OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
AI Developer Tools & SDKs

Tongflow

Tongflow is an open-source web application for assembling workflows that transform and combine text, images, audio, video and 3D materials. Users choose a model for each step and can feed its output into later steps on the canvas.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Tongflow — OpenViST project profile in AI Developer Tools & SDKs.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Tongflow when a creative task involves multiple connected generation or transformation steps and outputs need to become inputs for later stages.

Who it is for

  • Creators building workflows that combine multiple media types.
  • Developers and technical users who want to configure plugins and model credentials.
  • Teams or individuals looking for a self-hostable visual workflow canvas.

Documented uses

  • Connect text, image, audio, video and 3D transformations in one workflow.
  • Choose a model for each workflow step.
  • Reuse generated results as inputs to subsequent steps.
  • Build media sequences such as a script, speech and character image leading to a talking-head video.
Before you choose

Requirements & limits

The README describes a browser-based cloud studio, a desktop shell around it and self-hosting options. The repository specifies the AGPL-3.0 license.

  • The self-hosted application starts without plugins, so users must install the needed ones.
  • Each plugin may require its own credentials, configured in Settings.
  • The README describes the cloud studio and desktop app as sign-in based.
  • The project is an application with a visual canvas; its documented workflow setup depends on plugins rather than a built-in fixed provider.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Configure and run the self-hosted example workflow

Install the plugins and credentials needed to run the preloaded text-to-image-to-video example.

Before you start

  • A running self-hosted Tongflow instance.
  • Credentials for the selected plugins.
  • For the documented example plugins, a Modal account and token.

Steps

  1. Open the plugin manager and install tongflow-modal-z-image, tongflow-modal-qwen-image-edit and tongflow-modal-minimax-h3.

  2. In Settings, add the Modal token values MODAL_TOKEN_ID and MODAL_TOKEN_SECRET.

  3. Add any other environment variables required by the installed plugins, such as OPENAI_API_KEY if using the API plugins.

  4. Run the preloaded example node by node, or switch to Execute Mode and run the whole workflow.

Expected outcome

The preloaded workflow can be run through text-to-image, image fusion and image-to-video stages.

Guide limitations

  • A self-hosted installation has no plugins installed by default.
  • Each plugin’s README specifies the credentials it requires.
  • Modal GPU compute may incur charges; the README states that Modal offers up to $30/month of free GPU compute.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
14 October 2026
Original website title
tong-io/tongflow · Official homepage title · retained in its source language
How we review sourcesSuggest a correction