Sd-Webui-Text2video

Visit Tool

sd-webui-text2video is a Content & Design tool that implements text-to-video diffusion models within AUTOMATIC1111's Stable Diffusion WebUI. It supports models like ModelScope and VideoCrafter, allowing users to generate video content from text prompts.

Claim this tool

1View

At a glance

Pricing

Open Source

Free tier

Yes

API

Yes

Skill level

Technical

About

What is sd-webui-text2video?

sd-webui-text2video is an extension for AUTOMATIC1111's Stable Diffusion WebUI, designed to implement various text-to-video diffusion models such as ModelScope and VideoCrafter. This tool leverages only Auto1111 webui dependencies and downloadable models, eliminating the need for external logins. It enables users to generate videos from textual descriptions, supporting features like prompt weights, in-framing/in-painting for existing images, and seamless video looping. The extension also offers Torch2/xformers optimizations for efficient VRAM usage, allowing for longer video generations. Users can also fine-tune models and utilize LoRA support for customized video outputs. It provides a flexible and powerful solution for creating dynamic visual content directly within the Stable Diffusion environment.

Best used for

Ideal for content creators who need to generate short videos from text prompts, animate existing images, and create seamless video loops. Especially valuable for those working within the AUTOMATIC1111 Stable Diffusion WebUI environment and seeking to leverage advanced text-to-video diffusion models.

Common actions

generate videos from text

animate images

create video loops

fine-tune video models

github copilotface swappingcollaborationworkflowsautomated workflowlow-code/no-codeopen-source"AI Agents"deepfake

Capabilities

Key features

Text-to-video generation
ModelScope integration
VideoCrafter integration
Prompt weights
In-framing/in-painting
Video looping
LoRA support

Target Audience

content creator

Integrations

Not yet documented

Pricing & Plans

Open Source

Free

FAQs

What are the VRAM requirements for sd-webui-text2video?

ModelScope can run on as little as 4GBs of VRAM for 192x192 videos, with 6GBs recommended for 256x256. For longer videos (125 frames), 12GBs of VRAM is sufficient with Torch2 optimizations, while 250 frames may require 20GBs. VideoCrafter typically needs around 9.2GBs of VRAM.

Can I use fine-tuned models with sd-webui-text2video?

Yes, the extension supports trained LoRAs and fine-tuned models. You can follow instructions from the Text-To-Video-Finetuning repository to train them, then convert Diffusers-formatted models into the original weights format for use within the extension.

Does sd-webui-text2video support in-painting and looping videos?

Yes, the extension includes support for in-framing and in-painting, allowing you to animate existing pictures. It also enables seamless looping of videos, providing more creative control over your generated content.

Trending

Subcategories trending in Content & Design

Image Generation AI Writing Assistants Audio & Music Video Generation Photo Editing Graphic Design

Trending

Explore

Browse AI tools by category

Content & Design Productivity & Business Coding & Development AI Agents & Automation Research & Education Wellness & Lifestyle Career Development Marketing & Growth Data & Analytics Customer Support & CX Finance E-commerce