NVILA-Lite-2B-hf-preview
Efficient-Large-Model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。
基础资料已收录 · 缺失资料后续补充
输入 待核验→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗DISCOVER & COMPARE
探索 AI 模型 84994
Sana_1600M_1024px
Efficient-Large-Model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。
基础资料已收录 · 缺失资料后续补充
输入 文本→ 输出 图像
价格待核验多模态与渠道费用须分别核对
查看详情 ↗Sana_1600M_1024px_BF16
Efficient-Large-Model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。
输入 文本→ 输出 图像
价格待核验多模态与渠道费用须分别核对
查看详情 ↗SANA-Video_2.0_5B_720p
Efficient-Large-ModelSANA-Video 2.0 is an efficient diffusion transformer for high-resolution video generation. This release provides the 5B-class checkpoint jointly post-trained for text-to-video (T2V) and text-image-to-video (TI2V) generation at 720p for about eight seconds. The model combines gated bidirectional linear-attention layers with periodic dense softmax-attention anchors and shared Attention Residual aggregation. It uses Gemma 2 2B IT for text conditioning and the LTX 2.3 VAE contract with 128 latent channels and `(8, 32, 32)` temporal/spatial compression. The checkpoint is an inference artifact containing only the merged model `state_dict`. It does not contain optimizer, scheduler, training-state, or standalone LoRA tensors. The EMA base weights and ReFL post-training adapter were merged before release. Stored tensors retain their merged source dtypes; the official inference entry point casts the transformer to BF16.
译文排队中 · 当前显示来源原文
输入 文本→ 输出 视频
价格待核验多模态与渠道费用须分别核对
查看详情 ↗SANA-Video_2.0_5B_720p_4step
Efficient-Large-Model> **Research preview:** This distilled checkpoint is an early T2V-only preview. > For the original 50-step T2V + TI2V release, use > `SANA-Video_2.0_5B_720p`. SANA-Video 2.0 is an efficient diffusion transformer for high-resolution video generation. This preview provides the latest global-step-1000 full-model EMA checkpoint distilled for four-stage text-to-video generation at 720p, plus an auxiliary RL LoRA for post-hoc strength adjustment. It combines gated bidirectional linear-attention layers with periodic dense softmax-attention anchors and shared Attention Residual aggregation. The selected checkpoint is the latest global-step-1000 tri-temporal DMD EMA export initialized from the SANA-Video 2.0 SFT model after merging the ReFL step-500 adapter. DMD then updates the full transformer; the primary release artifact is therefore a full model, **not a LoRA adapter**.
译文排队中 · 当前显示来源原文
输入 文本→ 输出 视频
价格待核验多模态与渠道费用须分别核对
查看详情 ↗SANA1.5_4.8B_1024px
Efficient-Large-Model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。
基础资料已收录 · 缺失资料后续补充
输入 文本→ 输出 图像
价格待核验多模态与渠道费用须分别核对
查看详情 ↗SoL-Refiner-LTX-2.5-for-MiniMax-H3
Efficient-Large-Model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。
基础资料已收录 · 缺失资料后续补充
输入 待核验→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗StreamRender-H3
Efficient-Large-ModelStreamRender-H3 splits an interactive world into a **Code Game Engine** and a **Streaming Diffusion Render**. The engine keeps the world state in code (maps, physics, rules) and streams a semantic map for every frame. A two-step streaming video model built on MiniMax-H3 Ref2VA renders those maps into photorealistic video as the player drives, with the look set by a reference image and a prompt. - Two denoising steps per chunk in the distilled student. - Diffusion render of 217.96 ms per streaming step on 8 GB200 GPUs, a 3.67× speedup over the PyTorch baseline. - Fast Causal H3 VAE decodes 2 latent frames at 720p in 24 ms on one GB200, built by a self-improving agent loop. There are five distinct model components. Qwen's two storage formats are the same model. The causal decoder is constructed directly from its architecture configuration and student checkpoint; no native H3 video VAE checkpoint is needed. Streaming reference encoding uses TAE, and video decoding uses the trained causal decoder.
译文排队中 · 当前显示来源原文
输入 待核验→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗VILA1.5-3b
Efficient-Large-Model**Model type:** VILA is a visual language model (VLM) pretrained with interleaved image-text data at scale, enabling multi-image VLM. VILA is deployable on the edge, including Jetson Orin and laptop by AWQ 4bit quantization through TinyChat framework. We find: (1) image-text pairs are not enough, interleaved image-text is essential; (2) unfreezing LLM during interleaved image-text pre-training enables in-context learning; (3)re-blending text-only instruction data is crucial to boost both VLM and text-only performance. VILA unveils appealing capabilities, including: multi-image reasoning, in-context learning, visual chain-of-thought, and better world knowledge. - The code is released under the Apache 2.0 license as found in the LICENSE file. - The pretrained weights are released under the CC-BY-NC-SA-4.0 license. - The service is a research preview intended for non-commercial use only, and is subject to the following licenses and terms: - Model License of LLaMA - Terms of Use of the data generated by OpenAI - Dataset Licenses for each one used during training. **Where to send questions or comments about the model:** https://github.com/NVLabs/VILA/issues
译文排队中 · 当前显示来源原文
输入 文本→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗lite-whisper-large-v3
efficient-speechLite-Whisper is a compressed version of OpenAI Whisper with LiteASR. See our GitHub repository and paper for details.
译文排队中 · 当前显示来源原文
输入 音频→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗lite-whisper-large-v3-acc
efficient-speechLite-Whisper is a compressed version of OpenAI Whisper with LiteASR. See our GitHub repository and paper for details.
译文排队中 · 当前显示来源原文
输入 音频→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗lite-whisper-large-v3-fast
efficient-speechLite-Whisper is a compressed version of OpenAI Whisper with LiteASR. See our GitHub repository and paper for details. The paper is also available on Hugging Face: Link to Hugging Face Paper Page
译文排队中 · 当前显示来源原文
输入 音频→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗lite-whisper-large-v3-turbo
efficient-speech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。
输入 音频→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗lite-whisper-large-v3-turbo-acc
efficient-speechLite-Whisper is a compressed version of OpenAI Whisper with LiteASR. See our GitHub repository and paper for details. The easiest way to run our model is to use our integration with HuggingFace Transformers library. We provide model weights for the compressed version of OpenAI Whisper series here.
译文排队中 · 当前显示来源原文
输入 音频→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗lite-whisper-large-v3-turbo-fast
efficient-speech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。
输入 音频→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗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。
基础资料已收录 · 缺失资料后续补充
输入 文本→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗cohere-asr-ja
efwkjn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。
基础资料已收录 · 缺失资料后续补充
输入 音频→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗whisper-ja-1.5B
efwkjn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。
基础资料已收录 · 缺失资料后续补充
输入 音频→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗whisper-ja-760M
efwkjn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。
基础资料已收录 · 缺失资料后续补充
输入 音频→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗whisper-ja-anime-v0.3
efwkjn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。
输入 音频→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗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。
基础资料已收录 · 缺失资料后续补充
输入 文本→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗lucida
egeorcunLucida is a BiRefNet-based background-removal / image-matting model fine-tuned to excel where most open models fail: **camouflaged objects, transparent materials (glass), text & logos, VFX glows, and illustrations** — while staying competitive everywhere else. On our 203-image, 9-category benchmark (MAE, lower is better) Lucida leads every model we tested — including a commercial reference — in **camouflage (0.0270)** and **illustration (0.0092)**, beats the commercial reference in **text/logo preservation (0.0091 vs 0.0123)** and in **print-design/sticker art (0.0235 — 2x better than every model measured)**, and sets our best-ever **transparency-in-mixed-objects** handling and **overall (0.0257)** score — ahead of every model we measured, specialist or commercial, on the 203-image average. Full benchmark, gallery and training recipe: **https://github.com/egeorcun/lucida** — or try the live demo. > **Changelog note (2026-07-24):** an experimental v13 build was published for a day and then > reverted — community testing showed it regressed on real-world layered artwork > (poster/collage-style illustrations) that our synthetic design test set does not cover. > The current weights are the proven v7. The v13 improvements (reduced background haze on > real photos, a transparency milestone) will return in v14 together with the fix.
译文排队中 · 当前显示来源原文
输入 图像→ 输出 图像
价格待核验多模态与渠道费用须分别核对
查看详情 ↗EndoViT
egeozsoy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。
输入 待核验→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗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。
基础资料已收录 · 缺失资料后续补充
输入 待核验→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗暂未找到匹配模型
可以调整厂商、分类或输入输出条件；新模型正持续收录。
COST EXPLORER
好模型，也要算好成本。
调整月度 Token 用量，直观比较不同模型的预估 API 开支。
1 M = 100 万 Token · 美元计价
仅比较同一渠道的基础文本 Token 报价
仅比较同一渠道的基础文本 Token 报价
使用已采集且单位可比的 USD / 百万 Token 渠道报价。报价为采集时快照；不计缓存优惠、阶梯价、推理额外输出与税费，请以来源的当前报价为准。
MODEL HANDBOOK
读懂模型，再做选择
API 价格应该怎么比较？+
先区分输入、输出和缓存价格，再使用同一任务和用量估算总费用。图像、音频和视频可能按张、时长或分辨率计费，不能直接与 Token 单价比较。
开放权重，就代表可以免费商用吗？+
不一定。必须逐一核对具体模型版本的许可证、商用限制及使用政策。自己部署还需要考虑显存、推理资源和运维费用。
排行榜第一，就是最适合我的模型吗？+
榜单取决于测试任务、版本与评测方法。建议用实际业务样本比较准确性、时延、稳定性和成本，再选择模型。