Stable Diffusion Models by Stability AI
1 model2022
About
Stable Diffusion is Stability AI's open-source latent diffusion model series for text-to-image generation. The 1.x series (including v1.5) became the foundation for a vast open-source ecosystem of fine-tunes, ControlNet extensions, and community models. SD 1.5 uses a UNet architecture with CLIP text encoder and runs efficiently on consumer hardware.
Current Variants
Use-when guidance is derived from seed capabilities, context, release, and replacement fields.
1 in view
Stable Diffusion 1.5Current
Use when the workload needs image, 860 parameters, and multimodal inputs.
2022-10image860 parametersmultimodal inputs
| Model | Use when | Released | Signals | Status |
|---|---|---|---|---|
| Stable Diffusion 1.5 | Use when the workload needs image, 860 parameters, and multimodal inputs. | 2022-10 | image860 parametersmultimodal inputs | Current |
Release Timeline
1 release group2022-10
1 current
Stable Diffusion 1.5
Currentimage860 parametersmultimodal inputs
Specifications(1 models)
| Model | Released | Parameters | Multimodal |
|---|---|---|---|
| Stable Diffusion 1.5 | 2022-10 | 860 | Yes |
Available From(1 provider)
Frequently Asked Questions
- What is Stable Diffusion used for?
- Stable Diffusion is used for image, vision and multimodal work, and coding. The family description and listed model capabilities point to those workloads as the best fit.
- How does Stable Diffusion compare to Stable Virtual Assistant?
- Stable Diffusion by Stability AI is strongest where you need image, while Stable Virtual Assistant by Stability AI is the closest related family to check for adjacent model selection. Stable Diffusion has 1 listed variant, so compare the specs and pricing tables before choosing a production model.
- Which Stable Diffusion model should I use?
- If price is the main constraint, use the pricing table first because Stable Diffusion does not have complete provider pricing in the local data. For the most capable/latest local choice, evaluate Stable Diffusion 1.5 with multimodal inputs.
