AI 모델 라이브러리

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 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。

번역 대기 중 · 원문 표시

영상 생성

입력 이미지→ 출력 영상

요금 미확인멀티모달 및 채널 요금 별도 확인

자세히 보기 ↗

비교 추가출처 / 문서 ↗

Wan2.2-Fun-A14B-Control-Camera

alibaba-pai

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 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。

번역 대기 중 · 원문 표시

영상 생성

입력 텍스트→ 출력 영상

요금 미확인멀티모달 및 채널 요금 별도 확인

자세히 보기 ↗

비교 추가출처 / 문서 ↗

Wan2.2-Fun-A14B-InP

alibaba-pai

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 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。

번역 대기 중 · 원문 표시

영상 생성

입력 이미지→ 출력 영상

요금 미확인멀티모달 및 채널 요금 별도 확인

자세히 보기 ↗

비교 추가출처 / 문서 ↗

Wan2.2-Fun-Reward-LoRAs

alibaba-pai

We 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.

번역 대기 중 · 원문 표시

영상 생성

입력 텍스트→ 출력 영상

요금 미확인멀티모달 및 채널 요금 별도 확인

자세히 보기 ↗

비교 추가출처 / 문서 ↗

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。

번역 대기 중 · 원문 표시

영상 생성

입력 텍스트→ 출력 영상

요금 미확인멀티모달 및 채널 요금 별도 확인

자세히 보기 ↗

비교 추가출처 / 문서 ↗

Z-Image-Fun-Controlnet-Union-2.1

alibaba-pai

Then run the file `examples/z_image_fun/predict_t2i_control_2.1.py` and `examples/z_image_fun/predict_i2i_inpaint_2.1.py`.

번역 대기 중 · 원문 표시

분류 준비 중

입력 미확인→ 출력 미확인

요금 미확인멀티모달 및 채널 요금 별도 확인

자세히 보기 ↗

비교 추가출처 / 문서 ↗

Z-Image-Fun-Lora-Distill

alibaba-pai

The 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

번역 대기 중 · 원문 표시

이미지 생성

입력 텍스트→ 출력 이미지

요금 미확인멀티모달 및 채널 요금 별도 확인

자세히 보기 ↗

비교 추가출처 / 문서 ↗

Z-Image-Turbo-Fun-Controlnet-Union

alibaba-pai

The 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.

번역 대기 중 · 원문 표시

분류 준비 중

입력 미확인→ 출력 미확인

요금 미확인멀티모달 및 채널 요금 별도 확인

자세히 보기 ↗

비교 추가출처 / 문서 ↗

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.

번역 대기 중 · 원문 표시

분류 준비 중

입력 미확인→ 출력 미확인

요금 미확인멀티모달 및 채널 요금 별도 확인

자세히 보기 ↗

비교 추가출처 / 문서 ↗

mossformer2-librimix-2spk

alibabasglab

source code for model inference, - github: https://github.com/alibabasglab/MossFormer2 - modelscope: https://modelscope.cn/models/iic/speech_mossformer2_separation_temporal_8k

번역 대기 중 · 원문 표시

분류 준비 중

입력 미확인→ 출력 미확인

요금 미확인멀티모달 및 채널 요금 별도 확인

자세히 보기 ↗

비교 추가출처 / 문서 ↗