Providers · Local runtime
GGML
GGML is the local runtime CSuite bundles for on-device image and video generation, built on stable-diffusion.cpp. Model weights are downloaded once and every frame is rendered on your own hardware — no API key and no per-use fees. It's the most demanding of the local runtimes, so each model lists the machine it needs.
Image(3 models)
Flux 2 Klein 4b
Compact 4B Flux diffusion model for fast, high-quality image generation.
8 months ago (Jan 2026)
Z Image Turbo
High-speed image generation model optimised for low-latency creative output.
10 months ago (Nov 2025)
Qwen Image
Alibaba Qwen's 20B image model, running fully offline on your own machine. Known for rendering long passages of text — English and Chinese — inside the image, and needs no API key or network once the weights are downloaded.
1 year ago (Aug 2025)
Video(5 models)
H3 Local
MiniMax's H3 video model running offline, with synchronised audio. The heaviest local entry by a wide margin: its text encoder alone is a 32B vision-language model.
1 month ago (Aug 2026)
LTX-2.3 Distilled
Lightricks' 22B video model, distilled for fewer sampling steps. Generates synchronised audio alongside the video, and drives a Gemma 3 language model as its text encoder.
4 months ago (May 2026)
Wan 2.2 T2V A14B
Alibaba's largest open Wan model, a two-expert mixture that swaps between a high-noise and a low-noise transformer partway through denoising. Highest quality of the local Wan entries and by far the heaviest.
1 year ago (Jul 2025)
Wan 2.2 TI2V-5B
Alibaba's compact 5B video model, running fully offline on your own machine. Handles both text-to-video and image-to-video, and needs no API key or network once the weights are downloaded.
1 year ago (Jul 2025)
Wan 2.1 T2V 1.3B
Alibaba's smallest Wan video model, and the lightest local option. Runs at 480p on modest hardware and shares its text encoder with the other Wan entries, so it costs little extra once one of them is installed.
1 year ago (Feb 2025)