Models🎵
Stable Audio Open 1.0
Released Jun 5, 2024Stable Audio 3.0
Up to 47 seconds of text-to-audio: high-quality music and sound effects. Excellent for local audio production and sound design.
MusicaAudioOpen Source
Back to resources
Stable Diffusion 1.5
Released on Oct 20, 2022
The image-generation classic: fast, light, and with the largest LoRA/ControlNet ecosystem of all. Perfect for 6-8GB GPUs.
Features
- 1024px max
- Huge LoRA ecosystem
- 6-8GB VRAM
- Very fast
Version history
- SD 3.5 LargeLatest
Flagship riaddestrata da 8,1 miliardi di parametri con MMDiT-X e QK normalization, rilasciata con licenza rivista.
- SD3 Medium
Primo modello aperto della famiglia SD3 basato su Diffusion Transformer (MMDiT, 2B parametri) con obiettivo rectified flow.
- SDXL 1.0
Modello text-to-image di 2.6 miliardi di parametri, 8 volte i dati di addestramento di SD1.5, in grado di produrre immagini 1024x1024.
- Stable Diffusion 2.0
Nuova release di Stability AI con architettura aggiornata e modelli 768x768 (700M e 1.4B parametri).
- Stable Diffusion 1.5
Pubblicato su Hugging Face da RunwayML (fine-tuning di 595.000 passi da SD 1.2 a 512x512) e successivamente riconosciuto come checkpoint ufficiale SD 1.5.
Tags
Useful links
Discover Stable Diffusion 1.5
Visit the official site to download, learn more and start using Stable Diffusion 1.5.
Related resources — Models
Models🎨
Stable Diffusion XL 1.0
Released Jul 26, 2023SD 3.5 Large
The current standard for photoreal and artistic images at 1024px. Better prompt adherence and more coherent composition than SD 1.5.
ImmaginiDiffusionOpen Source
Models🎬
Stable Video Diffusion
Released Nov 21, 2023SVD 1.1
Turns an image into a short ~2s video clip. The entry point for local video generation; 16GB VRAM recommended.
VideoDiffusionOpen Source