Wispr Flow-Now on Android!
Mini toolsHunyuan models
Browse all models from this model family.
to
-
By TencentHunyuanImage-3.0-Instruct is Tencent’s 80B MoE image-editing model that first reasons over an input image and text, then performs stable one-line edits and multi-image fusion for layout-safe poster, logo and product updates.NewImageReleased 1mo ago
-
By TencentTencent HY-Motion 1.0 is an open text-to-3D human motion generator using billion-scale Diffusion Transformer and flow matching, turning prompts into skeleton-based 3D animations ready for game and character pipelines.NewImageReleased 1mo ago
-
By TencentTencent-HY-MT1.5 is a multilingual machine-translation family with 1.8B and 7B models, supporting 33 languages plus dialects and advanced features like terminology control, context-aware and format-preserving translationNewTextReleased 1mo ago
-
By TencentTencent Hunyuan 3D, powered by the Hunyuan 3D Generate Large Model 2.5, is a 3D AI engine that turns text, images and sketches into low-poly 3D assets and scenes, supporting text-to-3D, image-to-3D, animation and texture generation in the browser.NewImageReleased 2mo ago
-
By TencentHunyuanOCR is Tencent Hunyuan’s 1B parameter end-to-end OCR expert VLM. It reads documents, screenshots, and video frames, handling text detection, recognition, layout parsing, information extraction, subtitles, and photo translation in one shot, with strong multilingual support and state-of-the-art accuracy.TextReleased 3mo ago
-
By TencentHunyuanVideo-1.5 is Tencent's 8.3B-parameter open-source video diffusion model for text-to-video and image-to-video generation, delivering high-quality, stable motion clips while running efficiently on consumer-grade GPUs.VideoReleased 3mo ago
-
By TencentHunyuanWorld Mirror is a scene-reconstruction and world-modeling system. It turns photos and videos into a consistent digital twin that you can explore, edit, and render, with export to common 3D formats for simulation, virtual production, and design.ImageReleased 4mo ago
-
By TencentHunyuanImage 3.0 is Tencent’s next-gen text-to-image model. It delivers sharper detail, stronger style and identity consistency, improved typography, and precise, in-place editing—built for fast iteration from concept to production-ready visuals.ImageReleased 4mo ago
-
3dReleased 5mo ago
-
By TencentHunyuan-MT-7B is Tencent’s compact 7B multilingual model tuned for fast, accurate translation and cross-lingual tasks. It supports long-context inputs, preserves formatting and terminology, and outputs structured JSON for enterprise pipelines.TextReleased 5mo ago
-
By TencentHunyuanVideo-Avatar is Tencent’s talking-avatar video generator. It turns text or audio into lifelike, lip-synced video characters with controllable voice, style, gaze, and background—designed for real-time agents, tutorials, marketing spokespeople, and localized content at scale.VideoReleased 8mo ago
-
By TencentHunyuanCustom is Tencent’s customization framework for the Hunyuan model family. It lets enterprises fine-tune or adapt base Hunyuan models—text, vision, or multimodal—for their own domains, while keeping deployment secure and efficient on Tencent Cloud.VideoReleased 9mo ago
-
By TencentHunyuan3D-Paint is Tencent’s text-to-3D painting and texture generation model. It takes existing 3D meshes or scenes and generates high-quality, style-consistent textures from natural language prompts or reference images, making asset creation faster for games, AR/VR, and digital twins.ImageReleased 1y ago
-
By TencentHunyuan3D-2 is Tencent’s second-generation text-to-3D model. It creates detailed 3D assets directly from natural language prompts or reference images, with higher fidelity, cleaner topology, and faster generation than its predecessor—suited for games, AR/VR, and digital content pipelines.ImageReleased 1y ago
-
VideoReleased 1y ago
-
By TencentHunyuan-Large is Tencent’s flagship large language model in the Hunyuan family. It’s built for advanced reasoning, coding, and multilingual tasks, with long-context support, tool/function calling, and structured (JSON) outputs for enterprise copilots and RAG applications.TextReleased 1y ago
No models found
Try adjusting your search or filters.
