Machine Learning Workstation

Bild Generation

• Nerfstudio
  • https://sites.hslu.ch/werkstatt/neural-radiance-fields-nerfs/
• Stable Diffusion
  • WebUI 
    • Multiple Models, LoRA`s and Controlnet Options
    • https://sites.hslu.ch/werkstatt/stable-diffusion-webui/
  • Fooocus
    • https://sites.hslu.ch/werkstatt/fooocus/
• Stable Diffusion Turbo XL
  • ComfyUI
• Stable Diffusion Differential Diffusion
  • WebUI
• FaceFusion
  • Faceswap
• Instant ID
  • Zero-shot Identity-Preserving Generation in Seconds
• Photo Maker
  • Customizing Realistic Human Photos via Stacked ID Embedding
• Deus
• Dreamtalk
  • speech to face animation

Bildbearbeitung

• Supir
  • Bildrestauration Upscale
• BRIA_RMBG
  • Bild / Video Hintergrund Löschen
• InvokeAI
  • Bildgenerierung / Bearbeitung

Video

• VideoCrafter 2
  • Text to Video
  • Image to Video
• Stable Diffusion Video
  • WebUI
• Moore-AnimateAnyone
  • Animiere Fotografien mit Openpose Videos
• Video2Openpose
  • Extrahiere Openpose Skellette aus Videos
• Video2Densepose
  • Extrahiere Densepose Segmentationen aus Videos
• AnimateMagic
  • Temporally Consistent Human Image Animation using Diffusion Model
• Realtime Stable Diffusion
  • Video to video
• LaVie
  • text to video
• AnimateDiff
  • Animation Generator

Machine- Vision

• Moondream2
  • A tiny open-source computer-vision model that runs everywhere and kicks ass.
  • Bild zu Text Model
• Mirror
  • Livebeschrieb von Webcamfeed

3D Objekte

• Nerfstudio
  • Neureal Radiance Fields
  • https://sites.hslu.ch/werkstatt/neural-radiance-fields-nerfs/

• TripoSR

  • Schnelle 3D-Objektgenerierung aus Einzelbildern
• DUSt3R
  • 3D Objekte aus wenigen Bildern
• LGM
  • Large Multi-View Gaussian Model for High-Resolution 3D Content Creation

Text Generation

• whisper by open ai
  • Whisper
    • https://sites.hslu.ch/werkstatt/whisper-openai-transkription/

Chatbots

• LobeChat
• Chatbot-Ollama

Audio

• ZETA
  • Textbasierte Audiobearbeitung mit Zero-Shot und DDPM-Invertierung
• MeloTTS
  • Text to Speech in verschiedenen Sprachen
• Bark Voice Coning
  • Text to Speech in verschiedenen Sprachen
  • Voice Cloning
• MAGNeT
  • Text to Music
  • Text to Sound
• OpenVoice
  • Text to Speech
  • Voice Cloning
• LP-MusicCaps
  • Music to Description
• XTTS
  • Voice Cloning

Verschiedene Modelle 

• openWebUI