3 to analyze past journal entries and summarize therapy sessions for gaining new perspectives on personal struggles. Dan Shipper loaded person journal into the neural network so he could ask different questions, including asking about his own Myers-Briggs personality type (INTJ for those who wondered).
It's a powerful example of how AI tools can help individuals become more productive, effective, and happy. As we continue to see the integration of #AI in various industries, it's important for modern blue collar workers to learn how to properly work with these tools in order to stay at the peak of efficiency.
Let's embrace the future and learn to use AI to our advantage rather than to spread FUD about AI replacing workforce. It wonβt but it will enable some people to achieve more and be way more productive.
Link: https://every.to/chain-of-thought/can-gpt-3-explain-my-past-and-tell-me-my-future
#aiusecase #toolsnotactors
Just came across an interesting article about using #GPT-3 to analyze past journal entries and summarize therapy sessions for gaining new perspectives on personal struggles. Dan Shipper loaded person journal into the neural network so he could ask different questions, including asking about his own Myers-Briggs personality type (INTJ for those who wondered).
It's a powerful example of how AI tools can help individuals become more productive, effective, and happy. As we continue to see the integration of #AI in various industries, it's important for modern blue collar workers to learn how to properly work with these tools in order to stay at the peak of efficiency.
Let's embrace the future and learn to use AI to our advantage rather than to spread FUD about AI replacing workforce. It wonβt but it will enable some people to achieve more and be way more productive.
Link: https://every.to/chain-of-thought/can-gpt-3-explain-my-past-and-tell-me-my-future
#aiusecase #toolsnotactors
ββReBotNet: Fast Real-time Video Enhancement
The authors introduce a novel Recurrent Bottleneck Mixer Network (ReBotNet) method, designed for real-time video enhancement in practical scenarios, such as live video calls and video streams. ReBotNet employs a dual-branch framework, where one branch focuses on learning spatio-temporal features, and the other aims to enhance temporal consistency. A common decoder combines the features from both branches to generate the improved frame. This method incorporates a recurrent training approach that utilizes predictions from previous frames for more efficient enhancement and superior temporal consistency.
To assess ReBotNet, the authors use two new datasets that simulate real-world situations and show that their technique surpasses existing methods in terms of reduced computations, decreased memory requirements, and quicker inference times.
Paper: https://arxiv.org/abs/2303.13504
Project link: https://jeya-maria-jose.github.io/rebotnet-web/
A detailed unofficial overview of the paper: https://andlukyane.com/blog/paper-review-rebotnet
#deeplearning #cv #MachineLearning #VideoEnhancement #AI #Innovation #RealTimeVideo
The authors introduce a novel Recurrent Bottleneck Mixer Network (ReBotNet) method, designed for real-time video enhancement in practical scenarios, such as live video calls and video streams. ReBotNet employs a dual-branch framework, where one branch focuses on learning spatio-temporal features, and the other aims to enhance temporal consistency. A common decoder combines the features from both branches to generate the improved frame. This method incorporates a recurrent training approach that utilizes predictions from previous frames for more efficient enhancement and superior temporal consistency.
To assess ReBotNet, the authors use two new datasets that simulate real-world situations and show that their technique surpasses existing methods in terms of reduced computations, decreased memory requirements, and quicker inference times.
Paper: https://arxiv.org/abs/2303.13504
Project link: https://jeya-maria-jose.github.io/rebotnet-web/
A detailed unofficial overview of the paper: https://andlukyane.com/blog/paper-review-rebotnet
#deeplearning #cv #MachineLearning #VideoEnhancement #AI #Innovation #RealTimeVideo
π₯ Say Goodbye to LoRA, Hello to DoRA π€©π€©
DoRA consistently outperforms LoRA with various tasks (LLM, LVLM, etc.) and backbones (LLaMA, LLaVA, etc.)
[Paper] https://arxiv.org/abs/2402.09353
[Code] https://github.com/NVlabs/DoRA
#Nvidia
#icml #PEFT #lora #ML #ai
@opendatascience
DoRA consistently outperforms LoRA with various tasks (LLM, LVLM, etc.) and backbones (LLaMA, LLaVA, etc.)
[Paper] https://arxiv.org/abs/2402.09353
[Code] https://github.com/NVlabs/DoRA
#Nvidia
#icml #PEFT #lora #ML #ai
@opendatascience
Forwarded from Machinelearning
FoleyCrafter - ΠΌΠ΅ΡΠΎΠ΄ΠΈΠΊΠ°, ΡΠ°Π·ΡΠ°Π±ΠΎΡΠ°Π½Π½Π°Ρ Π΄Π»Ρ Π°Π²ΡΠΎΠΌΠ°ΡΠΈΡΠ΅ΡΠΊΠΎΠ³ΠΎ ΡΠΎΠ·Π΄Π°Π½ΠΈΡ Π·Π²ΡΠΊΠΎΠ²ΡΡ ΡΡΡΠ΅ΠΊΡΠΎΠ², ΡΠΈΠ½Ρ ΡΠΎΠ½ΠΈΠ·ΠΈΡΠΎΠ²Π°Π½Π½ΡΡ Ρ ΡΠ΅Π»Π΅Π²ΡΠΌ Π²ΠΈΠ΄Π΅ΠΎΡΡΠ΄ΠΎΠΌ
ΠΡΡ ΠΈΡΠ΅ΠΊΡΡΡΠ° ΠΌΠ΅ΡΠΎΠ΄Π° ΠΏΠΎΡΡΡΠΎΠ΅Π½Π° Π½Π° ΠΎΡΠ½ΠΎΠ²Π΅ ΠΏΡΠ΅Π΄Π²Π°ΡΠΈΡΠ΅Π»ΡΠ½ΠΎ ΠΎΠ±ΡΡΠ΅Π½Π½ΠΎΠΉ ΠΌΠΎΠ΄Π΅Π»ΠΈ ΠΏΡΠ΅ΠΎΠ±ΡΠ°Π·ΠΎΠ²Π°Π½ΠΈΡ ΡΠ΅ΠΊΡΡΠ° Π² Π°ΡΠ΄ΠΈΠΎ (Text2Audio). Π‘ΠΈΡΡΠ΅ΠΌΠ° ΡΠΎΡΡΠΎΠΈΡ ΠΈΠ· Π΄Π²ΡΡ ΠΊΠ»ΡΡΠ΅Π²ΡΡ ΠΊΠΎΠΌΠΏΠΎΠ½Π΅Π½ΡΠΎΠ²:
ΠΠ±Π° ΠΊΠΎΠΌΠΏΠΎΠ½Π΅Π½ΡΠ° ΡΠ²Π»ΡΡΡΡΡ ΠΎΠ±ΡΡΠ°Π΅ΠΌΡΠΌΠΈ ΠΌΠΎΠ΄ΡΠ»ΡΠΌΠΈ, ΠΊΠΎΡΠΎΡΡΠ΅ ΠΏΡΠΈΠ½ΠΈΠΌΠ°ΡΡ Π²ΠΈΠ΄Π΅ΠΎ Π² ΠΊΠ°ΡΠ΅ΡΡΠ²Π΅ Π²Ρ ΠΎΠ΄Π½ΡΡ Π΄Π°Π½Π½ΡΡ Π΄Π»Ρ ΡΠΈΠ½ΡΠ΅Π·Π° Π°ΡΠ΄ΠΈΠΎ. ΠΡΠΈ ΡΡΠΎΠΌ ΠΌΠΎΠ΄Π΅Π»Ρ Text2Audio ΠΎΡΡΠ°Π΅ΡΡΡ ΡΠΈΠΊΡΠΈΡΠΎΠ²Π°Π½Π½ΠΎΠΉ Π΄Π»Ρ ΡΠΎΡ ΡΠ°Π½Π΅Π½ΠΈΡ Π΅Π΅ ΡΠΏΠΎΡΠΎΠ±Π½ΠΎΡΡΠΈ ΠΊ ΡΠΈΠ½ΡΠ΅Π·Ρ Π°ΡΠ΄ΠΈΠΎ ΠΏΠΎΡΡΠΎΡΠ½Π½ΠΎΠ³ΠΎ ΠΊΠ°ΡΠ΅ΡΡΠ²Π°.
Π Π°Π·ΡΠ°Π±ΠΎΡΡΠΈΠΊΠΈ FoleyCrafter ΠΏΡΠΎΠ²Π΅Π»ΠΈ ΠΊΠΎΠ»ΠΈΡΠ΅ΡΡΠ²Π΅Π½Π½ΡΠ΅ ΠΈ ΠΊΠ°ΡΠ΅ΡΡΠ²Π΅Π½Π½ΡΠ΅ ΡΠΊΡΠΏΠ΅ΡΠΈΠΌΠ΅Π½ΡΡ Π½Π° Π½Π°Π±ΠΎΡΠ°Ρ Π΄Π°Π½Π½ΡΡ VGGSound ΠΈ AVSync15 ΠΏΠΎ ΠΌΠ΅ΡΡΠΈΠΊΠ°ΠΌ ΡΠ΅ΠΌΠ°Π½ΡΠΈΡΠ΅ΡΠΊΠΎΠ³ΠΎ ΡΠΎΠΎΡΠ²Π΅ΡΡΡΠ²ΠΈΡ MKL, CLIP Score, FID ΠΈ Π²ΡΠ΅ΠΌΠ΅Π½Π½ΠΎΠΉ ΡΠΈΠ½Ρ ΡΠΎΠ½ΠΈΠ·Π°ΡΠΈΠΈ Onset ACC, Onset AP.
ΠΠΎ ΡΡΠ°Π²Π½Π΅Π½ΠΈΡ Ρ ΡΡΡΠ΅ΡΡΠ²ΡΡΡΠΈΠΌΠΈ ΠΌΠ΅ΡΠΎΠ΄Π°ΠΌΠΈ Text2Audio (SpecVQGAN, Diff-Foley ΠΈ V2A-Mapper) FoleyCrafter ΠΏΠΎΠΊΠ°Π·Π°Π» Π»ΡΡΡΠΈΠ΅ ΡΠ΅Π·ΡΠ»ΡΡΠ°ΡΡ.
# Clone the Repository
git clone https://github.com/open-mmlab/foleycrafter.git
# Navigate to the Repository
cd projects/foleycrafter
# Create Virtual Environment with Conda & Install Dependencies
conda create env create -f requirements/environment.yaml
conda activate foleycrafter
# Install GiT LFS
conda install git-lfs
git lfs install
# Download checkpoints
git clone https://huggingface.co/auffusion/auffusion-full-no-adapter checkpoints/auffusion
git clone https://huggingface.co/ymzhang319/FoleyCrafter checkpoints/
# Run Gradio
python app.py --share
π ΠΠΈΡΠ΅Π½Π·ΠΈΡΠΎΠ²Π°Π½ΠΈΠ΅: Apache-2.0
πΠ‘ΡΡΠ°Π½ΠΈΡΠ° ΠΏΡΠΎΠ΅ΠΊΡΠ°
πArxiv
πΠΠΎΠ΄Π΅Π»ΠΈ Π½Π° HF
πDemo
πGithub [ Stars: 272 | Issues: 4 | Forks: 15]
@ai_machinelearning_big_data
#AI #Text2Audio #FoleyCrafter #ML
Please open Telegram to view this post
VIEW IN TELEGRAM
Please open Telegram to view this post
VIEW IN TELEGRAM
Forwarded from Machinelearning
ControlNet++ - ΡΡΠΎ Π½Π°Π±ΠΎΡ ΠΌΠΎΠ΄Π΅Π»Π΅ΠΉ ControlNet, ΡΠΎΠ±ΡΠ°Π½Π½ΡΠΉ Π½Π° Π½ΠΎΠ²ΠΎΠΉ Π°ΡΡ ΠΈΡΠ΅ΠΊΡΡΡΠ΅ ΠΈ ΡΠΏΠ°ΠΊΠΎΠ²Π°Π½Π½ΡΠΉ Π² ΠΎΠ΄ΠΈΠ½ Π΅Π΄ΠΈΠ½ΡΠΉ ΡΠ°ΠΉΠ» Π±Π΅Π· Π½Π΅ΠΎΠ±Ρ ΠΎΠ΄ΠΈΠΌΠΎΡΡΠΈ ΡΠΊΠ°ΡΠΈΠ²Π°ΡΡ Π΄ΠΎΠΏΠΎΠ»Π½ΠΈΡΠ΅Π»ΡΠ½ΡΠ΅ ΠΏΡΠ΅ΠΏΡΠΎΡΠ΅ΡΡΠΎΡΡ ΠΈ Π½Π°Π±ΠΎΡΡ ΠΌΠΎΠ΄Π΅Π»Π΅ΠΉ.
ΠΠ±Π½ΠΎΠ²Π»Π΅Π½ΠΈΠ΅ ProMaΡ Π²ΠΊΠ»ΡΡΠ°Π΅Ρ Π² ΡΠ΅Π±Ρ Π²Π΅ΡΡ ΡΡΡΠ΅ΡΡΠ²ΡΡΡΠΈΠΉ Π½Π°Π±ΠΎΡ ControlNet Union, Π² ΠΊΠΎΡΠΎΡΡΠΉ Π±ΡΠ»ΠΈ Π΄ΠΎΠ±Π°Π²Π»Π΅Π½Ρ Π²ΠΎΠ·ΠΌΠΎΠΆΠ½ΠΎΡΡΠΈ ΠΊΠΎΠΌΠ±ΠΈΠ½Π°ΡΠΈΠΈ Π½Π΅ΡΠΊΠΎΠ»ΡΠΊΠΈΡ ΡΠΈΠΏΠΎΠ² ControlNet ΠΊ ΠΎΠ΄Π½ΠΎΠΌΡ ΠΈΡΡ ΠΎΠ΄Π½ΠΎΠΌΡ ΠΈΠ·ΠΎΠ±ΡΠ°ΠΆΠ΅Π½ΠΈΡ ΠΈ Π½ΠΎΠ²ΡΠ΅ ΡΡΠ½ΠΊΡΠΈΠΈ Tile Deblur, Tile Superresolution, Tile Variation, Inpaint ΠΈ Outpaint.
C ΡΡΠ΅ΡΠΎΠΌ ΠΎΠ±Π½ΠΎΠ²Π»Π΅Π½ΠΈΡ, Π½Π°Π±ΠΎΡ ControlNet ProMax Π²ΡΠΏΠΎΠ»Π½ΡΠ΅Ρ 12 ΡΡΠ½ΠΊΡΠΈΠΉ ΠΈ 5 Π΄ΠΎΠΏΠΎΠ»Π½ΠΈΡΠ΅Π»ΡΠ½ΡΡ ΠΌΠ΅ΡΠΎΠ΄ΠΈΠΊ ΡΠ΅Π΄Π°ΠΊΡΠΈΡΠΎΠ²Π°Π½ΠΈΡ ΠΈΠ·ΠΎΠ±ΡΠ°ΠΆΠ΅Π½ΠΈΠΉ:
Π Π°ΡΡ ΠΈΡΠ΅ΠΊΡΡΡΠ΅ ControlNet++ Π±ΡΠ»ΠΈ ΡΠ°Π·ΡΠ°Π±ΠΎΡΠ°Π½Ρ Π΄Π²Π° Π½ΠΎΠ²ΡΡ ΠΌΠΎΠ΄ΡΠ»Ρ: Condition Transformer ΠΈ Control Encoder, ΠΊΠΎΡΠΎΡΡΠ΅ ΡΠ»ΡΡΡΠ°ΡΡ ΠΏΡΠ΅Π΄ΡΡΠ°Π²Π»Π΅Π½ΠΈΠ΅ ΠΈ ΠΎΠ±ΡΠ°Π±ΠΎΡΠΊΡ ΡΡΠ»ΠΎΠ²ΠΈΠΉ Π² ΠΌΠΎΠ΄Π΅Π»ΠΈ.
ΠΠ°ΠΆΠ΄ΠΎΠΌΡ ΡΡΠ»ΠΎΠ²ΠΈΡ Π½Π°Π·Π½Π°ΡΠ°Π΅ΡΡΡ ΡΠ½ΠΈΠΊΠ°Π»ΡΠ½ΡΠΉ ΠΈΠ΄Π΅Π½ΡΠΈΡΠΈΠΊΠ°ΡΠΎΡ ΡΠΈΠΏΠ° ΡΠΏΡΠ°Π²Π»Π΅Π½ΠΈΡ, ΠΊΠΎΡΠΎΡΡΠΉ ΠΏΡΠ΅ΠΎΠ±ΡΠ°Π·ΡΠ΅ΡΡΡ Π² ΡΠΌΠ±Π΅Π΄Π΄ΠΈΠ½Π³ΠΈ.
Condition Transformer ΠΏΠΎΠ·Π²ΠΎΠ»ΡΠ΅Ρ ΠΎΠ±ΡΠ°Π±Π°ΡΡΠ²Π°ΡΡ Π½Π΅ΡΠΊΠΎΠ»ΡΠΊΠΎ ΡΡΠ»ΠΎΠ²ΠΈΠΉ ΠΎΠ΄Π½ΠΎΠ²ΡΠ΅ΠΌΠ΅Π½Π½ΠΎ, ΠΈΡΠΏΠΎΠ»ΡΠ·ΡΡ ΠΎΠ΄ΠΈΠ½ ΠΊΠΎΠ΄ΠΈΡΠΎΠ²ΡΠΈΠΊ ΠΈ Π²ΠΊΠ»ΡΡΠ°Π΅Ρ ΡΠ»ΠΎΠΉ ΡΡΠ°Π½ΡΡΠΎΡΠΌΠ΅ΡΠ° Π΄Π»Ρ ΠΎΠ±ΠΌΠ΅Π½Π° ΠΈΠ½ΡΠΎΡΠΌΠ°ΡΠΈΠ΅ΠΉ ΠΌΠ΅ΠΆΠ΄Ρ ΠΈΡΡ ΠΎΠ΄Π½ΡΠΌ ΠΈΠ·ΠΎΠ±ΡΠ°ΠΆΠ΅Π½ΠΈΠ΅ΠΌ ΠΈ ΡΡΠ»ΠΎΠ²Π½ΡΠΌΠΈ ΠΈΠ·ΠΎΠ±ΡΠ°ΠΆΠ΅Π½ΠΈΡΠΌΠΈ.
Condition Encoder ΡΠ²Π΅Π»ΠΈΡΠΈΠ²Π°Π΅Ρ ΠΊΠΎΠ»ΠΈΡΠ΅ΡΡΠ²ΠΎ ΠΊΠ°Π½Π°Π»ΠΎΠ² ΡΠ²Π΅ΡΡΠΊΠΈ Π΄Π»Ρ ΠΏΠΎΠ²ΡΡΠ΅Π½ΠΈΡ ΠΏΡΠ΅Π΄ΡΡΠ°Π²ΠΈΡΠ΅Π»ΡΠ½ΠΎΠΉ ΡΠΏΠΎΡΠΎΠ±Π½ΠΎΡΡΠΈ, ΡΠΎΡ ΡΠ°Π½ΡΡ ΠΎΡΠΈΠ³ΠΈΠ½Π°Π»ΡΠ½ΡΡ Π°ΡΡ ΠΈΡΠ΅ΠΊΡΡΡΡ.
Π’Π°ΠΊΠΆΠ΅ Π±ΡΠ»Π° ΠΈΡΠΏΠΎΠ»ΡΠ·ΠΎΠ²Π°Π½Π° Π΅Π΄ΠΈΠ½Π°Ρ ΡΡΡΠ°ΡΠ΅Π³ΠΈΡ ΠΎΠ±ΡΡΠ΅Π½ΠΈΡ, ΠΊΠΎΡΠΎΡΠ°Ρ ΠΎΠ΄Π½ΠΎΠ²ΡΠ΅ΠΌΠ΅Π½Π½ΠΎ ΠΎΠΏΡΠΈΠΌΠΈΠ·ΠΈΡΠΎΠ²Π°Π»Π° ΡΡ ΠΎΠ΄ΠΈΠΌΠΎΡΡΡ Π΄Π»Ρ ΠΎΠ΄ΠΈΠ½ΠΎΡΠ½ΡΡ ΡΡΠ»ΠΎΠ²ΠΈΠΉ ΠΈ ΡΠΏΡΠ°Π²Π»ΡΠ»Π° ΡΠ»ΠΈΡΠ½ΠΈΠ΅ΠΌ ΠΌΠ½ΠΎΠΆΠ΅ΡΡΠ²Π΅Π½Π½ΡΡ ΡΡΠ»ΠΎΠ²ΠΈΠΉ, ΠΏΠΎΠ²ΡΡΠ°Ρ ΡΡΡΠΎΠΉΡΠΈΠ²ΠΎΡΡΡ ΡΠ΅ΡΠΈ ΠΈ Π΅Π΅ ΡΠΏΠΎΡΠΎΠ±Π½ΠΎΡΡΡ ΠΊ Π³Π΅Π½Π΅ΡΠ°ΡΠΈΠΈ ΠΊΠ°ΡΠ΅ΡΡΠ²Π΅Π½Π½ΡΡ ΠΈΠ·ΠΎΠ±ΡΠ°ΠΆΠ΅Π½ΠΈΠΉ.
ControlNet Pro Max ΠΏΠΎΠ΄Π΄Π΅ΡΠΆΠΈΠ²Π°Π΅Ρ ΡΠ°Π±ΠΎΡΡ Ρ Π»ΡΠ±ΠΎΠΉ Π³Π΅Π½Π΅ΡΠ°ΡΠΈΠ²Π½ΠΎΠΉ ΠΌΠΎΠ΄Π΅Π»ΡΡ ΡΠ΅ΠΌΠ΅ΠΉΡΡΠ²Π° Stable Diffusion XL. ΠΠΎΠ΄Π΄Π΅ΡΠΆΠΊΠ° ΡΠ΅ΠΌΠ΅ΠΉΡΡΠ²Π° Stable Diffusion 3 Π½Π°Ρ ΠΎΠ΄ΠΈΡΡΡ Π² ΡΠ°Π·ΡΠ°Π±ΠΎΡΠΊΠ΅.
@ai_machinelearning_big_data
#AI #ControlNet #ML #Diffusers #SDXL
Please open Telegram to view this post
VIEW IN TELEGRAM
Please open Telegram to view this post
VIEW IN TELEGRAM