LTX MSR Multi-Reference Workflow
Workflow Introduction This workflow is based on the LTX video model and the MSR Multi-Reference LoRA. It allows users to directly input character reference images and scene referen...
LTX 2.3 Depth-Guided Video-to-Video Workflow
Workflow Overview This workflow uses an input motion video to guide the first-frame reference image, allowing the generated video to reproduce the same character movements and came...
Klein Image Generation & Editing Workflows
This workflow is based on the Flux2 Klein model. Currently, two workflows are available: Klein Single Image Editing WorkflowThis workflow allows you to edit one input image. Klein ...
REmix3 video generation workflow
Workflow Introduction This workflow is based on the Remix v3.0 model version. It supports local AI video generation, including image-to-video and first-and-last-frame video generat...
Krea2 Image Generation Workflow
Workflow Introduction Krea2 is a high-quality image generation model developed by Krea. It is especially good at creating visually appealing, design-oriented images with rich detai...
Scail Motion Transfer Workflow
Workflow Introduction SCAIL-2 is an open-source model for end-to-end controlled character animation. It uses a driving video to animate a reference character, while also supporting...
Start and End Frames LTX2.3 workflow
Workflow IntroductionBased on the LTX2.3 model, this workflow can generate videos from two or three input images. Model SetupThe model configuration is the same as the other LTX wo...
Camera Multi Angle control Workflow
Workflow Introduction This workflow is based on the Qwen Image Edit 2511 model and the qwen-image-edit-2511-multiple-angles-lora. It can generate new camera angles from an input im...
Bernini Video Edit Workflow
Workflow Introduction Based on ByteDance's open-source Bernini video model, this workflow package provides multiple video workflows, including video editing, image reference, video...
LTX2.3 Single-Person Audio-Driven Workflow
Workflow IntroductionThis workflow is based on the LTX2.3 large model. It can generate videos from an input image and audio, allowing the character in the video to speak according ...
