My stuff

  • My Workflows

  • Liked Workflows

  • Following Workflows

Go to OpenArt main site
Upload workflow

VACE 14B-Image video (with automatic word prompts)

5.0

0 reviews
1
1.6K
366
1
Description

🚀Edit& Run it online (RunningHub):

https://www.runninghub.cn/post/1922977171818598402/aiDetail/?utm_source=openar

RunningHub – Highly Reliable Cloud-Based ComfyUI, Edit and Run Workflows Online, no local installation required. Powered by RTX 4090 GPUs for faster performance and fully error-free node operation.

----------------------------------------------------------

🚀 在线编辑运行(RunningHub):

https://www.runninghub.cn/ai-detail/1923002381888311297/?utm_source=openar

【RunningHub - 超高可用性云端ComfyUI,在线编辑运行工作流,标配RTX4090带来更快运行速度,节点全不报红】

----------------------------------------------------------

Workflow Description

Title: VACE 14B-Image-generated video (with automatic word prompts)

Step 1: Upload 1 image,

Step 2: Enter the video ratio [0 or 1, the number "0" represents the size ratio of the uploaded image, and the number "1" represents the manually set size ratio]

Select the number 1 to manually set the video ratio. Common ratios are

- 1:1: Square screen, suitable for social media, highlighting the subject, and conducive to mobile browsing and sharing.

- 3:4: Vertical rectangle, often used for portrait shooting and vertical video, highlighting vertical content.

- 4:3: Horizontal rectangle, suitable for early TV, surveillance video and old movies, etc., can create a retro feel.

- 16:9: Super long horizontal rectangle, which is the mainstream of TV, film and television and online videos, with a wide field of view and strong compatibility.

- 9:16: Super long vertical rectangle, which fits the vertical screen mode of short video platforms such as Douyin, focusing on the subject of the character.

Step 3: Set the number of video frames. The default is 81 frames (5 seconds). The calculation method is 16 multiples + 1, so 4 seconds 65 frames, 5 seconds 81 frames, 6 seconds 97 frames, and so on.

Step 4: Enter the text method [1 Automatic 2 Handwriting]. Select Manual to enter the prompt word in the box below.

After setting, click Run. The default parameters are expected to generate a video in about 15 minutes. If it has not been generated for more than 30 minutes, it is recommended to cancel the task and re-adjust the parameters before running.

----------------------------------------------------------

工作流内容介绍


标题:VACE 14B-图生视频(可自动提示词)

步骤一、上传1张图像,

步骤二、输入视频比例方式【0或1,数字“0”代表上传图像的尺寸比例,数字“1”代表手动设置的尺寸比例】

选择数字1,手动设置视频比例,常见比例有

- 1:1:正方形画面,适配社交媒体,突出主体,利于手机端浏览分享。- 3:4:竖版长方形,常用于人像拍摄与竖版视频,凸显垂直内容。- 4:3:横版长方形,适用于早期电视、监控视频和老电影等,可营造复古感。- 16:9:超长横版长方形,是电视、影视及网络视频主流,视野开阔,兼容性强。- 9:16:超长竖版长方形,契合抖音等短视频平台竖屏模式,聚焦人物主体。

步骤三、设置视频帧数,现默认是(5秒)81帧,计算方式是16的倍数+1,所以4秒65帧 5秒81帧  6秒97帧 以此类推

步骤四、输入文本方式【1自动 2手写】,选择手动可在下方框内输入提示词

设置完成后点击运行,默认参数预计15分钟左右可生成视频,如果超过30分钟还没生成,建议取消任务,重新调整参数后运行。

----------------------------------------------------------

RunningHub:Join Us to Claim Free Perks

Discussion

(No comments yet)

Loading...

Author

66
15.4K
182
63.3K

No reviews yet

  • - latest (4 months ago)

Primitive Nodes (21)

FluxResolutionNode (1)

ImageConcatMulti (1)

JWInteger (1)

LoadWanVideoT5TextEncoder (1)

RH_Captioner (1)

RH_Prompter (1)

Reroute (1)

WanVideoBlockSwap (1)

WanVideoDecode (1)

WanVideoEnhanceAVideo (1)

WanVideoExperimentalArgs (1)

WanVideoModelLoader (1)

WanVideoSLG (1)

WanVideoSampler (1)

WanVideoTeaCache (1)

WanVideoTextEncode (1)

WanVideoVACEEncode (1)

WanVideoVACEModelSelect (1)

WanVideoVAELoader (1)

easy anythingIndexSwitch (2)

Custom Nodes (21)

ComfyUI

  • - LoadImage (1)

ComfyUI Easy Use

  • - easy showAnything (2)

  • - easy textSwitch (1)

  • - ImageResize+ (2)

  • - TextCombinerTwo (2)

  • - JjkText (3)

  • - Int (2)

  • - VHS_VideoCombine (2)

  • - ColorMatch (1)

  • - MathExpression|pysssss (4)

Checkpoints (0)

LoRAs (0)