Search Results for "visual-"
Sort By:
Showing 66 open source projects for "visual-"
View related business solutions-
$300 Free Credits for Your Google Cloud ProjectsLaunch your next project with $300 in free Google Cloud credits—no strings attached. Test, build, and deploy without risk. Use your credits across the entire Google Cloud platform to find what works best for your needs. After your credits are used, continue with always-free tier services. Only pay when you're ready to scale. Sign up in minutes and start exploring.
-
Ship Agents FasterGemini Enterprise Agent Platform lets you rapidly build, scale, govern and optimize production-ready agents grounded in your organization's data. The platform enables developers to build custom or pre-built agents for virtually any use case. New customers get $300 in free credits.
-
1
DeepSeek-OCR 2
Visual Causal Flow
DeepSeek-OCR-2 is the second-generation optical character recognition system developed to improve document understanding by introducing a “visual causal flow” mechanism, enabling the encoder to reorder visual tokens in a way that better reflects semantic structure rather than strict raster scan order. It is designed to handle complex layouts and noisy documents by giving the model causal reasoning capabilities that mimic human visual scanning behavior, enhancing OCR performance on documents with rich spatial structure. ... -
2
ComfyUI-LTXVideo
LTX-Video Support for ComfyUI
ComfyUI-LTXVideo is a bridge between ComfyUI’s node-based generative workflow environment and the LTX-Video multimedia processing framework, enabling creators to orchestrate complex video tasks within a visual graph paradigm. Instead of writing code to apply effects, transitions, edits, and data flows, users can assemble nodes that represent video inputs, transformations, and outputs, letting them prototype and automate video production pipelines visually. This integration empowers non-programmers and rapid-iteration teams to harness the performance of LTX-Video while maintaining the clarity and flexibility of a dataflow graph model. ... -
3
Kimi K2.5
Moonshot's most powerful AI model
Kimi K2.5 is Moonshot AI’s open-source, native multimodal agentic model built through continual pretraining on approximately 15 trillion mixed vision and text tokens. Based on a 1T-parameter Mixture-of-Experts (MoE) architecture with 32B activated parameters, it integrates advanced language reasoning with strong visual understanding. K2.5 supports both “Thinking” and “Instant” modes, enabling either deep step-by-step reasoning or low-latency responses depending on the task. Designed for agentic workflows, it features an Agent Swarm mechanism that decomposes complex problems into coordinated sub-agents executing in parallel. With a 256K context length and MoonViT vision encoder, the model excels across reasoning, coding, long-context comprehension, image, and video benchmarks. ... -
4
Qwen3-VL
Qwen3-VL, the multimodal large language model series by Alibaba Cloud
Qwen3-VL is the latest multimodal large language model series from Alibaba Cloud’s Qwen team, designed to integrate advanced vision and language understanding. It represents a major upgrade in the Qwen lineup, with stronger text generation, deeper visual reasoning, and expanded multimodal comprehension. The model supports dense and Mixture-of-Experts (MoE) architectures, making it scalable from edge devices to cloud deployments, and is available in both instruction-tuned and reasoning-enhanced variants. Qwen3-VL is built for complex tasks such as GUI automation, multimodal coding (converting images or videos into HTML, CSS, JS, or Draw.io diagrams), long-context reasoning with support up to 1M tokens, and comprehensive video understanding. ... -
Build Securely on AWS with Proven FrameworksMoving to the cloud brings new challenges. How can you manage a larger attack surface while ensuring great network performance? Turn to Fortinet’s Tested Reference Architectures, blueprints for designing and securing cloud environments built by cybersecurity experts. Learn more and explore use cases in this white paper.
-
5
Ideogram 4
Open image model at the forefront of design
Ideogram 4 is an open-weight text-to-image model focused on high-quality visual generation, design control, and accurate text rendering inside images. It is built for users who need more than generic image generation, especially when layout, typography, composition, color, and language understanding matter. The project introduces a structured JSON prompting workflow that gives creators more explicit control over scene details and visual constraints. -
6
SAM 3
Code for running inference and finetuning with SAM 3 model
SAM 3 (Segment Anything Model 3) is a unified foundation model for promptable segmentation in both images and videos, capable of detecting, segmenting, and tracking objects. It accepts both text prompts (open-vocabulary concepts like “red car” or “goalkeeper in white”) and visual prompts (points, boxes, masks) and returns high-quality masks, boxes, and scores for the requested concepts. Compared with SAM 2, SAM 3 introduces the ability to exhaustively segment all instances of an open-vocabulary concept specified by a short phrase or exemplars, scaling to a vastly larger set of categories than traditional closed-set models. ... -
7
Gorden Super PPT Skills
AI PPT Track Terminator, the strongest PPT Skill ever
...The orchestration skill chains both steps so users can create a polished visual deck and then recover an editable version. It is designed for Codex-based workflows and is useful for users who want more elaborate slide design than standard text-to-PPT generators provide. -
8
Moondream
Tiny vision language model
...It serves as both a playground for the author’s artistic curiosity and a resource for other creative coders interested in generative art techniques. The repository may include shaders, canvas/WebGL code, visual demos, and utilities that demonstrate how mathematical functions or noise patterns can be harnessed for compelling visuals. -
9
LTX-2.3
Official Python inference and LoRA trainer package
...Unlike most earlier video generation systems that only produced silent clips, LTX-2 combines video and audio generation in a unified architecture capable of producing coherent audiovisual scenes. The model uses a diffusion-transformer-based architecture designed to generate high-fidelity visual frames while simultaneously producing corresponding audio elements such as speech, music, ambient sound, or effects. This unified approach allows creators to generate complete multimedia sequences where motion, timing, and sound are aligned automatically. LTX-2 is designed for both research and production workflows and can generate high-resolution video clips with precise control over structure, motion, and camera behavior. -
MongoDB Atlas runs apps anywhereMongoDB Atlas gives you the freedom to build and run modern applications anywhere—across AWS, Azure, and Google Cloud. With global availability in over 115 regions, Atlas lets you deploy close to your users, meet compliance needs, and scale with confidence across any geography.
-
10
Qwen-Image-Layered
Qwen-Image-Layered: Layered Decomposition for Inherent Editablity
Qwen-Image-Layered is an extension of the Qwen series of multimodal models that introduces layered image understanding, enabling the model to reason about hierarchical visual structures — such as separating foreground, background, objects, and contextual layers within an image. This architecture allows richer semantic interpretation, enabling use cases such as scene decomposition, object-level editing, layered captioning, and more fine-grained multimodal reasoning than with flat image encodings alone. ... -
11
Depth Anything 3
Recovering the Visual Space from Any Views
Depth Anything 3 is a research-driven project that brings accurate and dense depth estimation to any input image or video, enabling foundational understanding of 3D structure from 2D visual content. Designed to work across diverse scenes, lighting conditions, and image types, it uses advanced neural networks trained on large, heterogeneous datasets, producing depth maps that reveal scene depth relationships and object surfaces with strong fidelity. The model can be applied to photography, AR/VR content creation, robotics perception, and 3D reconstruction workflows, making it versatile across industries and research domains. ... -
12
Janus
Unified Multimodal Understanding and Generation Models
Janus is a sophisticated open-source project from DeepSeek AI that aims to unify both visual understanding and image generation in a single model architecture. Rather than having separate systems for “look and describe” and “prompt and generate”, Janus uses an autoregressive transformer framework with a decoupled visual encoder—allowing it to ingest images for comprehension and to produce images from text prompts with shared internal representations. -
13
FramePack
Lets make video diffusion practical
FramePack explores compact representations for sequences of image frames, targeting tasks where many near-duplicate frames carry redundant information. The idea is to “pack” frames by detecting shared structure and storing differences efficiently, which can accelerate training or inference on video-like data. By reducing I/O and memory bandwidth, datasets become lighter to load while models still see the essential temporal variation. The repository demonstrates both packing and unpacking... -
14
Wan2.1
Wan2.1: Open and Advanced Large-Scale Video Generative Model
Wan2.1 is a foundational open-source large-scale video generative model developed by the Wan team, providing high-quality video generation from text and images. It employs advanced diffusion-based architectures to produce coherent, temporally consistent videos with realistic motion and visual fidelity. Wan2.1 focuses on efficient video synthesis while maintaining rich semantic and aesthetic detail, enabling applications in content creation, entertainment, and research. The model supports text-to-video and image-to-video generation tasks with flexible resolution options suitable for various GPU hardware configurations. ... -
15
VOID
Video Object and Interaction Deletion
VOID is an advanced AI video processing system developed by Netflix that focuses on removing objects from videos while preserving the physical and visual realism of the surrounding environment. Unlike traditional inpainting methods that only erase pixels or simple artifacts, VOID models the full interaction dynamics between objects and their environment, including shadows, reflections, and even physical consequences such as movement or balance changes. Built on top of transformer-based architectures and fine-tuned for video inpainting tasks, the system uses interaction-aware mask conditioning to ensure temporal consistency across frames. ... -
16
GLM-Image
GLM-Image: Auto-regressive for Dense-knowledge and High-fidelity Image
...It excels at generating images that include complex layouts and detailed text content, making it especially useful for posters, diagrams, info-graphics, social media graphics, and visual content that requires precise text placement and semantic alignment. Because it blends linguistic reasoning with image synthesis, GLM-Image produces visual outputs where semantic relationships and textual accuracy are prioritized alongside artistic style and realism, and its model structure enables it to handle dense visual knowledge tasks that challenge many pure diffusion models. ... -
17
FastVLM
This repository contains the official implementation of FastVLM
...The repository documents model variants, showcases head-to-head numbers against known baselines, and explains how the encoder integrates with common LLM backbones. Apple’s research brief frames FastVLM as targeting real-time or latency-sensitive scenarios, where lowering visual token pressure is critical to interactive UX. In short, it’s a practical recipe to make VLMs fast without exotic token-selection heuristics. -
18
LTX-2
Python inference and LoRA trainer package for the LTX-2 audio–video
LTX-2 is a powerful, open-source toolkit developed by Lightricks that provides a modular, high-performance base for building real-time graphics and visual effects applications. It is architected to give developers low-level control over rendering pipelines, GPU resource management, shader orchestration, and cross-platform abstractions so they can craft visually compelling experiences without starting from scratch. Beyond basic rendering scaffolding, LTX-2 includes optimized math libraries, resource loaders, utilities for texture and buffer handling, and integration points for native event loops and input systems. ... -
19
HunyuanWorld 1.0
Generating Immersive, Explorable, and Interactive 3D Worlds
...The architecture integrates panoramic proxy generation, semantic layering, and hierarchical 3D reconstruction to produce high-quality scene-scale 3D worlds from both text and images. HunyuanWorld-1.0 surpasses existing open-source methods in visual quality and geometric consistency, demonstrated by superior scores in BRISQUE, NIQE, Q-Align, and CLIP metrics. -
20
CogView4
CogView4, CogView3-Plus and CogView3(ECCV 2024)
CogView4 is the latest generation in the CogView series of vision-language foundation models, developed as a bilingual (Chinese and English) open-source system for high-quality image understanding and generation. Built on top of the GLM framework, it supports multimodal tasks including text-to-image synthesis, image captioning, and visual reasoning. Compared to previous CogView versions, CogView4 introduces architectural upgrades, improved training pipelines, and larger-scale datasets, enabling stronger alignment between textual prompts and generated visual content. It emphasizes bilingual usability, making it well-suited for cross-lingual multimodal applications. ... -
21
Qwen3.5
Qwen3.5 is the large language model series developed by Qwen team
...Qwen3.5 builds on earlier Qwen generations by improving multilingual understanding, reasoning ability, and efficiency, while also introducing native multimodal capabilities that allow the model to work with both language and visual inputs. Architecturally, the system leverages modern large-scale training techniques and mixture-of-experts style efficiency so that very large parameter counts can be used while keeping inference practical. -
22
HunyuanVideo-Foley
Multimodal Diffusion with Representation Alignment
HunyuanVideo-Foley is a multimodal diffusion model from Tencent Hunyuan for high-fidelity Foley (sound effects) audio generation synchronized to video scenes. It is designed to generate audio that matches both visual content and textual semantic cues, for use in video production, film, advertising, games, etc. The model architecture aligns audio, video, and text representations to produce realistic synchronized soundtracks. Produces high-quality 48 kHz audio output suitable for professional use. Hybrid architecture combining multimodal transformer blocks and unimodal refinement blocks. ... -
23
DINOv3
Reference PyTorch implementation and models for DINOv3
DINOv3 is the third-generation iteration of Meta’s self-supervised visual representation learning framework, building upon the ideas from DINO and DINOv2. It continues the paradigm of learning strong image representations without labels using teacher–student distillation, but introduces a simplified and more scalable training recipe that performs well across datasets and architectures. DINOv3 removes the need for complex augmentations or momentum encoders, streamlining the pipeline while maintaining or improving feature quality. ... -
24
DeepSeek VL2
Mixture-of-Experts Vision-Language Models for Advanced Multimodal
...or “Generate a caption appropriate to context”). The model supports both image understanding (vision tasks) and multimodal reasoning, and is likely used as a component in agent systems to process visual inputs as context for downstream tasks. The repository includes evaluation results (e.g. image/text alignment scores, common VL benchmarks), configuration files, and model weights (where permitted). While the internal architecture details are not fully documented publicly, the repo suggests that VL2 introduces enhancements over prior vision-language models (e.g. better scaling, cross-modal attention, more robust alignment) to improve grounding and multimodal understanding. -
25
Seamless Communication
Foundational Models for State-of-the-Art Speech and Text Translation
...The system architecture includes a real-time multimodal signal pipeline for audio, video, and sensor data, a dialog manager that can decide when to act (speak, gesture, point) or query, and a cross-modal reasoning layer that fuses perception with semantic context. The research prototype includes components for visual grounding (understanding when a user references something in view), gesture recognition and synthesis, and turn-taking mechanisms that mirror human conversational timing. Because latency and synchronization are critical, the codebase invests in asynchronous scheduling, overlap of perception and reasoning, and fast fallback responses.