Wan2.1-Fun-V1.1-14B-Control-Camera
alibaba-pai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 视频
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 84853
Wan2.1-Fun-V1.1-14B-InP
alibaba-paiV1.1: | 名称 | 存储空间 | Hugging Face | Model Scope | 描述 | |--|--|--|--|--| | Wan2.1-Fun-V1.1-1.3B-InP | 19.0 GB | 🤗Link | 😄Link | Wan2.1-Fun-V1.1-1.3B文图生视频权重，以多分辨率训练，支持首尾图预测。 | | Wan2.1-Fun-V1.1-14B-InP | 47.0 GB | 🤗Link | 😄Link | Wan2.1-Fun-V1.1-14B文图生视频权重，以多分辨率训练，支持首尾图预测。 | | Wan2.1-Fun-V1.1-1.3B-Control | 19.0 GB | 🤗Link | 😄Link| Wan2.1-Fun-V1.1-1.3B视频控制权重支持不同的控制条件，如Canny、Depth、Pose、MLSD等，支持参考图 + 控制条件进行控制，支持使用轨迹控制。支持多分辨率（512，768，1024）的视频预测，支持多分辨率（512，768，1024）的视频预测，以81帧、每秒16帧进行训练，支持多语言预测 | | Wan2.1-Fun-V1.1-14B-Control | 47.0 GB | 🤗Link | 😄Link| Wan2.1-Fun-V1.1-14B视视频控制权重支持不同的控制条件，如Canny、Depth、Pose、MLSD等，支持参考图 + 控制条件进行控制，支持使用轨迹控制。支持多分辨率（512，768，1024）的视频预测，支持多分辨率（512，768，1024）的视频预测，以81帧、每秒16帧进行训练，支持多语言预测 | | Wan2.1-Fun-V1.1-1.3B-Control-Camera | 19.0 GB | 🤗Link | 😄Link| Wan2.1-Fun-V1.1-1.3B相机镜头控制权重。支持多分辨率（512，768，1024）的视频预测，支持多分辨率（512，768，1024）的视频预测，以81帧、每秒16帧进行训练，支持多语言预测 | | Wan2.1-Fun-V1.1-14B-Control | 47.0 GB | 🤗Link | 😄Link| Wan2.1-Fun-V1.1-14B相机镜头控制权重。支持多分辨率（512，768，1024）的视频预测，支持多分辨率（512，768，1024）的视频预测，以81帧、每秒16帧进行训练，支持多语言预测 | V1.0: | 名称 | 存储空间 | Hugging Face | Model Scope | 描述 | |--|--|--|--|--| | Wan2.1-Fun-1.3B-InP | 19.0 GB | 🤗Link | 😄Link | Wan2.1-Fun-1.3B文图生视频权重，以多分辨率训练，支持首尾图预测。 | | Wan2.1-Fun-14B-InP | 47.0 GB | 🤗Link | 😄Link | Wan2.1-Fun-14B文图生视频权重，以多分辨率训练，支持首尾图预测。 | | Wan2.1-Fun-1.3B-Control | 19.0 GB | 🤗Link | 😄Link| Wan2.1-Fun-1.3B视频控制权重，支持不同的控制条件，如Canny、Depth、Pose、MLSD等，同时支持使用轨迹控制。支持多分辨率（512，768，1024）的视频预测，支持多分辨率（512，768，1024）的视频预测，以81帧、每秒16帧进行训练，支持多语言预测 | | Wan2.1-Fun-14B-Control | 47.0 GB | 🤗Link | 😄Link| Wan2.1-Fun-14B视频控制权重，支持不同的控制条件，如Canny、Depth、Pose、MLSD等，同时支持使用轨迹控制。支持多分辨率（512，768，1024）的视频预测，支持多分辨率（512，768，1024）的视频预测，以81帧、每秒16帧进行训练，支持多语言预测 | Windows 的详细信息： - 操作系统 Windows 10 - python: python3.10 & python3.11 - pytorch: torch2.2.0 - CUDA: 11.8 & 12.1 - CUDNN: 8+ - GPU： Nvidia-3060 12G & Nvidia-3090 24G
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 ↗Wan2.2-Fun-5B-Control
alibaba-pai- 目录 - 模型地址 - 视频作品 - 快速启动 - 如何使用 - 参考文献 - 许可证 阿里云在Freetier提供免费GPU时间，获取并在阿里云PAI-DSW中使用，5分钟内即可启动CogVideoX-Fun。 我们的ComfyUI界面如下，具体查看ComfyUI README。
输入 图像→ 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 ↗Wan2.2-Fun-5B-Control-Camera
alibaba-pai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 图像→ 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 ↗Wan2.2-Fun-5B-InP
alibaba-pai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 图像→ 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 ↗Wan2.2-Fun-A14B-Control
alibaba-paiWindows 的详细信息： - 操作系统 Windows 10 - python: python3.10 & python3.11 - pytorch: torch2.2.0 - CUDA: 11.8 & 12.1 - CUDNN: 8+ - GPU： Nvidia-3060 12G & Nvidia-3090 24G Linux 的详细信息： - 操作系统 Ubuntu 20.04, CentOS - python: python3.10 & python3.11 - pytorch: torch2.2.0 - CUDA: 11.8 & 12.1 - CUDNN: 8+ - GPU：Nvidia-V100 16G & Nvidia-A10 24G & Nvidia-A100 40G & Nvidia-A100 80G 由于Wan2.2的参数非常大，我们需要考虑显存节省方案，以节省显存适应消费级显卡。我们给每个预测文件都提供了GPU_memory_mode，可以在model_cpu_offload，model_cpu_offload_and_qfloat8，sequential_cpu_offload中进行选择。该方案同样适用于CogVideoX-Fun的生成。
输入 图像→ 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 ↗Wan2.2-Fun-A14B-Control-Camera
alibaba-paiWindows 的详细信息： - 操作系统 Windows 10 - python: python3.10 & python3.11 - pytorch: torch2.2.0 - CUDA: 11.8 & 12.1 - CUDNN: 8+ - GPU： Nvidia-3060 12G & Nvidia-3090 24G Linux 的详细信息： - 操作系统 Ubuntu 20.04, CentOS - python: python3.10 & python3.11 - pytorch: torch2.2.0 - CUDA: 11.8 & 12.1 - CUDNN: 8+ - GPU：Nvidia-V100 16G & Nvidia-A10 24G & Nvidia-A100 40G & Nvidia-A100 80G 由于Wan2.2的参数非常大，我们需要考虑显存节省方案，以节省显存适应消费级显卡。我们给每个预测文件都提供了GPU_memory_mode，可以在model_cpu_offload，model_cpu_offload_and_qfloat8，sequential_cpu_offload中进行选择。该方案同样适用于CogVideoX-Fun的生成。
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 ↗Wan2.2-Fun-A14B-InP
alibaba-paiWindows 的详细信息： - 操作系统 Windows 10 - python: python3.10 & python3.11 - pytorch: torch2.2.0 - CUDA: 11.8 & 12.1 - CUDNN: 8+ - GPU： Nvidia-3060 12G & Nvidia-3090 24G Linux 的详细信息： - 操作系统 Ubuntu 20.04, CentOS - python: python3.10 & python3.11 - pytorch: torch2.2.0 - CUDA: 11.8 & 12.1 - CUDNN: 8+ - GPU：Nvidia-V100 16G & Nvidia-A10 24G & Nvidia-A100 40G & Nvidia-A100 80G 由于Wan2.2的参数非常大，我们需要考虑显存节省方案，以节省显存适应消费级显卡。我们给每个预测文件都提供了GPU_memory_mode，可以在model_cpu_offload，model_cpu_offload_and_qfloat8，sequential_cpu_offload中进行选择。该方案同样适用于CogVideoX-Fun的生成。
输入 图像→ 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 ↗Wan2.2-Fun-Reward-LoRAs
alibaba-paiWe explore the Reward Backpropagation technique 1 2 to optimized the generated videos by Wan2.2-Fun for better alignment with human preferences. We provide the following pre-trained models (i.e. LoRAs) along with the training script. You can use these LoRAs to enhance the corresponding base model as a plug-in or train your own reward LoRA. For more details, please refer to our GitHub repo. > [!NOTE] > We found that, MPS reward LoRA for the low-noise model converges significantly more slowly than on the other models, and may not deliver satisfactory results. Therefore, for the low-noise model, we recommend using HPSv2.1 reward LoRA.
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 ↗Wan2.2-VACE-Fun-A14B
alibaba-pai- 目录 - 模型地址 - 视频作品 - 快速启动 - 如何使用 - 参考文献 - 许可证 阿里云在Freetier提供免费GPU时间，获取并在阿里云PAI-DSW中使用，5分钟内即可启动CogVideoX-Fun。 我们的ComfyUI界面如下，具体查看ComfyUI README。
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 ↗Z-Image-Fun-Controlnet-Union-2.1
alibaba-paiThen run the file `examples/z_image_fun/predict_t2i_control_2.1.py` and `examples/z_image_fun/predict_i2i_inpaint_2.1.py`.
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 ↗Z-Image-Fun-Lora-Distill
alibaba-paiThe 2602 model tends to produce blurry images with sigmas below 0.500, as the distillation model was not trained on certain steps. The 2603 model introduces a random timesteps strategy, making it better adapted to sigmas below 0.500. As shown below, when using kl_optimal, many sigmas fall below 0.500. The 2603 model handles these cases correctly, while the 2602 model does not. Note that although kl_optimal is used in the figure, we still recommend using the simple scheduler for inference. Z-Image-Fun-Lora-Distill-8-Steps-2602 Z-Image-Fun-Lora-Distill-4-Steps-2602 Z-Image-Fun-Lora-Distill-8-Steps
译文排队中 · 当前显示来源原文
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 ↗Z-Image-Turbo-Fun-Controlnet-Union
alibaba-paiThe new control model with more control blocks and inpaint mode is released. - This ControlNet is added on 6 blocks. - The model was trained from scratch for 10,000 steps on a dataset of 1 million high-quality images covering both general and human-centric content. Training was performed at 1328 resolution using BFloat16 precision, with a batch size of 64, a learning rate of 2e-5, and a text dropout ratio of 0.10. - It supports multiple control conditions—including Canny, HED, Depth, Pose and MLSD can be used like a standard ControlNet. - You can adjust control_context_scale for stronger control and better detail preservation. For better stability, we highly recommend using a detailed prompt. The optimal range for control_context_scale is from 0.65 to 0.80. Then download the weights into models/Diffusion_Transformer and models/Personalized_Model.
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 ↗Z-Image-Turbo-Fun-Controlnet-Union-2.1
alibaba-pai- **[2026.02.26]** Update to version 2602, with support for Gray Control. - **[2026.01.12]** Update to version 2601, with support for Scribble Control. Added lite models (1.9GB, 5 layers). Retrained Control and Tile models with enriched mask varieties, improved training schedules, and multi-resolution control images (512~1536) to fix mask pattern leakage and large `control_context_scale` artifacts. - **[2025.12.22]** Performed 8-step distillation on v2.1 to restore acceleration lost when applying ControlNet. Uploaded a tile model for super-resolution. - **[2025.12.17]** Fixed v2.0 typo (`control_layers` used instead of `control_noise_refiner`), which caused double forward pass and slow inference. Speed restored in v2.1. - This ControlNet is applied to 15 layer blocks and 2 refiner layer blocks (Lite models: 3 layer blocks and 2 refiner layer blocks). It supports multiple control conditions including Canny, HED, Depth, Pose, and MLSD (supporting Scribble in 2601 models and Gray in 2602 models). - Inpainting mode is also supported. For inpaint mode, use a larger `control_context_scale` for better image continuity. - **Training Process:** - **2.0:** Trained from scratch for 70,000 steps on 1M high-quality images (general and human-centric content) at 1328 resolution with BFloat16 precision, batch size 64, learning rate 2e-5, and text dropout ratio 0.10. - **2.1:** Continued training from 2.0 weights for 11,000 additional steps after fixing a typo, using the same parameters and dataset. - **2.1-8-steps:** Distilled from version 2.1 using an 8-step distillation algorithm for 5,500 steps. - **Note on Steps:** - **2.0 and 2.1:** Higher `control_context_scale` values may require more inference steps for better results, likely because the control model has not been distilled. - **2.1-8-steps:** Use 8 steps for inference. - Adjust `control_context_scale` (optimal range: 0.65–1.00) for stronger control and better detail preservation. A detailed prompt is highly recommended for stability. - In versions 2.0 and 2.1, applying ControlNet to Z-Image-Turbo caused loss of acceleration capability and blurry images. For strength and step count testing details, refer to Scale Test Results (generated with version 2.0). The old 8-steps model had bright spots/artifacts when the control_context_scale was too large, while the new version does not.
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 ↗mossformer2-librimix-2spk
alibabasglabsource code for model inference, - github: https://github.com/alibabasglab/MossFormer2 - modelscope: https://modelscope.cn/models/iic/speech_mossformer2_separation_temporal_8k
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 ↗ltx2310eros
alibaybay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 ↗MiniMax-H3-Prompt-Rewriter-GGUF
alibaybay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 ↗qwen_progressive_thinking_16bit
alibidaran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 ↗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 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。
输入 文本 · 图像→ 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 ↗JevK5
alibiserikbayJevK5 is an independent, Apache-2.0 open-source alternative to TypeSafe's Jev for typed decisions. It reads a state and a yes/no (`noul`), choice, or score question and returns a **probability for every option in one forward pass, with zero generated tokens**. The open weights can be self-hosted using the JevK5 runtime, which serves a TypeSafe-style `/v1/systemone` endpoint. This is not Jev's model or architecture and is not affiliated with TypeSafe AI. Use the JevK5 runtime shown below to read option probabilities. Generic text-generation examples on the Hub call `generate()` and do not perform JevK5's decision readout. - **Base:** Qwen3.5-4B, with a LoRA (rank 16, attention projections) merged into the weights - **Readout:** SemIf's protocol (TheoLeeCJ/SemIf, MIT): a softmax over the answer letters' next-token logits, divided by one calibration temperature. Questions with more than 16 options are read in several passes and combined with a second temperature. Both are in `jevk5_config.json`: `temperature` 1.22 and `knockout_temperature` 0.93 - **Runtime:** github.com/allebee/jevk5, 0.3.0 or later. One CUDA graph per padded input length: ~13 ms per decision on an H100 - **License:** Apache-2.0 - **Previous version:** v0.2 stays available under the Hub tag `v0.2` (see Use)
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 ↗JevK5-2B
alibiserikbay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 ↗JevK5-9B
alibiserikbay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 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗JevK5-GGUF
alibiserikbayGGUF builds of JevK5 (4B), JevK5-9B and JevK5-2B for llama.cpp, which runs on NVIDIA, AMD, Intel and Apple GPUs and on plain CPUs. JevK5 is an Apache-2.0 open alternative to TypeSafe's Jev. It reads a document and a yes/no, choice, or score question and returns **a probability for every option in one forward pass, with nothing generated**. It is not affiliated with TypeSafe AI. Every file was checked against its unquantized model on JevBench's 231 public decisions, scored the same way: how often it gives the same answer, and its accuracy per tier. We publish a file only if at least 95% of its answers match. **Each model has its own temperatures; pass them to the client as shown under "Run it".**
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 ↗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。