New BEST local AI image generator is here!
Evaluating new open-source image models like Ernie Image helps filmmakers understand local generation alternatives for complex visual assets and text rendering.
What this lesson covers
This video reviews the Ernie Image open-source generator and demonstrates its installation and usage in ComfyUI. The creator compares Ernie Image head-to-head with Z Image across various complex prompts, text rendering, and art styles.
Key takeaways from the creator
AI-extracted notes, not independently verified product claims. Timestamp links let you check each point in the original video.
- 0:00 ↗
Ernie Image is a new open-source image generator noted for strong text rendering and prompt adherence.
- 1:02 ↗
Ernie Image handles complex realism and detailed natural scenes effectively without standard plasticky AI artifacts.
- 4:20 ↗
Ernie Image displays advanced text rendering capabilities inside generated images compared to previous open-source models.
- 15:08 ↗
The tutorial demonstrates how to install and run Ernie Image locally inside ComfyUI.
Workflow outlined in the video
- Download the Ernie Image model files from Hugging Face.
- Set up the required workflow nodes inside ComfyUI.
- Input detailed prompts incorporating text elements to test rendering accuracy.
Before you use this workflow
These notes describe the source video at its publication date. Model access, pricing, connectors and interfaces may have changed. Check the original source and the provider’s current documentation before installing an add-on, connecting an account or spending credits.
ReelStack has not independently tested this workflow. Preview one representative shot and check motion, continuity and output quality before applying it to a full production. No result, cost saving or model capability is guaranteed.
Explore the tools
How to interpret the numbers
178,138 views captured 23 October 2026. ReelStack recommendation score: 51/100. Formula: radar-v5. This is ReelStack’s calculation, not a YouTube rating or a measure of factual accuracy.
Show the calculation
- 45% performance: 1.49× views vs 12 other channel videos observed at a similar age. View-evidence factor 99% (views / (views + 1,000))
- 25% freshness: 0/100 with a 14-day half-life
- 20% momentum: 91 views/day vs 11 channel baseline (6 comparable uploads), with the same view-evidence factor
- 10% engagement: 69/100; likes + 4× comments, smoothed with a 500-view neutral prior