#jupyter_notebook #deep_learning #generative_model #image_animation #motion_retargeting

https://github.com/AliaksandrSiarohin/first-order-model

#python #alae #autoencoder #celeba #celeba_hq #computer_vision #cvpr2020 #deep_learning #face_generation #ffhq #gan #generative_adversarial_network #generative_model #machine_learning #neural_network #paper #paper_implementations #pytorch #pytorch_implementation #stylegan

https://github.com/podgorskiy/ALAE

#python #audio #generative_model #music #paper #pytorch #transformer #vq_vae

https://github.com/openai/jukebox

#python #artificial_intelligence #generative_adversarial_network #generative_model #machine_learning #pytorch

https://github.com/lucidrains/stylegan2-pytorch

#other #diffusion_models #generative_model #machine_learning #score_based_models

https://github.com/heejkoo/Awesome-Diffusion-Models

#other #diffusion_models #generative_adversarial_network #generative_model #image_to_image_translation #stable_diffusion #survey #text_to_image #vae

https://github.com/YangLing0818/Diffusion-Models-Papers-Survey-Taxonomy

#python #auto_regressive_model #autoregressive_models #diffusion_models #generative_ai #generative_model #gpt #gpt_2 #image_generation #large_language_models #neurips #transformers #vision_transformer

VAR (Visual Autoregressive Modeling) is a new way to generate images that improves upon existing methods. It uses a "next-scale prediction" approach, which means it generates images from coarse to fine details, unlike the traditional method of predicting pixel by pixel. This makes VAR models better than diffusion models for the first time. You can try VAR on a demo website and generate images interactively, which is fun and easy. VAR also follows power-law scaling laws, making it efficient and scalable. The benefit to you is that you can create high-quality images quickly and easily, and even explore technical details through provided scripts and models.

https://github.com/FoundationVision/VAR

#python #3d_creation #3d_generation #aigc #diffusion_models #generative_model #image_to_3d

DreamCraft3D is a method to create highly detailed and realistic 3D objects using a combination of 2D reference images and advanced algorithms. It ensures that the 3D objects look consistent from all angles and have realistic textures. This is achieved by using a special technique called "Bootstrapped Score Distillation" which improves both the shape and texture of the 3D object in a way that reinforces each other. The benefit to the user is that they can generate very realistic 3D models quickly and accurately, which can be useful for various applications such as video games, movies, and architectural design.

https://github.com/deepseek-ai/DreamCraft3D