並び順

ブックマーク数

期間指定

  • から
  • まで

1 - 31 件 / 31件

新着順 人気順

Latentの検索結果1 - 31 件 / 31件

タグ検索の該当結果が少ないため、タイトル検索結果を表示しています。

Latentに関するエントリは31件あります。 AI機械学習github などが関連タグです。 人気エントリには 『GitHub - CompVis/stable-diffusion: A latent text-to-image diffusion model』などがあります。
  • GitHub - CompVis/stable-diffusion: A latent text-to-image diffusion model

    You signed in with another tab or window. Reload to refresh your session. You signed out in another tab or window. Reload to refresh your session. You switched accounts on another tab or window. Reload to refresh your session. Dismiss alert

      GitHub - CompVis/stable-diffusion: A latent text-to-image diffusion model
    • The joy of building a ray tracer, for fun, in Rust. // flurries of latent creativity

      TLDR? You can find the code and a bunch of examples on GitHub at dps/rust-raytracer. Over the holiday break, I decided to learn Rust. Rust is a modern systems programming language which has a really interesting type system. The type system can catch broad classes of common programming mistakes - e.g. ensuring memory is accessed safely - at compile time while generating tight, performant machine co

        The joy of building a ray tracer, for fun, in Rust. // flurries of latent creativity
      • [Latent Diffusion] AIでテキストから画像を生成する

        初めに、論文発表元のGithubからソースコードを取得します %cd /content !git clone https://github.com/CompVis/latent-diffusion.git 次にライブラリをインストールします。 %cd /content !git clone https://github.com/CompVis/taming-transformers !pip install -e ./taming-transformers !pip install omegaconf>=2.0.0 pytorch-lightning>=1.0.8 torch-fidelity einops import sys sys.path.append(".") sys.path.append('./taming-transformers') from taming.models

          [Latent Diffusion] AIでテキストから画像を生成する
        • GitHub - adamian98/pulse: PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models

          You signed in with another tab or window. Reload to refresh your session. You signed out in another tab or window. Reload to refresh your session. You switched accounts on another tab or window. Reload to refresh your session. Dismiss alert

            GitHub - adamian98/pulse: PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models
          • PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models

            The primary aim of single-image super-resolution is to construct a high-resolution (HR) image from a corresponding low-resolution (LR) input. In previous approaches, which have generally been supervised, the training objective typically measures a pixel-wise average distance between the super-resolved (SR) and HR images. Optimizing such metrics often leads to blurring, especially in high variance

              PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models
            • GitHub - radames/Real-Time-Latent-Consistency-Model: Demo showcasing ~real-time Latent Consistency Model pipeline with Diffusers and a MJPEG stream server

              You signed in with another tab or window. Reload to refresh your session. You signed out in another tab or window. Reload to refresh your session. You switched accounts on another tab or window. Reload to refresh your session.

                GitHub - radames/Real-Time-Latent-Consistency-Model: Demo showcasing ~real-time Latent Consistency Model pipeline with Diffusers and a MJPEG stream server
              • Generate images in one second on your Mac using a latent consistency model

                Generate images in one second on your Mac using a latent consistency model Posted October 25, 2023 by @fofr Latent consistency models (LCMs) are based on Stable Diffusion, but they can generate images much faster, needing only 4 to 8 steps for a good image (compared to 25 to 50 steps). By running an LCM on your M1 or M2 Mac you can generate 512x512 images at a rate of one per second. Simian Luo et

                  Generate images in one second on your Mac using a latent consistency model
                • Human Herpesvirus 6B Greatly Increases Risk of Depression by Activating Hypothalamic-Pituitary -Adrenal Axis during Latent Phase of Infection | Published:May 21, 2020 | CellPress iScience

                  If you don't remember your password, you can reset it by entering your email address and clicking the Reset Password button. You will then receive an email that contains a secure link for resetting your password

                    Human Herpesvirus 6B Greatly Increases Risk of Depression by Activating Hypothalamic-Pituitary -Adrenal Axis during Latent Phase of Infection | Published:May 21, 2020 | CellPress iScience
                  • GitHub - rinnakk/japanese-stable-diffusion: Japanese Stable Diffusion is a Japanese specific latent text-to-image diffusion model capable of generating photo-realistic images given any text input.

                    You signed in with another tab or window. Reload to refresh your session. You signed out in another tab or window. Reload to refresh your session. You switched accounts on another tab or window. Reload to refresh your session. Dismiss alert

                      GitHub - rinnakk/japanese-stable-diffusion: Japanese Stable Diffusion is a Japanese specific latent text-to-image diffusion model capable of generating photo-realistic images given any text input.
                    • Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models

                      1 LMU Munich, 2 NVIDIA, 3 Vector Institute, 4 University of Toronto, 5 University of Waterloo Latent Diffusion Models (LDMs) enable high-quality image synthesis while avoiding excessive compute demands by training a diffusion model in a compressed lower-dimensional latent space. Here, we apply the LDM paradigm to high-resolution video generation, a particularly resource-intensive task. We first pr

                      • AudioLDM: Text-to-Audio Generation with Latent Diffusion Models - Speech Research

                        AudioLDM 2: Learning Holistic Audio Generation with Self-supervised Pretraining Haohe Liu 📮,1, Qiao Tian2,Yi Yuan1, Xubo Liu1, Xinhao Mei1,Qiuqiang Kong2 Yuping Wang2, Wenwu Wang1, Yuxuan Wang2, Mark D. Plumbley1 1CVSSP, University of Surrey, Guildford, UK 2Speech, Audio & Music Intelligence (SAMI), ByteDance 📮Corresponding author 😃 For text-to-audio generation, we generated a total of 350 audi

                        • GitHub - Stability-AI/stablediffusion: High-Resolution Image Synthesis with Latent Diffusion Models

                          March 24, 2023 Stable UnCLIP 2.1 New stable diffusion finetune (Stable unCLIP 2.1, Hugging Face) at 768x768 resolution, based on SD2.1-768. This model allows for image variations and mixing operations as described in Hierarchical Text-Conditional Image Generation with CLIP Latents, and, thanks to its modularity, can be combined with other models such as KARLO. Comes in two variants: Stable unCLIP-

                            GitHub - Stability-AI/stablediffusion: High-Resolution Image Synthesis with Latent Diffusion Models
                          • scikit-learnのLatent Dirichlet Allocation (LDA) のcoherenceを求める - Qiita

                            scikit-learnのLatent Dirichlet Allocation (LDA) のcoherenceを求めるPython機械学習scikit-learnLDA はじめに ちゃお…† まいおり…† LDA (Latent Dirichlet Allocation)、わたしの好きなモデルです。 しかし、現時点のscikit-learn (1.2.2) にはLDAモデルのcoherence (コヒーレンス) を求める関数はありません。 そこで強引に?LDAモデルのcoherenceを求める方法を記します。 コヒーレンスとは 記述や事実の集合は、それらが互いに支持し合っている場合、首尾一貫している (coherent) と言われます。したがって、首尾一貫した事実の集合は、事実のすべてまたは大部分をカバーする文脈で解釈することができます。 トピックのコヒーレンスを測るとは、トピック内の

                              scikit-learnのLatent Dirichlet Allocation (LDA) のcoherenceを求める - Qiita
                            • High-Resolution Image Synthesis with Latent Diffusion Models

                              By decomposing the image formation process into a sequential application of denoising autoencoders, diffusion models (DMs) achieve state-of-the-art synthesis results on image data and beyond. Additionally, their formulation allows for a guiding mechanism to control the image generation process without retraining. However, since these models typically operate directly in pixel space, optimization o

                              • Text-to-Audio Generation using Instruction Tuned LLM and Latent Diffusion Model

                                Text-to-Audio Generation using Instruction Tuned LLM and Latent Diffusion Model Deepanway Ghosal1, Navonil Majumder1, Ambuj Mehrish1, Soujanya Poria1 1DeCLaRe Lab, Singapore University of Technology and Design, Singapore 🔥🔥🎉🎉 We released Tango 2 which surpasses the performance of AudioLDM2 and Tango. Access it here. 🔥🔥🎉🎉 We released Tango-AF trained on synthetic AudioSet captions. Access i

                                • 複数キャラを生成できるプロンプトと、キャラ毎に属性を設定できる拡張機能「Latent Couple extension」の使い方を紹介!【Stable Diffusion】

                                  こんにちは!悠です。 今回は「Stable Diffusion WebUI」を使って、簡単に複数キャラを作成できるプロンプトと、キャラ毎に髪型や服装といった属性を指定できる拡張機能「Latent Couple extension (two shot diffusion port)」の使い方を紹介していきます。 Google Colaboratory版とローカル版のどちらでも使えるので、ぜひ参考にしてください!

                                    複数キャラを生成できるプロンプトと、キャラ毎に属性を設定できる拡張機能「Latent Couple extension」の使い方を紹介!【Stable Diffusion】
                                  • StyleGAN2学習済みモデルを使ったmorphing、latent spaceの探求 - すぎゃーんメモ

                                    学習データはまだまだ収集途中だし 学習もまだ完了とは言えない状態なのだけど、なんとなくそれっぽい顔画像は生成できるくらいまでは出来てきているので、それを使った実験をしてみている。 学習した生成モデルを使って morphingを試してみてる #StyleGAN2 pic.twitter.com/NxlaOgp1RX— すぎゃーん💯 (@sugyan) February 7, 2020 なるほどねー pic.twitter.com/7Qmf61G14t— すぎゃーん💯 (@sugyan) February 9, 2020 主にこの記事を参考にしています。 qiita.com 1. latents_in の線形移動 まず最初に試したのは、通常の generator network を使った場合の latents_inを使ったもの。 generator は、(?, 512) の任意の入力を受け

                                      StyleGAN2学習済みモデルを使ったmorphing、latent spaceの探求 - すぎゃーんメモ
                                    • Real-Time Latent Consistency Model (LCM)から掘り下げる最近の画像生成AIの高速化研究|しらいはかせ(Hacker作家)

                                      今週世間を賑わせている画像生成AIの話題で一番インパクトのある話題が 「Real-Time Latent Consistency Model」、通称「RT-LCM」だと思います。 "RT-LCM" Real-Time-Latent-Consistency-Model リアルタイムで潜在空間が一貫して動きます CUDAとPython、またはM1/M2/M3チップを搭載したMacでも動くようです HuggingFaceSpacesでのデモもありますhttps://t.co/T7AmuKNzTC pic.twitter.com/U0l2WX7u6p — AICU Inc. (@AICUai) November 1, 2023 このLCM関係の論文を調査していたらけっこう勉強になったので簡単に紹介しておきたいとおもいます。 この数日で、既にいろんなデモが出ているのですが、いちばん有名と思われるのが

                                        Real-Time Latent Consistency Model (LCM)から掘り下げる最近の画像生成AIの高速化研究|しらいはかせ(Hacker作家)
                                      • 複数のキャラクターを描き分けられる「Latent Couple extension」の使い方【Stable Diffusion web UI】

                                          複数のキャラクターを描き分けられる「Latent Couple extension」の使い方【Stable Diffusion web UI】
                                        • GitHub - hnmr293/sd-webui-llul: LLuL - Local Latent upscaLer

                                          You signed in with another tab or window. Reload to refresh your session. You signed out in another tab or window. Reload to refresh your session. You switched accounts on another tab or window. Reload to refresh your session. Dismiss alert

                                            GitHub - hnmr293/sd-webui-llul: LLuL - Local Latent upscaLer
                                          • GitHub - tg-bomze/Face-Depixelizer: Face Depixelizer based on "PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models" repository.

                                            You signed in with another tab or window. Reload to refresh your session. You signed out in another tab or window. Reload to refresh your session. You switched accounts on another tab or window. Reload to refresh your session. Dismiss alert

                                              GitHub - tg-bomze/Face-Depixelizer: Face Depixelizer based on "PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models" repository.
                                            • 【Real-Time Latent Consistency Model】リアルタイムで入力したプロンプトがすぐに画像になる高速画像生成AIを使ってみた | WEEL

                                              ホーム大人気のオープンソースツール【Real-Time Latent Consistency Model】リアルタイムで入力したプロンプトがすぐに画像になる高速画像生成AIを使ってみた 【Real-Time Latent Consistency Model】リアルタイムで入力したプロンプトがすぐに画像になる高速画像生成AIを使ってみた 2023 11/06 Real-Time Latent Consistency Modelは、リアルタイムで画像生成をすることができ、ユーザーが入力したプロンプトが反映された画像を逐一出力します。 一文字変えるだけでも瞬時に別の画像を生成するので、理想の画像が作れると今世間を賑わせており、デモを紹介したポストには1700以上のいいねがついています。 実際にこんなことができちゃうんです! 一瞬で画像が変化するのはすごいですよね! 今回は、Real-Time L

                                                【Real-Time Latent Consistency Model】リアルタイムで入力したプロンプトがすぐに画像になる高速画像生成AIを使ってみた | WEEL
                                              • High-Resolution Image Synthesis with Latent Diffusion Models - Computer Vision & Learning Group

                                                High-Resolution Image Synthesis with Latent Diffusion Models (A.K.A. LDM & Stable Diffusion) Robin Rombach1,2, Andreas Blattmann1,2, Dominik Lorenz1,2, Patrick Esser3, Björn Ommer1,2 1LMU Munich, 2IWR, Heidelberg University, 3Runway CVPR 2022 (ORAL) Abstract By decomposing the image formation process into a sequential application of denoising autoencoders, diffusion models (DMs) achieve state-of-t

                                                  High-Resolution Image Synthesis with Latent Diffusion Models - Computer Vision & Learning Group
                                                • [輪講資料] Optimus: Organizing Sentences via Pre-trained Modeling of a Latent Space

                                                  事前学習済み言語モデルを統合することによって構築される大規模Variational Auto-Encoder (VAE)モデルのOptimusと、その論文について解説した資料です。 Optimusを支えるVAEの目的関数の導出から丁寧に紹介します。

                                                    [輪講資料] Optimus: Organizing Sentences via Pre-trained Modeling of a Latent Space
                                                  • How to Explore the GAN Latent Space When Generating Faces - MachineLearningMastery.com

                                                    How to Use Interpolation and Vector Arithmetic to Explore the GAN Latent Space. Generative Adversarial Networks, or GANs, are an architecture for training generative models, such as deep convolutional neural networks for generating images. The generative model in the GAN architecture learns to map points in the latent space to generated images. The latent space has no meaning other than the meanin

                                                      How to Explore the GAN Latent Space When Generating Faces - MachineLearningMastery.com
                                                    • GitHub - ai-forever/Kandinsky-2: Kandinsky 2 — multilingual text2image latent diffusion model

                                                      — Inference example — Fine-tuning with LoRA Habr post Demo fusionbrain.ai Telegram-bot Description: Kandinsky 2.2 brings substantial improvements upon its predecessor, Kandinsky 2.1, by introducing a new, more powerful image encoder - CLIP-ViT-G and the ControlNet support. The switch to CLIP-ViT-G as the image encoder significantly increases the model's capability to generate more aesthetic pictur

                                                        GitHub - ai-forever/Kandinsky-2: Kandinsky 2 — multilingual text2image latent diffusion model
                                                      • GitHub - lllyasviel/LayerDiffuse: Transparent Image Layer Diffusion using Latent Transparency

                                                        You signed in with another tab or window. Reload to refresh your session. You signed out in another tab or window. Reload to refresh your session. You switched accounts on another tab or window. Reload to refresh your session. Dismiss alert

                                                          GitHub - lllyasviel/LayerDiffuse: Transparent Image Layer Diffusion using Latent Transparency
                                                        • Latent Couple(TwoShot)をwebuiに導入し、プロンプト適用領域を部分指定→複数キャラ混ぜずに描写する方法

                                                          よく分かる!Latent Coupleの使い方。WebUI(1111)の拡張機能「stable-diffusion-webui-two-shot」(Latent Couple extension)をインストールし、全く異なる複数キャラを混ざることなく描写する方法を、画像付きで丁寧に解説します。

                                                          • Latent Consistency Models: Synthesizing High-Resolution Images with Few-step Inference

                                                            " LCMs: The next generation of generative models after Latent Diffusion Models (LDMs). " We propose Latent Consistency Models (LCMs) to overcome the slow iterative sampling process of Latent Diffusion models (LDMs), enabling fast inference with minimal steps on any pre-trained LDMs (e.g Stable Diffusion). Viewing the guided reverse diffusion process as solving an augmented probability flow ODE (PF

                                                            • 2/28 Latent Couple Extentionの本当の使い方|あいおえおえかきの|pixivFANBOX

                                                              今回はLatent Couple Extentionの使い方を説明します。 説明するのは以下の4つです。 ①Latent Couple Extentionとは ②Divisionsについて ③Positionsについて ④例題 ⑤プロンプトについて ⑥Weightsについて ⑤まではダラダラした説明が続きますが、この記事の本題は⑥Weightsについてです。 【①Latent Couple Extentionとは...

                                                                2/28 Latent Couple Extentionの本当の使い方|あいおえおえかきの|pixivFANBOX
                                                              • アプリに潜む脆弱性 - LINEの場合 - / Vulnerability latent in LINE android app

                                                                Androidアプリケーションのセキュリティと聞かれて皆さんは何を思い浮かべるでしょうか? データの暗号化・ProGuard/R8といったコード難読化・不正購入、はたまたAndroid本体のセキュリティなど様々な要素が挙がるでしょう。 今回はその中でも特に「脆弱性」にフォーカスしてみます。 Androi…

                                                                  アプリに潜む脆弱性 - LINEの場合 - / Vulnerability latent in LINE android app
                                                                1

                                                                新着記事