#python #ddpm #diffusion_probabilistic #image_generation #pytorch #super_resolution

https://github.com/Janspiry/Image-Super-Resolution-via-Iterative-Refinement

#python #creative_ai #cross_modal #dalle #diffusion #disco_diffusion #generative_art #multimodal #prompts

https://github.com/jina-ai/discoart

#python #deep_learning #diffusion #image_generation #pytorch #score_based_generative_modeling

https://github.com/huggingface/diffusers

#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 #computer_vision #deep_learning #diffusion_models #image_editing #image_generation #image_manipulation #paint_by_example #pytorch #stable_diffusion

https://github.com/Fantasy-Studio/Paint-by-Example

#jupyter_notebook #diffusion #fine_ #lora #stable_diffusion

https://github.com/cloneofsimo/lora

#typescript #ai #audio #diffusion #music #nextjs #stable_diffusion #threejs

https://github.com/hmartiro/riffusion-app

#python #ai #audio #diffusers #diffusion #music #stable_diffusion

https://github.com/hmartiro/riffusion-inference

#python #artificial_intelligence #atari #deep_learning #diffusion_models #machine_learning #reinforcement_learning #research #world_models

DIAMOND is a new way to train AI agents using a technique called diffusion in world models. It allows the agent to learn and play games like Atari and even simulate environments like Counter-Strike: Global Offensive. The benefit to you is that you can easily try out these pre-trained models on your own computer by following simple installation steps. You can watch the AI play, take control yourself, and even adjust how the AI imagines the game world, making it a fun and interactive way to explore advanced AI technology.

https://github.com/eloialonso/diamond

#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

#python #3d #3d_aigc #3d_generation #diffusion_models #hunyuan3d #image_to_3d #shape #shape_generation #text_to_3d #texture_generation

Hunyuan3D 2.0 is a powerful tool that creates detailed 3D models with textures in two steps: first building the shape, then adding colors and materials. It works efficiently on standard computers (as low as 5GB VRAM for basic models) and offers multiple ways to use it, like coding, Blender plugins, or online demos, making it accessible for creating game-ready 3D assets, VR/AR content, or custom designs without needing advanced hardware.

https://github.com/Tencent/Hunyuan3D-2

#python #diffusion_models #dit #image_to_video #image_to_video_generation #text_to_video #text_to_video_generation

LTX-Video is a powerful AI model that creates high-quality, realistic videos in real time, running faster than you can watch them. It can generate videos from text descriptions, images, or existing videos, and supports advanced features like keyframe animation and video extension. You can use it online or run it locally with easy setup. It offers great control over video details, smooth motion, and works well even on consumer hardware. This helps you quickly create custom videos for storytelling, social media, or prototyping, saving time and boosting creativity with detailed, lifelike results[2][4][5].

https://github.com/Lightricks/LTX-Video

#python #comfyui #diffusion_models #dit #image_to_video #image_to_video_generation #text_to_image #text_to_image_generation

ComfyUI-LTXVideo is a tool that helps create high-quality videos from images using AI. It offers features like key frame control, improved video quality, and faster generation speeds. This means you can make smooth videos with fewer errors and more control over how they look. It also supports commercial use, so you can use the videos for business projects. The tool is designed to work well with consumer-grade GPUs, making it accessible to more users. Overall, it helps you create professional-looking videos quickly and easily.

https://github.com/Lightricks/ComfyUI-LTXVideo

#python #deep_learning #diffusion #flax #flux #hacktoberfest #image_generation #image2image #image2video #jax #latent_diffusion_models #pytorch #score_based_generative_modeling #stable_diffusion #stable_diffusion_diffusers #text2image #text2video #video2video

The Hugging Face Diffusers library is a powerful and easy-to-use tool for generating images, audio, and 3D molecular structures using advanced diffusion models. It offers ready-to-use pretrained models and flexible components like pipelines, schedulers, and model building blocks, allowing you to quickly create or customize your own diffusion-based projects. Installation is simple via pip or conda, and you can generate high-quality outputs with just a few lines of code. This library benefits you by making cutting-edge AI generation accessible, customizable, and efficient, whether you want to run models or train your own[1][2][5].

https://github.com/huggingface/diffusers