RSS

Lab · the UK

Stability AI

AI models from Stability AI: 118 models in the catalog, version timeline, prices and sourced benchmarks.

  • 118 models in the catalog
  • 115 with open weights
  • 3 closed or without public weights
  • 0 with sourced benchmarks
  • 0 with a page here

We count grouped models: Instruct, Base, quantized and size variants of the same line become one. Behind that there are 119 Hugging Face repositories, 0 OpenRouter endpoints and 29 historical records at Epoch AI.

Version timeline by family

Main model lines

20232023202420242025202520262026Stable Diffusion2.1Stable Diffusion 2.1, 20221.6Stable Diffusion 1.6, 20233Stable Diffusion 3, 20243.5Stable Diffusion 3.5, 2024Stable Video3Stable Video 3, 20244Stable Video 4, 2024SV3DSV3DSV3D, 2024SV4DSV4D, 2024CosxlCosxlCosxl, 2024Stable Audio Open1.0Stable Audio Open 1.0, 2024MindEye2MindEye 2, 2024Stable Fast3Stable Fast 3, 2024ControlNet (SD 3.5 La…ControlNet (SD 3.5 Large) DepthControlNet …ControlNet (SD 3.5 Large) Depth, 2024ControlNet (SD 3.5 La…ControlNet (SD 3.5 Large) BlurControlNet …ControlNet (SD 3.5 Large) Blur, 2024ControlNet (SD 3.5 La…ControlNet (SD 3.5 Large) CannyControlNet …ControlNet (SD 3.5 Large) Canny, 2024Stable Point Aware3Stable Point Aware 3, 2024Stable Virtual CameraStable Virt…Stable Virtual Camera, 2025Stable Audio Open Sma…Stable Audio Open SmallStable Audi…Stable Audio Open Small, 2025Stable Audio3Stable Audio 3, 202620232023202420242025202520262026Stable Diffusion2.1Stable Diffusion 2.1, 20221.6Stable Diffusion 1.6, 2023Stable Diffusion 3, 20243.5Stable Diffusion 3.5, 2024Stable Video3Stable Video 3, 2024Stable Video 4, 2024SV3DSV3DSV3D, 2024SV4D, 2024CosxlCosxlCosxl, 2024Stable Audio Open1.0Stable Audio Open 1.0, 2024MindEye2MindEye 2, 2024Stable Fast3Stable Fast 3, 2024ControlNet (SD 3.5 Large) DepthControlNet (SD 3.5 Large) Depth, 2024ControlNet (SD 3.5 Large) BlurControlNet (SD 3.5 Large) Blur, 2024ControlNet (SD 3.5 Large) CannyControlNet (SD 3.5 Large) Canny, 2024Stable Point Aware3Stable Point Aware 3, 2024Stable Virtual CameraStable Virtual Camera, 2025Stable Audio Open SmallStable Audio Open Small, 2025Stable Audio3Stable Audio 3, 2026

Tap a point to see the version.Tap or hover over a point to see the version. Dates come from the sources: OpenRouter listing or Hugging Face repo creation, which may differ from the official launch. Family and version were grouped by rule from the name.

Other lab models in the catalog (50)

ModelModalityWeightsContextInput US$/1MDownloads (30 days)1ª
stable-diffusion-xl-base-1.0imagemopenno datano data4,652,0452023
sdxlimagemopenno datano data607,6952023
stable-diffusion-3-mediumimagemopenno datano data63,9962024
stable-diffusion-3.5-largeimagemopenno datano data52,6522024
sd-vae-ft-mseimagemopenno datano data326,6842022
sdimagemopenno datano data437,5292023
stable-video-diffusion-img2vid-xtvídeoopenno datano data126,7532023
stable-diffusion-xl-refiner-1.0imagemopenno datano data109,3162023
sdxl-vaeimagemopenno datano data227,9552023
TripoSR3dopenno datano data183,0852024
stable-audio-open-1.0vozopenno datano data19,9952024
stable-diffusion-3.5-mediumimagemopenno datano data74,4712024
stable-fast-3d3dopenno datano data35,5672024
stable-audio-3-mediumvozopenno datano data116,5442026
stable-cascadeimagemopenno datano data18,6582024
stable-video-diffusion-img2vidvídeoopenno datano data39,5852023
stable-diffusion-xl-base-0.9imagemopenno datano data232023
stable-video-diffusion-img2vid-xt-1-1vídeoopenno datano data3,4972024
stable-audio-3-small-sfxvozopenno datano data66,0242026
control-loraimagemopenno datano datano data2023
stable-codecódigoopenno datano data9,1442024
StableBeluga2textoopenno datano data8652023
stable-diffusion-x4-upscalerimagemopenno datano data6,1342022
stable-zero1233dopenno datano datano data2023
sv3dvídeoopenno datano datano data2024
stable-virtual-cameravídeoopenno datano data31,4632025
stablelm-tuned-alphatextoopenno datano data2,8302023
stablelm-zephyrtextoopenno datano data23,8912023
stable-point-aware-3d3dopenno datano data4,8872024
stable-audio-3-small-musicvozopenno datano data23,0732026
stable-audio-3-optimizedvozopenno datano data38,9412026
stablelm-3b-4e1ttextoopenno datano data11,7112023
sd-vae-ft-emaimagemopenno datano data13,4422022
stable-audio-open-smallvozopenno datano data7,1452025
stablecode-completion-alphacódigoopenno datano data1,8202023
stablelm-base-alphatextoopenno datano data4,4542023
stable-diffusion-xl-refiner-0.9imagemopenno datano data152023
sv4dimagemopenno datano data122024
stablelm-2-1textoopenno datano data8,7822024
stablecode-instruct-alphacódigoopenno datano datano data2023
stablelm-2-zephyr-1textoopenno datano data7,5122024
StableBelugatextoopenno datano data1,4412023
cosxlimagemopenno datano datano data2024
stablelm-2sem rótulo, textoopenno datano data2,0632024
stable-diffusion-3.5-controlnetsimagemopenno datano data1,9202024
sd-x2-latent-upscalerimagemopenno datano data2,0642023
stable-diffusion-xl-1.0-tensorrtimagemopenno datano data2542023
stable-diffusion-3-medium-tensorrtimagemopenno datano data82024
japanese-stablelm-base-alphatextoopenno datano data8252023
japanese-stable-diffusion-xlimagemopenno datano data532023

Sources

  • Hugging Face Hub, metadados públicos do Hub; licença de cada modelo no repositório, latest version we checked.
  • OpenRouter, dados públicos da API; exports de benchmarks e rankings em CC BY 4.0, latest version we checked.
  • Epoch AI, CC BY 4.0, latest version we checked.

Dates come from the sources: OpenRouter listing or Hugging Face repo creation, which may differ from the official launch. Family and version were grouped by rule from the name.