From language to images, open weights to APIs. Understand capabilities and compare real costs.
Find the right engine for your next idea.
Kuaishou Kaling provides an officially authorized API that is secure and stable. It supports synchronous updates for all official models, and its billing methods are consistent with those of the official platform. To integrate, simply replace the official API domain and token with your own on-premises instance.
快手可灵提供官方授权API，安全稳定。 同步更新支持官方所有模型、计费方式也与官方一致 对接仅需将官方 API 域名、令牌更换成本站即可
Translation queued · Showing source text
Kuaishou Kaling provides an officially authorized API that is secure and stable. It supports synchronous updates for all official models, and its billing methods are consistent with those of the official platform. To integrate, simply replace the official API domain and token with your own on-premises instance.
Kuaishou Kaling provides an officially authorized API that is secure and stable. It supports synchronous updates for all official models, and its billing methods are consistent with those of the official platform. To integrate, simply replace the official API domain and token with your own on-premises instance.
全球首个统一的多模态视频模型! · 输入任何内容，支持多模态视频生成 · 多模态输入，统一创作与修改 · 解决视频一致性问题 · 强大组合，创意更多 · 可控生成时间，3-10秒自由叙事 注意文图生视频和参考视频生视频价格不一样
Translation queued · Showing source text
视频生音效
Translation queued · Showing source text
全球领先的视频生成大模型：可灵是首个效果对标 Sora 、面向用户开放的视频生成大模型，目前在国内及国际上均处于领先地位。
Translation queued · Showing source text
全球领先的视频生成大模型：可灵是首个效果对标 Sora 、面向用户开放的视频生成大模型，目前在国内及国际上均处于领先地位。
Translation queued · Showing source text
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
V2.5 Turbo模型能力核心升级： · 动态质量大幅提升，打造电影级动感叙事 · 构图美学突破性升级，沉浸式光影氛围拉满 · 画风响应提升，支持2D日漫、国漫、美漫等多种风格 · 静态保持、拍摄视角响应更佳：广角、跟拍等刁钻镜头不在话下 · 主体响应增强，抽象主体理解力 · 复杂细微表情语义遵循，演技更上一层楼
Translation queued · Showing source text
【 可灵视频 2.6重磅发布 】 「听见画面，看见声音」 已为您定向开白API，即刻可用！ 打通“音”“画”两个世界：音画同出，高度协调节奏、情绪与叙事表达，实现视频生成“所见即所闻”！ 这次升级，我们重点强化了： ●音画协同：语音节奏、环境音与画面动作紧密呼应，避免“画面一套、声音一套”的割裂感。 ●音频质量：支持人声、音效、环境声等多类型声音生成，音质更干净、层次更丰富，更接近真实混音效果。 官方文档: https://docs.qingque.cn/d/home/eZQB6Bbl5WgW8eIVN--duPVl1?identityId=1oEFzU43FYK#section=h.6r1a53lc1aw0
Translation queued · Showing source text
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Kuaishou Kaling provides an officially authorized API that is secure and stable. It supports synchronous updates for all official models, and its billing methods are consistent with those of the official platform. To integrate, simply replace the official API domain and token with your own on-premises instance.
Kuaishou Kaling provides an officially authorized API that is secure and stable. It supports synchronous updates for all official models, and its billing methods are consistent with those of the official platform. To integrate, simply replace the official API domain and token with your own on-premises instance.
快手可灵提供官方授权API，安全稳定。 同步更新支持官方所有模型、计费方式也与官方一致 对接仅需将官方 API 域名、令牌更换成本站即可
Translation queued · Showing source text
LivePortrait: Efficient Portrait Animation with Stitching and Retargeting Control Jianzhu Guo 1*†   Dingyun Zhang 1,2*   Xiaoqiang Liu 1   Zhizhou Zhong 1,3   Yuan Zhang 1   1 Kuaishou Technology  2 University of Science and Technology of China  3 Fudan University 
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
- Model Details - How to Get Started With the Model - Uses - Risks, Limitations and Biases - Training - Evaluation - Environmental Impact - Technical Specifications - Citation Information - Model Card Authors **Model Description:** KLUE BERT base is a pre-trained BERT Model on Korean Language. The developers of KLUE BERT base developed the model in the context of the development of the Korean Language Understanding Evaluation (KLUE) Benchmark. - **Developed by:** See GitHub Repo for model developers - **Model Type:** Transformer-based language model - **Language(s):** Korean - **License:** cc-by-sa-4.0 - **Parent Model:** See the BERT base uncased model for more information about the BERT base model. - **Resources for more information:** - Research Paper - GitHub Repo
Pretrained RoBERTa Model on Korean Language. See Github and Paper for more details. _NOTE:_ Use `BertTokenizer` instead of RobertaTokenizer. (`AutoTokenizer` will load `BertTokenizer`)
_NOTE:_ Use `BertTokenizer` instead of RobertaTokenizer. (`AutoTokenizer` will load `BertTokenizer`)
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Adjust provider, category or input/output filters. New models are added continuously.
Adjust monthly token usage to compare estimated API costs.
Uses collected, comparable USD-per-million-token rates. Snapshots exclude cache discounts, tiers, extra reasoning output and taxes. Check current source prices.
Separate input, output and cache rates, then estimate the same workload. Image, audio and video rates may use items, duration or resolution rather than tokens.
Not necessarily. Check each version’s license, commercial restrictions and policies. Self-hosting also incurs compute and maintenance costs.
Rankings depend on tasks, versions and methods. Compare accuracy, latency, reliability and costs on your own workload.
