Skywork Open Models: Model List and Licenses
About Skywork
Skywork releases a wide range of models on its Skywork organization on Hugging Face, including video generation, image generation and multimodal reasoning. It has 82 models and kept updating through 2026.
What It Releases
- SkyReels V3 (January 2026): its flagship video generation model. According to the model card, built on a unified multimodal in-context learning framework, it natively supports multi-subject video generation from reference images, video generation guided by audio, and video-to-video generation. There are A2V (19B), R2V (14B) and V2V (14B) versions.
- Matrix-Game 3.0 (March 2026): according to its model card, a memory-augmented interactive world model (video that advances in response to controls, like a game) for real-time, long-form 720p video generation.
- UniPic 3 (January 2026): a model unifying image generation and editing, with fast distilled versions (DMD, Consistency).
- R1V: multimodal models that reason over images (R1V4 in December 2025).
Licenses
They differ by line. SkyReels V3 uses its own Skywork Community License, which permits commercial use subject to its terms. Matrix-Game 3.0 is Apache-2.0, and UniPic and R1V are MIT. Read each model’s license text before use. This summary is not legal advice.
Running Them Locally
- There are no official GGUF builds (as of 2026-09-26).
- The video models are fairly large, 14B to 19B. They also load a text encoder and VAE, so check the memory needed for all components in the tables in our articles.
Sources: model cards of Skywork/SkyReels-V3-A2V-19B, Skywork/Matrix-Game-3.0 and Skywork/Unipic3; the model list of the Skywork organization on Hugging Face (all as of 2026-09-26).
Our Coverage and Data
Local Model Watch has not published an article on Skywork’s models yet. The model list below is collected by code from Hugging Face every day. Part of our publisher index; model families link to their family pages.
At a Glance
| Item | Value |
|---|---|
| Hugging Face organization | Skywork |
| Models on Hugging Face | 82 |
| Articles on its own models | 0 |
| Articles on derived models | 0 |
Recent Models on Hugging Face
The publisher lists 82 models in total on Hugging Face. Below are up to 15 of the most recent generative models (text, image, video, audio and so on), the scope of this site, per organization. Classifiers, feature extractors, research components and repositories without a model card are omitted, and the publisher’s own quantized builds and helper variants are folded into the row of the original model. Parameter counts are left blank for repositories that pack weights into integer types, where Hugging Face’s count is not the real parameter count.
→ Scroll horizontally to see all columns
| Released | Model | Task | Parameters | License | Official variants |
|---|---|---|---|---|---|
| 2026-03-27 | Skywork/Matrix-Game-3.0 | video generation | — | apache-2.0 |
— |
| 2026-01-19 | Skywork/SkyReels-V3-A2V-19B | video generation | 18.9B | skywork-license |
— |
| 2026-01-19 | Skywork/SkyReels-V3-R2V-14B | video generation | 14.3B | skywork-license |
— |
| 2026-01-19 | Skywork/SkyReels-V3-V2V-14B | video generation | — | skywork-license |
— |
| 2026-01-13 | Skywork/Unipic3 | vision-language | — | mit |
— |
| 2026-01-12 | Skywork/Unipic3-DMD | vision-language | — | mit |
— |
| 2026-01-12 | Skywork/Unipic3-Consistency-Model | vision-language | — | mit |
— |
| 2025-12-03 | Skywork/R1V4 | vision-language | — | mit |
— |
| 2025-08-13 | Skywork/UniPic2-Metaquery-GRPO-Flash | vision-language | — | mit |
— |
| 2025-08-13 | Skywork/UniPic2-SD3.5M-Kontext-GRPO-2B | vision-language | — | mit |
— |
| 2025-08-13 | Skywork/UniPic2-Metaquery-GRPO-9B | vision-language | — | mit |
— |
| 2025-08-12 | Skywork/UniPic2-Metaquery-Flash | vision-language | — | mit |
— |
| 2025-08-12 | Skywork/UniPic2-SD3.5M-Kontext-2B | vision-language | — | mit |
— |
| 2025-08-11 | Skywork/UniPic2-Metaquery-9B | vision-language | — | mit |
— |
| 2025-08-08 | Skywork/Matrix-Game-2.0 | video generation | — | mit |
— |
From the Hugging Face API. Last changed 2026-09-27 (JST). Collected by code.
Last updated 2026-09-27 (JST). The explanation at the top of this page was written with the help of AI from the primary sources it cites. The tables and lists under “Our Coverage and Data" are assembled by code from our article log and the Hugging Face API.