Search Results for "diffusion" - Page 4
Sort By:
115 projects for "diffusion" with 1 filter applied:
-
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.
-
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.
-
1
Anse
Supercharged experience for multiple models such as ChatGPT
Anse is a modern, polished web UI built to serve as a unified interface for interacting with multiple AI-model backends (such as OpenAI’s models, DALL-E, Stable Diffusion, etc.). It emphasizes a clean, user-friendly experience and supports different conversation modes (single prompt, continuous dialogue, image generation, etc.). Anse uses client-side storage (IndexDB) to keep session history locally, prioritizing user privacy and avoiding automatic uploads of sensitive chat content. It is responsive and optimized for mobile, supports dark mode, and is designed for deployment in a variety of environments (Vercel, Netlify, Docker, etc.). ... -
2
DreamBooth Dataset
Text-to-Image Diffusion Models for Subject-Driven Generation
...This method addresses a common limitation of general-purpose diffusion models, which often struggle to faithfully reproduce lesser-known or custom subjects without extensive retraining. -
3
Stable Diffusion
A latent text-to-image diffusion model
Stable Diffusion is a widely used open-source latent text-to-image diffusion model developed by the CompVis group for generating high-quality images from natural language prompts. The model operates by conditioning a diffusion process on text embeddings produced by a CLIP text encoder, enabling detailed and controllable image synthesis. It was trained on large-scale image datasets and later fine-tuned to produce 512×512 images with strong visual fidelity. -
4
Riffusion
Real-time music generation using stable diffusion techniques AI
Riffusion (hobby) is a Python-based open source library designed for real-time music and audio generation using stable diffusion techniques. Riffusion (hobby) works by generating and manipulating spectrogram images, which are then converted into playable audio clips, effectively bridging image-based diffusion models with sound synthesis. It implements a diffusion pipeline that supports prompt interpolation, allowing smooth transitions between different musical styles or prompts over time. ... -
$300 Free Credits to Build on Google CloudPut your $300 in credit toward real workloads, then keep building with free monthly usage for 20+ products. No commitment and no charge until you upgrade.
-
5
Point-E
Point cloud diffusion for 3D model synthesis
...Its principal advantage is speed: it can generate 3D assets in just 1–2 minutes on a single GPU, which is significantly faster than many competing text-to-3D models. The model works via a two-stage diffusion approach: first, it uses a text → image diffusion network to produce a synthetic 2D view consistent with the prompt; then a second diffusion model converts that image into a 3D point cloud. While it does not match the fine detail of some slower methods, the tradeoff in speed makes it practical for prototyping and interactive 3D generation. ... -
6
DiffSinger
Singing Voice Synthesis via Shallow Diffusion Mechanism
DiffSinger is an open-source PyTorch implementation of a diffusion-based acoustic model for singing-voice synthesis (SVS) and also text-to-speech (TTS) in a related variant. The core idea is to view generation of a sung voice (mel-spectrogram) as a diffusion process: starting from noise, the model iteratively “denoises” while being conditioned on a music score (lyrics, pitch, musical timing). -
7
Stable Diffusion Web UI
Feature showcase for stable-diffusion-webui
This repository curates a living gallery of examples that demonstrate what the Stable Diffusion Web UI and its ecosystem can do. It documents practical recipes that pair prompts with parameters, samplers, upscalers, and extensions so others can reproduce results reliably. The focus is on education by example: side-by-side comparisons reveal how settings like CFG scale, denoising strength, schedulers, or ControlNet inputs change an image. -
8
Cross Attention Control
Unofficial implementation of "Prompt-to-Prompt Image Editing
Cross Attention Control is an unofficial Stable Diffusion implementation of Prompt-to-Prompt image editing with cross-attention control. It modifies diffusion-model attention maps during inference so prompt changes can produce more controlled edits. The method is designed to avoid manual masks while requiring no additional training or fine-tuning. The notebooks include examples for editing images generated from the same seed. -
9
Guided Diffusion
Codebase for Diffusion Models Beat GANS on Image Synthesis
The guided-diffusion repository is centered on diffusion models for image synthesis, with a focus on classifier guidance and improvements over earlier diffusion frameworks. It is derived from OpenAI’s improved-diffusion work, enhanced to include guided generation where a classifier (or other guidance mechanism) can steer sampling toward desired classes or attributes. -
Custom VMs From 1 to 96 vCPUs With 99.95% UptimeLive migration and automatic failover keep workloads online through maintenance. One free e2-micro VM every month.
-
10
ViennaSHE is a modern semiconductor device simulator for 1D, 2D and 3D device simulation. It relies on deterministic solutions of the Boltzmann Transport Equation using Spherical Harmonics Expansions.
-
11
Cantera is a suite of object-oriented software tools for problems involving chemical kinetics, thermodynamics, and/or transport processes. It can be used from MATLAB, Python, C++, or Fortran.
-
12
PixelFlow
A Processing/Java library for high performance GPU-Computing (GLSL)
PixelFlow is a Processing library focused on advanced graphics and visual effects, offering an extensive suite of GPU-based tools for visual artists, researchers, and creative coders. It enables real-time simulation and rendering of complex effects such as fluid dynamics, reaction-diffusion systems, soft shadows, and more, all powered by GLSL shaders. Its modular structure allows for chaining and composing various visual effects easily, making it ideal for installations, performances, and visual experimentation. -
13
BioFVM
3-D diffusion solver for biological problems
BioFVM is an open source diffusive transport solver for biological problems. It can solve for the diffusion of tens or hundreds of substrates on large 3-D domains. For simplicity, the code has minimal external dependencies. BioFVM was first published in: A. Ghaffarizadeh, S.H. Friedman, and P. Macklin. BioFVM: an efficient, parallelized diffusive transport solver for 3-D biological simulations. Bioinformatics 32(8): 1156-8, 2016. -
14
Stochastic simulator for signaling pathways occuring in biological cells. Handles reaction-diffusion processes in 3D tetrahedral meshes. Please check our new repository: https://github.com/CNS-OIST/STEPS
-
15
LSDMap
Locally-Scaled Diffusion Maps from molecular dynamics trajectories
LSDMap is a set of Fortran90 codes parallelised with MPI for the calculation of Locally Scaled Diffusion Maps. The eigenvectors of the diffusion matrix can be used to form a small set of reaction coordinates describing the behaviour of a high-dimensional data set such as an equilibrium MD trajectory. -
16
An urban air pollution model based on the mass-conservation principle and the advection-diffusion equation. A technical report R-207-2012 can be found in http://www.nies.go.jp/kanko/kenkyu/index-e.html
-
17
SES Super-Encypherment Scrambler
SES brings back the uncrackable onetime pad, with a digital twist.
SES brings back the uncrackable onetime pad, with a digital twist. It is well known that a random key of message-length is the only provably unbreakable cipher. SES uses cryptographic strength pseudo-random keys of message-length for its many encipherments, in addition to offering true one-time pad capability for the intrepid. SES is built on ISAAC, Bob Jenkins' unbroken CSPRNG, a fast and simple stream cipher placed in the Public Domain in 1996. SES now gives you the ability to... -
18
NanoTrackJ
NanoTrackJ - Size characterization of freely diffusing nanoparticles
NanoTrackJ moved to GitHub! Please see: https://github.com/thorstenwagner/ij-nanotrackj or http://fiji.sc/NanoTrackJ -
19
Ideal Gas Simulator
An ideal gas simulator 2D developed in Java
-
20
Generateur Playlist
Générateur de playlist au format M3U, XSPF et PLS
La section BTS SIO du Lycée André Malraux gère, maintient et anime la Radio Libre de l’établissement. Dans le cadre de sa gestion, les étudiants mettent en place des infrastructures et des services permettant la création, le traitement, la gestion et la diffusion de programmes radiophoniques Libres. L’organisation est structurée de manière singulière, en effet elle dispose d’outils qui sont mis en œuvre ou conçus par des étudiants aux compétences hétérogènes, et à des moments différents. -
21
Smart Virus
Play the role of a virus in a quest to replicate.
...That DNA is found in a master cell, but to find it, you must first go through and infect a series of other cells to obtain the proteins needed to locate the elusive master cell which releases a signaling chemical through diffusion. Track down the origin of this chemical and you track down the master cell and achieve replicative success. -
22
Smoldyn is a computer program for simulating reactions and diffusion at a mesoscopic size scale. This scale lies between the more traditional microscopic size scale, in which all or most atoms are considered.
-
23
fick is fluid diffusion simulator (for both liquids and gases): it uses the Flick diffusion laws to drive the evolution of a cellular automata.
-
24
This project is concerned with developing a Monte Carlo simulation code for a simple hopping model of diffusion on a comb-like lattice. It is coded in C.
-
25
Meredys (MEsoscopic REaction DYnamics Simulator) is a particle based stochastic simulation software designed to model and simulate reaction-diffusion systems. (http://www.ebi.ac.uk/compneur-srv/meredys.html)
