ccpt5/comfyui-berninistudio

★ 23JavaScriptAudience · vibe coderComplexity · 3/5Setup · moderate

Mindmap

mindmap
  root((comfyui-berninistudio))
    What it does
      Single node for Bernini
      Simplified workflow
      Auto prompt generation
    Editing modes
      Video to video
      Reference image guided
      Text to video
      Image animation
    How it works
      ComfyUI plugin
      Ollama integration
      Vision model prompts
    Requirements
      ComfyUI with Bernini
      Bernini model weights
      Ollama for auto prompts

mindmap root((comfyui-berninistudio)) What it does Single node for Bernini Simplified workflow Auto prompt generation Editing modes Video to video Reference image guided Text to video Image animation How it works ComfyUI plugin Ollama integration Vision model prompts Requirements ComfyUI with Bernini Bernini model weights Ollama for auto prompts

Click or tap to explore — scroll the page freely

Things people build with this

USE CASE 1

Edit an existing video using text instructions inside ComfyUI without manually wiring together multiple nodes.

USE CASE 2

Generate a new video from a text description using the Bernini model through a simple single-node interface.

USE CASE 3

Automatically generate accurate video editing prompts by feeding reference images to a local Ollama vision model.

USE CASE 4

Animate a still image into a short video using the Bernini model's image animation mode.

Tech stack

JavaScriptComfyUIOllama

Getting it running

Difficulty · moderate Time to first run · 1h+

Requires a specific version of ComfyUI that supports Bernini, plus the Bernini model weights downloaded separately. Ollama is optional but needed for auto prompt generation.

In plain English

ComfyUI is a visual tool for building AI image and video generation workflows by connecting nodes together, similar to wiring up a flowchart. This repository is an add-on for ComfyUI that simplifies working with Bernini, a video editing model released by ByteDance. Bernini can take an existing video and modify it based on text instructions, replace objects in a scene with reference images, generate entirely new videos from text descriptions, or animate a still image. Normally, using Bernini inside ComfyUI requires wiring together five or more separate nodes to handle all the text encoding, video encoding, and image preparation steps. This plugin collapses all of that into a single node, reducing setup time and visual clutter in the workflow. The plugin also includes a prompt enhancement panel powered by Ollama, which is a tool for running AI language models on your own computer. When you connect reference images, the panel can send those images to a locally running vision model to generate accurate descriptions, which are then folded into your video editing prompt automatically. This helps produce more consistent results when you want the edited video to match a specific person, object, or visual style. The project supports several editing modes including video-to-video editing, reference-image-guided editing, text-to-video generation, and single-frame image editing. Each mode corresponds to how the Bernini model was trained to accept input. The author describes this as a personal tool built with AI assistance and shared without any support or maintenance commitment. It requires a specific version of ComfyUI that includes Bernini model support, along with the Bernini model weights downloaded separately.

Copy-paste prompts

Prompt 1

Set up the ComfyUI BerniniStudio node to edit my video by replacing the main subject with a reference image I provide.

Prompt 2

Use ComfyUI BerniniStudio to generate a new video from this text description: [describe the video you want].

Prompt 3

Configure Ollama with a vision model in ComfyUI BerniniStudio to auto-generate editing prompts from my reference photos.

Prompt 4

Animate this still image into a short video using the BerniniStudio single-frame editing mode in ComfyUI.

Open on GitHub → Explain another repo

← ccpt5 on gitmyhub — every repo by this author, as a profile.

Verify against the repo before relying on details.