Do you have a project in your
mind? Keep connect to me.

Contact Me

Mobile +573208278067
[email protected] [email protected]
Bogotá CO, Madrid ES
Toronto CA

Portfolio Details

Creating video from text

Working on a AI model that can create realistic and imaginative scenes from text instructions.

Training AI to comprehend and replicate the dynamics of the physical world, aiming to develop models that assist individuals in solving real-world challenges through interaction.

Testing parts and components on text-to-video generation model. Trying create videos preserving visual fidelity and alignment with the user's input.

Project Info: Confidential

Category:

Artwork Video with RNN, Difussion Transformers, Deep learning & LLM.

Infrastructure:

AWS & Kubernetes

ML Frameworks:

PyTorch, TensorFlow, Keras, Parallel Distrubution.

Patent:

In process

Pending Issues:

Quality, reality, flexibility, accuracity, escalability.

Prev Project

Next Project

#Computer Vision, #TextToImage, #LLM Inference, #MusicGen, #TrackChannels, #GenAudio, #Speech-shyntetize, #ImageRemoveBackground, #ImageRestoration, #FaceID, #FaceSwapperEnhancer, #VirtualTry-On, #TextToMusic, #AudioEdition, #DeepFake, #CaptionsMusicTracks, #CaptionsYoutube, #TextToSpeech, #VideoGeneration, #ImageTextEdit, #ImageMaterialTransfer, #Yolo, #ImageAnalisis, #Render3d, #AITown, #CloneVoice

Do you have a project in your mind? Keep connect to me.