Open-Sora alternatives

Open-Sora is an open-source model, Free (open source). These 12 tools are in the same category and share the most vendor-stated features with it.

Why each one is here

• CogVideoX: Open-weight text-to-video and image-to-video models (CogVideoX-2B, 5B and 1.5) that run on desktop GPUs; CogVideoX1.5 makes 10-second clips at 1360x768. Shared with Open-Sora: text to video, image to video, open weights.
• HunyuanVideo: Tencent's open-weight video generation model with text-to-video and image-to-video variants, single- and multi-GPU inference. Shared with Open-Sora: text to video, image to video, open weights.
• LTX-2 / LTX-Video: Lightricks' open-weight audio-video model family: LTX-2.5 generates synchronized audio and video, with a UHD 4K mode; earlier LTX-Video distilled models make up to 60-second clips. Shared with Open-Sora: text to video, image to video, open weights.
• MAGI-1: Sand AI's Apache-2.0 autoregressive video model that generates video chunk by chunk (24B and 4.5B weights), strong at image-to-video and long, streamed generation. Shared with Open-Sora: text to video, image to video, open weights.
• Wan: Alibaba's open-weight video models (Wan 2.x): text-to-video and image-to-video at 720p/24fps that run on a single consumer GPU such as an RTX 4090. Shared with Open-Sora: text to video, image to video, open weights.
• Genmo: Research lab behind Mochi 1, an open-source text-to-video model you can run yourself or in ComfyUI, plus a hosted playground. Shared with Open-Sora: text to video, open weights.
• SkyReels: Skywork's open-weight video models: SkyReels-V2 uses autoregressive diffusion forcing for long ("infinite-length") generation at 540p/720p, with V3 weights released in 2026. Shared with Open-Sora: image to video, open weights.
• Stable Video Diffusion: Stability AI's image-to-video latent diffusion model (SVD-XT: 25 frames at 576x1024), downloadable under the Stability AI Community License. Shared with Open-Sora: image to video, open weights.
• Adobe Firefly Video: Adobe's Firefly app generates video from text or images with Adobe's Firefly Video Model and partner models (Google, OpenAI and others), plus audio/video translation. Shared with Open-Sora: text to video, image to video.
• DeeVid AI: AI video and image generator offering popular third-party models on credit plans, with 720p-1080p output. Shared with Open-Sora: text to video, image to video.
• DomoAI: Style-transfer and animation tool (video-to-anime, character-to-video, talking avatars) that also runs third-party video models. Shared with Open-Sora: text to video, image to video.
• Google Veo: Google DeepMind's video model (Veo 3.1) with natively generated sound effects, ambience and dialogue; used in Google Flow, the Gemini app and the Gemini API. Shared with Open-Sora: text to video, image to video.

Head-to-head comparisons

Lists that include Open-Sora

How we pick alternatives: same product group (generators, avatar tools, or editors and clip tools), then ranked by shared vendor-stated features and published pricing. Methodology.