Stable Diffusion
#8 in Text-to-Bildstability-ai · siet 2022-08-22 · 12× · tolest 30. Juni 2026
39
Momentum
Stable Diffusion is an open-source text-to-image model by Stability AI, first released on August 22, 2022. It uses a latent diffusion approach and can be run locally on consumer GPU hardware or accessed via the Stability AI API/DreamStudio. The latest generation is Stable Diffusion 3.5 (SD3.5) with model variants ranging from 2.5B to 8.1B parameters. Model weights are publicly downloadable from Hugging Face; fine-tuning via LoRA, DreamBooth, and Textual Inversion is natively supported.
Momentum-Verloop
04.04.03.07.
Features
| Fine-Tuning | Models are specifically designed for easy fine-tuning/LoRA training (including via query-key normalization) |
| Generation Time | SD 3.5 Large Turbo: high-quality images in just 4 diffusion steps |
| License | Stability AI Community License: free for research, non-commercial use, and commercial use up to $1M annual revenue; Enterprise License required above that |
| Max Resolution | SD 3.5 Large: 1 megapixel (native 1024x1024); SD 3.5 Medium: up to 2 megapixels |
| Platform | Self-hosting (Hugging Face/GitHub weights), Stability API/Developer Platform, ComfyUI, Automatic1111, Amazon Bedrock, NVIDIA NIM |
| Price | API: 1 credit = $0.01; Stable Image Ultra $0.08/image, Core $0.03/image; SD3.5 models in between; self-hosting free under Community License |
| Release Date | SD 3.5 Large & Large Turbo: October 22, 2024; SD 3.5 Medium: October 29, 2024 |