comfyui_video_pipeline

Name: comfyui_video_pipeline
Availability: InStock
Author: yellowhama

Translate storyboards into T2I and I2V prompts with a JSON manifest for ComfyUI batch rendering.

Updated Feb 27, 2026

Search Tags:#prompt engineering #video generation #storyboard #text-to-image #comfyui #image-to-video

Ready to run

npx skills add https://github.com/yellowhama/vibecode-blog --skill comfyui-video-pipeline

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: comfyui_video_pipeline
Source: https://github.com/yellowhama/vibecode-blog/tree/main/.agents/skills/comfyui_video_pipeline
Command: npx skills add https://github.com/yellowhama/vibecode-blog --skill comfyui-video-pipeline

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill streamlines the creation of complex AI video prompts for ComfyUI, ensuring visual consistency and motion stability across generated clips.

Core Features & Use Cases

Storyboard to Prompt Translation: Converts storyboard descriptions into precise Text-to-Image (T2I) and Image-to-Video (I2V) prompts.
ComfyUI Workflow Integration: Outputs a JSON manifest directly usable with the comfy_batch_render.py script.
Visual Consistency Enforcement: Implements base style templates and character locking mechanisms (IP-Adapter/FaceID) for uniform visuals.
Anti-Hallucination Guardrails: Includes mandatory negative prompts to prevent text and speech generation in videos.

Quick Start

Use the comfyui_video_pipeline skill to translate the provided storyboard into a JSON manifest for the ComfyUI batch renderer.

Frequently Asked Questions about comfyui_video_pipeline

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I translate a storyboard into ComfyUI video prompts?▼

Translating a storyboard into ComfyUI video prompts involves converting scene descriptions into precise Text-to-Image and Image-to-Video prompts, outputting a JSON manifest for automated batch rendering while enforcing visual consistency.

How does character locking work for consistent AI video generation in ComfyUI?▼

Character locking for consistent AI video generation in ComfyUI uses style templates and IP-Adapter or FaceID mechanisms. This enforces uniform character visuals across multiple generated clips within a batch rendering workflow.

How do I prevent text and speech hallucinations in text-to-video generation?▼

Preventing text and speech hallucinations in text-to-video generation requires mandatory negative prompts as anti-hallucination guardrails. This restricts the model from generating unwanted non-verbal outputs or text artifacts.

Can I automate batch rendering of text-to-image and image-to-video workflows in ComfyUI?▼

Automating batch rendering of text-to-image and image-to-video workflows in ComfyUI is possible by generating a JSON manifest. This output integrates directly with the comfy_batch_render.py script for automated processing.

What do I need to generate a JSON manifest for ComfyUI batch rendering?▼

Generating a JSON manifest for ComfyUI batch rendering requires a storyboard description as input. The pipeline translates this into structured Text-to-Image and Image-to-Video prompts with enforced style templates.

Why do my AI generated video clips lack visual consistency across different scenes?▼

AI generated video clips lack visual consistency across scenes without base style templates and character locking. Applying these mechanisms enforces uniform visuals and motion stability throughout the generated sequence.