happyhorse-1.1/text-to-video
gpt-image-2/text-to-image
seedance-2.0/pro
wan-2.7/text-to-video

happyhorse-1.1/text-to-video

Happy Horse 1.1 is Alibaba's multimodal video model spanning text, image, reference-to-video, and editing with native audio. This page runs its text-to-video mode at 720P/1080P and 3-15s.

gpt-image-2/text-to-image

透過文字或提示產生精確的品牌就緒圖像,具有準確的圖像內文字、多語言渲染以及快速、可擴展的輸出,非常適合電子商務和行銷視覺效果。

seedance-2.0/pro

Generate cinematic 2K videos from text and media inputs with native audio, precise lip-sync, and smooth storytelling control for ads, film previz, and branded visual content.

wan-2.7/text-to-video

Wan 2.7 is a high-quality AI video model for generating short 720p and 1080p videos from text prompts, with optional audio guidance, flexible aspect ratios, controllable duration, and reproducible seed-based iteration on RunComfy.

立即體驗!
嘗試:
RunComfy
版權 2026 RunComfy. 保留所有權利。

RunComfy 是首選的 ComfyUI 平台,提供 ComfyUI 在線 環境和服務,以及 ComfyUI 工作流程 具有驚豔的視覺效果。 RunComfy還提供 AI Models, 幫助藝術家利用最新的AI工具創作出令人驚艷的藝術作品。