工作流名称：视频动作迁移controlnext_svd_diffusers【工作流介绍】首先上传一张图像，接着再上传一段跳舞视频。而后借助 ControlNeXt 节点进行操作，使跳舞视频中的人替换为您上次上传图像中的人。需要注意的是，您上传的人像分辨率最好事先调整好，以 64 的倍数为最佳。Image Concatenate Multi 可以实现视频拼接。现在内置参数已经设置完成，只需点击运行，便可实现这个操作。赶快前来尝试一番吧！【使用场景】例如，若您上传了一张明星的照片和一段精彩的舞蹈视频，经过...

Workflow name: Remove fixed watermark from video【Workflow Introduction】First, upload a video. Next, change the frame number of the video to 1 to generate a single frame image of the video. Then, send the image to the workflow. After that, modify the fra...

 Enter the fascinating world of video face-swapping! Just upload an exciting video and a close-up photo of a face, with the built-in parameters carefully set. Click run to achieve stunning face-swapping effects with a single click, bringing your cr...

Video background replacement is a technology that allows you to replace the background of a video. Simply upload a video and use AI masking technology to remove the background. Next, upload a background image and use SVD (Singular Value Decomposition) t

Upload a short video to remove the background with one click.

Workflow name: CogVideo-I2V LORA camera[Workflow introduction]This workflow can convert an image into a rotating video effect. Open this workflow, first upload an image you like, then scale the image proportionally, fill it with a background color, and ...

Workflow name: CogVideo LORA camera girl[Workflow introduction]This workflow can convert an image into a rotating video effect. Open this workflow, upload 1 image, generate prompt words by inferring the image, then use the flux model to make a text map,...

工作流名称：CogVideo LORA运镜女孩【工作流介绍】这个工作流可以将一张图像转换成旋转的视频效果。打开这个工作流，上传1张图像，通过反推图像生成提示词，然后使用flux模型进行文生图，最后使用CogVideo生成运镜展示效果。我们已经设置好内置参数，快来尝试吧！【使用场景】只需上传一张图像，即可一键生成图像中主体3D旋转的运镜效果，方便快捷实用，快来发挥你的创造力吧！【关键节点】CogVideo【模型版本】SDXL模型名称:sd3/t5xxl fp8 e4m3fn.safetensors【Lo...

工作流名称：CogVideo-I2V LORA运镜【工作流介绍】这个工作流可以将一张图像转换成旋转的视频效果。打开这个工作流，首先上传1张您喜欢的图像，然后先将图像进行等比缩放，再填充一个背景色，然后通过BiRefNet将背景移除填充黑色背景。最后使用CogVideo生成运镜展示效果。我们已经设置好内置参数，快来尝试吧！【使用场景】只需上传一张图像，即可一键生成图像中主体3D旋转的运镜效果，方便快捷实用，快来发挥你的创造力吧！【关键节点】CogVideo【模型版本】SDXL模型名称:sd3/t5xxl...

Upload a photo (portrait orientation supported). 1. Image retouching. 2. Generate short videos. 

输入一张照片，支持竖屏1，洗图2，生成短视频https://huggingface.co/THUDM/CogVideoX1.5-5B-I2V

CogVideoX-I2V 竖屏模式-图生视频

Initial context windowing with FreeNoise noise shuffling mainly for vid2vid and pose2vid pipelines for longer generations, haven't figured it out for img2vid yetGGUF models and tiled encoding for I2V and pose pipelines (thanks to MinusZoneAI)sageattenti...

CogVideoX-5B 从视频生成视频输入一个视频，根据输入的视频参考再生成一个视频效果一般吧

容易爆显存面向轨迹的 DiT 框架，它将文本、视觉和轨迹条件同时集成在一起以生成视频。具体来说，Tora 由轨迹提取器 (TE)、时空 DiT 和运动引导融合器 (MGF) 组成。TE 使用 3D 视频压缩网络将任意轨迹编码为分层时空运动块。MGF 将运动块集成到 DiT 块中以生成遵循轨迹的一致视频。我们的设计与 DiT 的可扩展性无缝契合，允许精确控制具有不同持续时间、宽高比和分辨率的视频内容的动态。大量实验证明，Tora 在实现高运动保真度方面非常出色，同时还能细致模拟物理世界的运动。https...

CogVideo重大更新Refactored the Fun version's sampler to accept any resolution, this should make it lot simpler to use with Tora. BREAKS OLD WORKFLOWS, old FunSampler nodes need to be remade.The old bucket resizing is now on it's own node (CogVideoXFunResize...

LTXVideo I2V Image to VideoOfficial example workflow

LTXVideo I2V 图生视频官方example workflow

LTXVideo I2V 文生视频

CogVideo major update Refactored the Fun version's sampler to accept any resolution, this should make it a lot simpler to use with Tora. BREAKS OLD WORKFLOWS, old FunSampler nodes need to be remade. The old bucket resizing is now on it's own node (CogVi...

Easy to burst video memoryA trajectory-oriented DiT framework that simultaneously integrates text, vision, and trajectory conditions to generate videos. Specifically, Tora consists of a trajectory extractor (TE), spatiotemporal DiT, and a motion-guided ...

CogVideoX-5B Generate video from videoInput a video and generate another video based on the input video referenceThe effect is average

Initial context windowing with FreeNoise noise shuffling mainly for vid2vid and pose2vid pipelines for longer generations, haven't figured it out for img2vid yetGGUF models and tiled encoding for I2V and pose pipelines (thanks to MinusZoneAI)sageattenti...

CogVideo5B Image VideoUse the strongest reverse Joy Caption + CogVideo 5BIf an error like this occursprompt_embeds and negative_prompt_embedsmust have the same shape when passed directly, but got: prompt _embeds" torch.Size([1, 452, 4096])!negative prom...

CogVideo5B 图生视频利用最强反推Joy Caption + CogVideo 5B如果出现类似这样的错误prompt_embeds and negative_prompt_embedsmust have the same shape when passed directly, but got: prompt _embeds" torch.Size([1, 452, 4096])!negative prompt embeds'toreh size([1, 226,40961)12说明提词 正面...

10.11更新增加加了超分和补帧该流做了一些流程的优化 效果比默认的I2V的流 效果好本流来自@datouhttps://openart.ai/workflows/profile/datou?sort=latesthttps://openart.ai/workflows/datou/cogvideox-i2v/vLKiaWUSWpaxpYNZgWvL

This flow has made some process optimizations and the effect is better than the default I2V flow.This flow comes from@datouhttps://openart.ai/workflows/profile/datou?sort=latesthttps://openart.ai/workflows/datou/cogvideox-i2v/vLKiaWUSWpaxpYNZgWvL

Workflow name: CogVideoX-5B Wensheng Video[Workflow Introduction]Enter positive and negative text prompts, and try to keep the number of words in the text balanced. The built-in parameters have been set, and the text-generated video function is super po...