Total runs:
86.7K
Run Growth:
-1.1K
Growth Rate:
-1.25%
Sponsored by
APIMart
alibaba-pai / EasyAnimateV5.1-12b-zh-InP-diffusers
Model's Last Updated: February 27 2025
Introduction of EasyAnimateV5.1-12b-zh-InP-diffusers
Model Details of EasyAnimateV5.1-12b-zh-InP-diffusers
简介
EasyAnimate是一个基于transformer结构的pipeline，可用于生成AI图片与视频、训练Diffusion Transformer的基线模型与Lora模型，我们支持从已经训练好的EasyAnimate模型直接进行预测，生成不同分辨率，6秒左右、fps8的视频（EasyAnimateV5.1，1 ~ 49帧），也支持用户训练自己的基线模型与Lora模型，进行一定的风格变换。
模型地址
EasyAnimateV5.1:
7B:
| 名称 | 种类 | 存储空间 | Hugging Face | Model Scope | 描述 |
|---|---|---|---|---|---|
| EasyAnimateV5.1-7b-zh-InP | EasyAnimateV5.1 | 30 GB | 🤗Link | 😄Link | 官方的图生视频权重。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49帧、每秒8帧进行训练，支持多语言预测 |
| EasyAnimateV5.1-7b-zh-Control | EasyAnimateV5.1 | 30 GB | 🤗Link | 😄Link | 官方的视频控制权重，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49帧、每秒8帧进行训练，支持多语言预测 |
| EasyAnimateV5.1-7b-zh-Control-Camera | EasyAnimateV5.1 | 30 GB | 🤗Link | 😄Link | 官方的视频相机控制权重，支持通过输入相机运动轨迹控制生成方向。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49帧、每秒8帧进行训练，支持多语言预测 |
| EasyAnimateV5.1-7b-zh | EasyAnimateV5.1 | 30 GB | 🤗Link | 😄Link | 官方的文生视频权重。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49帧、每秒8帧进行训练，支持多语言预测 |
12B:
| 名称 | 种类 | 存储空间 | Hugging Face | Model Scope | 描述 |
|---|---|---|---|---|---|
| EasyAnimateV5.1-12b-zh-InP | EasyAnimateV5.1 | 39 GB | 🤗Link | 😄Link | 官方的图生视频权重。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49帧、每秒8帧进行训练，支持多语言预测 |
| EasyAnimateV5.1-12b-zh-Control | EasyAnimateV5.1 | 39 GB | 🤗Link | 😄Link | 官方的视频控制权重，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49帧、每秒8帧进行训练，支持多语言预测 |
| EasyAnimateV5.1-12b-zh-Control-Camera | EasyAnimateV5.1 | 39 GB | 🤗Link | 😄Link | 官方的视频相机控制权重，支持通过输入相机运动轨迹控制生成方向。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49帧、每秒8帧进行训练，支持多语言预测 |
| EasyAnimateV5.1-12b-zh | EasyAnimateV5.1 | 39 GB | 🤗Link | 😄Link | 官方的文生视频权重。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49帧、每秒8帧进行训练，支持多语言预测 |
视频作品
图生视频 EasyAnimateV5.1-12b-zh-InP
文生视频 EasyAnimateV5.1-12b-zh
控制生视频 EasyAnimateV5.1-12b-zh-Control
轨迹控制
普通控制生视频（Canny、Pose、Depth等）
相机镜头控制 EasyAnimateV5.1-12b-zh-Control-Camera
| Pan Up | Pan Left | Pan Right |
| Pan Down | Pan Up + Pan Left | Pan Up + Pan Right |
如何使用
a、显存节省方案
由于EasyAnimateV5和V5.1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。
- model_cpu_offload代表整个模型在使用后会进入cpu，可以节省部分显存。
- model_cpu_offload_and_qfloat8代表整个模型在使用后会进入cpu，并且对transformer模型进行了float8的量化，可以节省更多的显存。
- sequential_cpu_offload代表模型的每一层在使用后会进入cpu，速度较慢，节省大量显存。
qfloat8会降低模型的性能，但可以节省更多的显存。如果显存足够，推荐使用model_cpu_offload。
b、通过comfyui
具体查看 ComfyUI README 。
c、运行python文件
- 步骤1：下载对应 权重 放入models文件夹。
-
步骤2：根据不同的权重与预测目标使用不同的文件进行预测。
-
文生视频：
- 使用predict_t2v.py文件中修改prompt、neg_prompt、guidance_scale和seed。
- 而后运行predict_t2v.py文件，等待生成结果，结果保存在samples/easyanimate-videos文件夹中。
-
图生视频：
- 使用predict_i2v.py文件中修改validation_image_start、validation_image_end、prompt、neg_prompt、guidance_scale和seed。
- validation_image_start是视频的开始图片，validation_image_end是视频的结尾图片。
- 而后运行predict_i2v.py文件，等待生成结果，结果保存在samples/easyanimate-videos_i2v文件夹中。
-
视频生视频：
- 使用predict_v2v.py文件中修改validation_video、validation_image_end、prompt、neg_prompt、guidance_scale和seed。
- validation_video是视频生视频的参考视频。您可以使用以下视频运行演示： 演示视频
- 而后运行predict_v2v.py文件，等待生成结果，结果保存在samples/easyanimate-videos_v2v文件夹中。
-
普通控制生视频（Canny、Pose、Depth等）：
- 使用predict_v2v_control.py文件中修改control_video、validation_image_end、prompt、neg_prompt、guidance_scale和seed。
- control_video是控制生视频的控制视频，是使用Canny、Pose、Depth等算子提取后的视频。您可以使用以下视频运行演示： 演示视频
- 而后运行predict_v2v_control.py文件，等待生成结果，结果保存在samples/easyanimate-videos_v2v_control文件夹中。
- 轨迹控制视频：
-
相机控制视频：
- 使用predict_v2v_control.py文件中修改control_video、ref_image、validation_image_end、prompt、neg_prompt、guidance_scale和seed。
- control_camera_txt是相机控制视频的控制文件，ref_image是参考的首帧图片。您可以使用以下图片和控制视频运行演示： 演示图像 ， 演示文件（来自于CameraCtrl）
- 而后运行predict_v2v_control.py文件，等待生成结果，结果保存在samples/easyanimate-videos_v2v_control文件夹中。
- 推荐使用ComfyUI进行交互。
-
文生视频：
- 步骤3：如果想结合自己训练的其他backbone与Lora，则看情况修改predict_t2v.py中的predict_t2v.py和lora_path。
d、通过ui界面
webui支持文生视频、图生视频、视频生视频和普通控制生视频（Canny、Pose、Depth等）
- 步骤1：下载对应 权重 放入models文件夹。
- 步骤2：运行app.py文件，进入gradio页面。
- 步骤3：根据页面选择生成模型，填入prompt、neg_prompt、guidance_scale和seed等，点击生成，等待生成结果，结果保存在sample文件夹中。
快速启动
1. 云使用: AliyunDSW/Docker
a. 通过阿里云 DSW
DSW 有免费 GPU 时间，用户可申请一次，申请后3个月内有效。
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EasyAnimate
b. 通过ComfyUI
我们的ComfyUI界面如下，具体查看
ComfyUI README
。
c. 通过docker
使用docker的情况下，请保证机器中已经正确安装显卡驱动与CUDA环境，然后以此执行以下命令：
# pull image
docker pull mybigpai-public-registry.cn-beijing.cr.aliyuncs.com/easycv/torch_cuda:easyanimate
# enter image
docker run -it -p 7860:7860 --network host --gpus all --security-opt seccomp:unconfined --shm-size 200g mybigpai-public-registry.cn-beijing.cr.aliyuncs.com/easycv/torch_cuda:easyanimate
# clone code
git clone https://github.com/aigc-apps/EasyAnimate.git
# enter EasyAnimate's dir
cd EasyAnimate
# download weights
mkdir models/Diffusion_Transformer
mkdir models/Motion_Module
mkdir models/Personalized_Model
# Please use the hugginface link or modelscope link to download the EasyAnimateV5.1 model.
# https://huggingface.co/alibaba-pai/EasyAnimateV5.1-12b-zh-InP
# https://modelscope.cn/models/PAI/EasyAnimateV5.1-12b-zh-InP
2. 本地安装: 环境检查/下载/安装
a. 环境检查
我们已验证EasyAnimate可在以下环境中执行：
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
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
我们需要大约 60GB 的可用磁盘空间，请检查！
EasyAnimateV5.1-12B的视频大小可以由不同的GPU Memory生成，包括：
| GPU memory | 384x672x25 | 384x672x49 | 576x1008x25 | 576x1008x49 | 768x1344x25 | 768x1344x49 |
|---|---|---|---|---|---|---|
| 16GB | 🧡 | ⭕️ | ⭕️ | ⭕️ | ❌ | ❌ |
| 24GB | 🧡 | 🧡 | 🧡 | 🧡 | 🧡 | ❌ |
| 40GB | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
| 80GB | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
EasyAnimateV5.1-7B的视频大小可以由不同的GPU Memory生成，包括：
| GPU memory | 384x672x25 | 384x672x49 | 576x1008x25 | 576x1008x49 | 768x1344x25 | 768x1344x49 |
|---|---|---|---|---|---|---|
| 16GB | 🧡 | 🧡 | ⭕️ | ⭕️ | ❌ | ❌ |
| 24GB | ✅ | ✅ | ✅ | 🧡 | 🧡 | ❌ |
| 40GB | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
| 80GB | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
✅ 表示它可以在"model_cpu_offload"的情况下运行，🧡代表它可以在"model_cpu_offload_and_qfloat8"的情况下运行，⭕️ 表示它可以在"sequential_cpu_offload"的情况下运行，❌ 表示它无法运行。请注意，使用sequential_cpu_offload运行会更慢。
有一些不支持torch.bfloat16的卡型，如2080ti、V100，需要将app.py、predict文件中的weight_dtype修改为torch.float16才可以运行。
EasyAnimateV5.1-12B使用不同GPU在25个steps中的生成时间如下：
| GPU | 384x672x72 | 384x672x49 | 576x1008x25 | 576x1008x49 | 768x1344x25 | 768x1344x49 |
|---|---|---|---|---|---|---|
| A10 24GB | 约120秒 (4.8s/it) | 约240秒 (9.6s/it) | 约320秒 (12.7s/it) | 约750秒 (29.8s/it) | ❌ | ❌ |
| A100 80GB | 约45秒 (1.75s/it) | 约90秒 (3.7s/it) | 约120秒 (4.7s/it) | 约300秒 (11.4s/it) | 约265秒 (10.6s/it) | 约710秒 (28.3s/it) |
b. 权重放置
我们最好将 权重 按照指定路径进行放置：
EasyAnimateV5.1:
📦 models/
├── 📂 Diffusion_Transformer/
│ ├── 📂 EasyAnimateV5.1-12b-zh-InP/
│ ├── 📂 EasyAnimateV5.1-12b-zh-Control/
│ ├── 📂 EasyAnimateV5.1-12b-zh-Control-Camera/
│ └── 📂 EasyAnimateV5.1-12b-zh/
├── 📂 Personalized_Model/
│ └── your trained trainformer model / your trained lora model (for UI load)
联系我们
- 扫描下方二维码或搜索群号：77450006752 来加入钉钉群。
-
扫描下方二维码来加入微信群（如果二维码失效，可扫描最右边同学的微信，邀请您入群）
参考文献
- CogVideo: https://github.com/THUDM/CogVideo/
- Flux: https://github.com/black-forest-labs/flux
- magvit: https://github.com/google-research/magvit
- PixArt: https://github.com/PixArt-alpha/PixArt-alpha
- Open-Sora-Plan: https://github.com/PKU-YuanGroup/Open-Sora-Plan
- Open-Sora: https://github.com/hpcaitech/Open-Sora
- Animatediff: https://github.com/guoyww/AnimateDiff
- HunYuan DiT: https://github.com/tencent/HunyuanDiT
- ComfyUI-KJNodes: https://github.com/kijai/ComfyUI-KJNodes
- ComfyUI-EasyAnimateWrapper: https://github.com/kijai/ComfyUI-EasyAnimateWrapper
- ComfyUI-CameraCtrl-Wrapper: https://github.com/chaojie/ComfyUI-CameraCtrl-Wrapper
- CameraCtrl: https://github.com/hehao13/CameraCtrl
- DragAnything: https://github.com/showlab/DragAnything
许可证
本项目采用 Apache License (Version 2.0) .
Runs of alibaba-pai EasyAnimateV5.1-12b-zh-InP-diffusers on huggingface.co
1.8K
Total runs
58
24-hour runs
212
3-day runs
536
7-day runs
-521
30-day runs
More Information About EasyAnimateV5.1-12b-zh-InP-diffusers huggingface.co Model
Url of EasyAnimateV5.1-12b-zh-InP-diffusers
EasyAnimateV5.1-12b-zh-InP-diffusers huggingface.co Url
Provider of EasyAnimateV5.1-12b-zh-InP-diffusers huggingface.co
Other API from alibaba-pai
Updated:February 26 2026
Total runs:
68.8K
Run Growth:
6.8K
Growth Rate:
10.65%
Total runs:
52.6K
Run Growth:
-31.2K
Growth Rate:
-60.01%
Total runs:
49.0K
Run Growth:
42.3K
Growth Rate:
86.48%
Total runs:
44.6K
Run Growth:
42.4K
Growth Rate:
98.05%
Total runs:
37.0K
Run Growth:
37.0K
Growth Rate:
100.00%
Total runs:
21.4K
Run Growth:
21.2K
Growth Rate:
100.00%
Total runs:
20.6K
Run Growth:
-2.7K
Growth Rate:
-13.18%
Total runs:
17.1K
Run Growth:
16.9K
Growth Rate:
98.97%
Total runs:
15.2K
Run Growth:
11.1K
Growth Rate:
72.19%
Total runs:
15.1K
Run Growth:
5.2K
Growth Rate:
34.45%
Total runs:
12.8K
Run Growth:
8.7K
Growth Rate:
68.35%
Total runs:
12.7K
Run Growth:
-797
Growth Rate:
-6.29%
Total runs:
12.4K
Run Growth:
11.4K
Growth Rate:
93.31%
Total runs:
11.7K
Run Growth:
32
Growth Rate:
0.27%
Total runs:
10.7K
Run Growth:
7.8K
Growth Rate:
68.94%
Total runs:
10.5K
Run Growth:
-917
Growth Rate:
-8.74%
Total runs:
7.5K
Run Growth:
353
Growth Rate:
4.68%
Total runs:
7.2K
Run Growth:
7.1K
Growth Rate:
98.12%
Total runs:
5.2K
Run Growth:
315
Growth Rate:
6.06%
Total runs:
4.9K
Run Growth:
3.4K
Growth Rate:
70.23%
Total runs:
4.1K
Run Growth:
-951
Growth Rate:
-23.27%
Total runs:
2.8K
Run Growth:
2.1K
Growth Rate:
74.81%
Total runs:
1.8K
Run Growth:
900
Growth Rate:
50.42%
Total runs:
1.7K
Run Growth:
960
Growth Rate:
55.98%
Total runs:
1.3K
Run Growth:
129
Growth Rate:
10.03%
Total runs:
1.2K
Run Growth:
1.1K
Growth Rate:
91.52%
Total runs:
1.0K
Run Growth:
611
Growth Rate:
59.03%
Total runs:
646
Run Growth:
367
Growth Rate:
56.81%
Total runs:
583
Run Growth:
338
Growth Rate:
57.98%
Total runs:
422
Run Growth:
185
Growth Rate:
45.91%
Total runs:
418
Run Growth:
176
Growth Rate:
42.11%
Total runs:
388
Run Growth:
4
Growth Rate:
1.03%
Total runs:
340
Run Growth:
10
Growth Rate:
2.94%
Total runs:
265
Run Growth:
15
Growth Rate:
5.66%
Total runs:
256
Run Growth:
182
Growth Rate:
71.09%
Total runs:
252
Run Growth:
-391
Growth Rate:
-155.16%
Total runs:
234
Run Growth:
-36
Growth Rate:
-15.38%
Total runs:
211
Run Growth:
126
Growth Rate:
61.46%
Total runs:
198
Run Growth:
139
Growth Rate:
70.20%
Total runs:
193
Run Growth:
111
Growth Rate:
57.51%
Total runs:
185
Run Growth:
-51
Growth Rate:
-27.57%
Total runs:
170
Run Growth:
-32
Growth Rate:
-18.82%
Total runs:
137
Run Growth:
7
Growth Rate:
5.11%
Total runs:
127
Run Growth:
-104
Growth Rate:
-82.54%
Total runs:
125
Run Growth:
-57
Growth Rate:
-45.60%
Total runs:
118
Run Growth:
-108
Growth Rate:
-91.53%
Total runs:
117
Run Growth:
36
Growth Rate:
30.25%
Total runs:
113
Run Growth:
65
Growth Rate:
57.02%
Total runs:
109
Run Growth:
22
Growth Rate:
20.18%
Total runs:
92
Run Growth:
79
Growth Rate:
85.87%
Total runs:
86
Run Growth:
-20
Growth Rate:
-24.10%
Total runs:
77
Run Growth:
-20
Growth Rate:
-25.97%
Total runs:
75
Run Growth:
-52
Growth Rate:
-69.33%
Total runs:
66
Run Growth:
-15
Growth Rate:
-22.73%
Total runs:
58
Run Growth:
20
Growth Rate:
37.04%
Total runs:
56
Run Growth:
15
Growth Rate:
26.79%
Total runs:
55
Run Growth:
28
Growth Rate:
50.91%
Total runs:
50
Run Growth:
0
Growth Rate:
0.00%
Total runs:
48
Run Growth:
2
Growth Rate:
4.65%
Total runs:
45
Run Growth:
25
Growth Rate:
55.56%
Total runs:
36
Run Growth:
32
Growth Rate:
88.89%
Total runs:
30
Run Growth:
6
Growth Rate:
21.43%
Total runs:
29
Run Growth:
-71
Growth Rate:
-244.83%
Total runs:
26
Run Growth:
2
Growth Rate:
7.69%
Total runs:
25
Run Growth:
-14
Growth Rate:
-56.00%
Total runs:
24
Run Growth:
11
Growth Rate:
45.83%
Total runs:
21
Run Growth:
10
Growth Rate:
47.62%
Total runs:
21
Run Growth:
12
Growth Rate:
57.14%
Total runs:
21
Run Growth:
2
Growth Rate:
10.00%
Total runs:
19
Run Growth:
3
Growth Rate:
15.79%
Total runs:
17
Run Growth:
-1
Growth Rate:
-5.88%
Total runs:
17
Run Growth:
-3
Growth Rate:
-17.65%
Total runs:
17
Run Growth:
5
Growth Rate:
29.41%
Total runs:
16
Run Growth:
-2
Growth Rate:
-13.33%
Total runs:
16
Run Growth:
-11
Growth Rate:
-68.75%
Total runs:
16
Run Growth:
-2
Growth Rate:
-12.50%
Total runs:
15
Run Growth:
1
Growth Rate:
6.67%
Total runs:
15
Run Growth:
11
Growth Rate:
73.33%
Total runs:
15
Run Growth:
-5
Growth Rate:
-33.33%
Total runs:
15
Run Growth:
3
Growth Rate:
20.00%
Total runs:
15
Run Growth:
1
Growth Rate:
6.67%
Total runs:
14
Run Growth:
6
Growth Rate:
42.86%
Total runs:
14
Run Growth:
7
Growth Rate:
50.00%
Total runs:
14
Run Growth:
6
Growth Rate:
42.86%
Total runs:
13
Run Growth:
4
Growth Rate:
30.77%
Total runs:
13
Run Growth:
7
Growth Rate:
53.85%
Total runs:
12
Run Growth:
1
Growth Rate:
8.33%
Total runs:
12
Run Growth:
1
Growth Rate:
8.33%
Total runs:
12
Run Growth:
-1
Growth Rate:
-8.33%
Total runs:
12
Run Growth:
1
Growth Rate:
8.33%
Total runs:
12
Run Growth:
2
Growth Rate:
16.67%
Total runs:
11
Run Growth:
4
Growth Rate:
36.36%
Total runs:
11
Run Growth:
5
Growth Rate:
45.45%
Total runs:
11
Run Growth:
8
Growth Rate:
72.73%
Total runs:
10
Run Growth:
1
Growth Rate:
10.00%
Total runs:
10
Run Growth:
-1
Growth Rate:
-10.00%
Total runs:
10
Run Growth:
4
Growth Rate:
40.00%
Total runs:
10
Run Growth:
5
Growth Rate:
50.00%
Total runs:
9
Run Growth:
1
Growth Rate:
11.11%