Projects sharing features with TurboDiffusion

MAGI-1 is an autoregressive video generation model designed to synthesize high-resolution video sequences from text prompts and image references. It functions as a generative system for text-to-video, image-to-video, and video-to-video transformations. The model utilizes an autoregressive architecture that treats spatio-temporal patches as a sequence of discrete tokens to maintain temporal motion. It employs a variational autoencoder to compress the spatial and temporal dimensions of video data and uses distillation-based step scaling to allow for inference budget control. The system integra

StoryDiffusion is a generative AI system designed for consistent character image and video generation. It utilizes a pluggable cross-attention module to inject shared character representations into pretrained diffusion models, allowing for visual identity stability across multiple images and scenes without retraining the base model. The project features a video generation pipeline that produces temporally coherent sequences from text prompts or condition images. It employs a latent space motion interpolator to predict intermediate frames and semantic motion, enabling long-range video generati

Text2Video-Zero is a text-to-video diffusion model and framework designed to synthesize temporally consistent video sequences from textual prompts. It functions as a zero-shot video generator, repurposing pre-trained image diffusion models to create video content without requiring additional training on video datasets. The system includes a conditional video synthesizer that allows for guided generation using depth, edge, or pose maps to control structural layout and movement. It also provides text-based video editing capabilities to modify the style or content of existing video clips through

Videocrafter is a latent diffusion model designed for AI video synthesis. It functions as both a text-to-video and image-to-video generation system, synthesizing high-quality video sequences from descriptive text prompts or static image inputs. The model utilizes a diffusion-based neural network to transform inputs into animated content, ensuring visual consistency and temporal coherence throughout the generated sequences. This allows for the creation of custom video clips and the animation of static images into fluid motion.

CogVideo is a generative video framework that uses diffusion models and transformer-based architectures to synthesize high-resolution video clips. It functions as both a text-to-video and image-to-video generator, converting textual descriptions or static images into temporal visual sequences. The system integrates large language model capabilities to expand short user prompts into detailed descriptions for better visual alignment. It supports the animation of static images through latent seeding and provides the ability to extend the length of existing video sequences. The project includes

ComfyUI-nunchaku is a 4-bit diffusion inference engine and a set of nodes for running low-precision quantized diffusion models within ComfyUI visual workflows. It provides a backend that reduces memory overhead and increases generation speed for transformer models. The project includes specialized tools for identity-preserving generation and an image-to-image guidance toolkit that uses depth maps and reference images. It also features a multimodal visual question answering implementation and a utility for merging multiple quantized model files into single unified files. The engine covers a b

Open-Sora is a video generation framework designed to produce cinematic sequences from text prompts and images. It functions as a generative system that transforms written descriptions or reference images into video content featuring realistic textures and lighting. The project includes a dedicated prompt engineering tool that uses large language models to expand simple user inputs into detailed descriptions. It also features a motion controller for adjusting movement intensity in generated sequences and evaluating motion levels in existing video files. The framework incorporates text-to-vid

Sana is a framework for high-resolution image and video synthesis based on a linear diffusion transformer. It provides a toolkit for the training, fine-tuning, and execution of text-to-image and text-to-video models, as well as a video generative world model capable of simulating physical environments with precise spatial control. The project is distinguished by its use of linear complexity layers to handle high resolutions and its support for long-form, minute-length video generation in real time. It implements a two-stage inference paradigm that separates structural generation from visual t

SkyReels-V2 is a video generation system that creates, extends, and refines video clips from text descriptions, images, or both. It operates as a diffusion-based video generation model that can produce videos of any duration by denoising frames sequentially, with each new frame conditioned on the ones that came before it. The system supports generating videos from scratch using text prompts, starting from a single image and producing subsequent frames, or constraining both the first and last frames to match user-provided images. What distinguishes SkyReels-V2 is its combination of infinite-le

LongCat-Video is a collection of specialized models for video synthesis, featuring a large language model based architecture for creating high-resolution videos from text, images, or existing sequences. It includes dedicated systems for text-to-video generation, image-to-video animation, and the creation of talking avatars. The project provides specific capabilities for extending the length of existing clips through a video continuation model that predicts subsequent frames. It also enables the synchronization of character lip movements with audio and text prompts to produce speaking videos.

This project is a research-oriented PyTorch framework designed for the implementation and training of generative video diffusion models. It provides a modular toolkit that extends standard image-based diffusion techniques into three dimensions, enabling the synthesis of coherent video sequences through iterative denoising processes. The framework distinguishes itself by utilizing factored space-time attention, which decomposes high-dimensional video data into separate spatial and temporal layers to maintain motion consistency while managing computational complexity. It supports multi-modal tr

AnimateDiff is a latent diffusion video generator and text-to-video diffusion framework. It converts existing text-to-image diffusion models into animation generators by applying specialized motion modules, allowing for the creation of video sequences without modifying the original base model. The project provides an image-to-video animation framework that uses sparse RGB images, sketches, or structural keyframe constraints to guide generation. It further distinguishes itself with a motion adapter system that injects cinematic camera movements, such as zooming, panning, and tilting, into anim

AnimateAnyone is an appearance-preserving video synthesizer designed for character animation from a single static image. It functions as a diffusion image-to-video generator that transforms a source image into a high-fidelity video sequence while maintaining consistent character identity, clothing, and visual details across all frames. The system enables video-driven character reenactment by transferring motions, facial expressions, and body movements from a reference video onto a static character. It employs pose-guided video generation to control movement via skeleton keypoints and pose sig

Nunchaku is a 4-bit model quantization library and diffusion model inference engine designed to run large-scale neural networks on consumer GPUs. It functions as a GPU-accelerated optimizer that reduces VRAM usage and increases inference speed through weight compression and memory management. The project utilizes low-rank weight decomposition and SVD weight quantization to compress models to four-bit precision while maintaining visual fidelity. It employs kernel-level operator fusion to minimize data movement and hardware-aware precision mapping to adjust numerical precision based on the unde

Lingbot-world is an interactive world simulator and framework for generating high-fidelity video environments from text and image prompts. It functions as a video generation system designed to create controllable simulations for applications such as robotics learning and gaming. The project includes a video motion controller that directs camera and object movement using transformation matrices and action strings. It utilizes a quantized inference engine to reduce memory usage and accelerate the generation of video sequences. The system covers a range of optimization techniques, including fou

EchoMimic is a multimodal human animation framework and diffusion-based video generator. It produces lifelike facial and semi-body animations of a reference image by synthesizing motion and appearance from various source data. The system enables portrait animation driven by audio, pose sequences, or driver videos. It features a landmark conditioning tool that allows for the precise control of facial movements by modifying specific landmark points. The framework covers multi-modal motion synthesis and the synchronization of reference images to match the physical movements of a target driver.

I've made everythign less reliant on torch.compile for VRAM efficiency, so things should work better even without it. Also figured workaround for some issues when using compile that made first run use drastically more VRAM, issue I battled with myself a lot.

CogVideo is a video generation framework and large language model architecture designed for synthesizing high-resolution video clips from natural language descriptions and images. It functions as a text-to-video and image-to-video generator, while also providing a model for video captioning to analyze visual content into descriptive text summaries. The system supports animating static images into motion sequences and transforming series of images into video based on prompts. It includes capabilities for extending the length of generated video clips to create longer sequences of motion. The f

Intel XPU LLM Acceleration Library is a toolkit designed to accelerate large language model inference and finetuning on Intel CPUs, GPUs, and NPUs. It provides a distributed inference engine for scaling models across multiple accelerators, a multimodal model runtime for vision and speech tasks, and a low-bit model quantization tool for converting weights into INT4, FP8, and GGUF formats. The project features a parameter-efficient finetuning framework that enables model adaptation using QLoRA and DPO on Intel hardware. It distinguishes itself by providing specialized optimizations for Intel XP

Wan2.2 is a generative video artificial intelligence system designed to synthesize visual media by interpreting natural language instructions. It functions as a text-to-video diffusion model that transforms written concepts into coherent motion sequences through deep learning and latent space manipulation. The system utilizes a transformer-based architecture to process video data as a series of tokens, allowing it to capture complex spatial and temporal relationships. By employing a temporal attention mechanism, the model maintains visual consistency across frames, while its latent space appr

Wan2.1 is a generative video synthesis framework that provides foundation models for creating high-fidelity video sequences and static images from descriptive text prompts. The system utilizes a unified architecture trained on both static and dynamic datasets, allowing it to function as a comprehensive tool for visual media creation. The framework distinguishes itself through a transformer-based temporal modeling approach that ensures structural coherence and consistent motion across video frames. It supports multi-resolution latent scaling, enabling the generation of content in various aspec

bert4keras is a lightweight reimplementation of the BERT transformer architecture for the Keras deep learning framework. It serves as a natural language processing toolkit and transformer model library used for text classification, sequence labeling, and semantic embedding extraction. The framework includes a sequence-to-sequence model system for question answering and text generation, as well as a model inference server to deploy trained transformers as web APIs for real-time predictions. Capabilities cover a broad range of natural language understanding tasks, including reading comprehensi

CogVLM is a multimodal large language model designed for visual reasoning and multi-turn dialogue. It functions as a visual grounding model and a quantized vision model, combining text and image processing to perform complex understanding and maintain context across visual inputs. The project includes capabilities as a GUI automation agent, allowing it to analyze application screenshots, plan operational steps, and return precise screen coordinates for interface interaction. It further supports visual grounding by generating bounding box coordinates to map text descriptions to specific spatia

This repository provides a collection of reference implementations and code examples for training and deploying machine learning models using the MLX framework. It serves as a practical guide for executing distributed training, fine-tuning large language models, converting model weights, and implementing multimodal generative workflows. The project distinguishes itself through specialized examples for local hardware execution, featuring weight quantization to reduce memory usage and low-rank adaptation for parameter-efficient fine-tuning. It also includes scripts for transforming external mod

Genkit is an open-source framework for building AI-powered applications. It provides a unified interface for connecting to hundreds of generative AI models from multiple providers, enabling text, image, audio, and video generation through a single API. The framework structures multi-step AI interactions—including chat, retrieval-augmented generation, tool use, and agentic workflows—as composable, traceable flows with built-in streaming and state management. The framework distinguishes itself through a comprehensive developer toolkit that includes a command-line interface and a local developer

Tune-A-Video is a text-to-video diffusion framework designed to convert pretrained text-to-image diffusion models into video generators. It utilizes a spatio-temporal attention mechanism and single text-video pair training to enable the synthesis of moving sequences from text prompts. The project provides tools for one-shot video personalization, allowing a model to be tuned on a single reference video to preserve specific characters or artistic styles across new generations. It also functions as a video editor that modifies subjects, backgrounds, and styles through noise-sampling prompt guid

Stable-Video-Infinity is a video synthesis tool based on Stable Video Diffusion designed for creating long-form animations and consistent visual content. It serves as an AI video extension framework and a conditioned animation synthesizer capable of producing video sequences of arbitrary length. The project enables infinite video extension by bypassing standard model duration constraints through an error-recycling loop. It supports conditioned animation synthesis using external inputs such as image streams, audio files, or skeletal motion data to guide the generation process. The framework i