I Tried Midjourney 8… Here’s the Truth
Evaluating newly released major model versions helps working filmmakers determine whether to update their prompt workflows or stick with reliable legacy models.
What this lesson covers
This video provides a first look at Midjourney v8 in alpha preview, comparing its image generation capabilities against Nano Banana Pro. It also touches on new updates from Freepik and Adobe regarding custom models and lip-syncing.
Key takeaways from the creator
AI-extracted notes, not independently verified product claims. Timestamp links let you check each point in the original video.
- 0:32 ↗
Midjourney v8 introduces faster generation speeds, native 2K resolution via an HD mode, and improved style reference handling.
- 1:53 ↗
Midjourney v8 is currently in alpha preview, meaning access may be restricted depending on your subscription tier.
- 3:37 ↗
Midjourney v8 introduces new command tags like dash-dash HD for 2K resolution rendering.
- 6:30 ↗
Style reference features in Midjourney v8 cannot be combined simultaneously with HD mode or quality four mode.
- 8:05 ↗
Nano Banana Pro often produces more compositionally accurate results when paired with specific style references compared to early tests of Midjourney v8.
Workflow outlined in the video
- Check your account access by navigating to alpha.midjourney.com to see if v8 is available.
- Set up your prompt and use the settings panel on the right side of the interface to manage generation parameters.
- Upload reference images or mood boards into the platform to maintain visual consistency across generations.
- Compare outputs between Midjourney v8 and alternative models like Nano Banana Pro when testing new prompts.
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
19,263 views captured 22 October 2026. ReelStack recommendation score: 43/100. Formula: radar-v5. This is ReelStack’s calculation, not a YouTube rating or a measure of factual accuracy.
Show the calculation
- 45% performance: 0.87× views vs 12 other channel videos observed at a similar age. View-evidence factor 95% (views / (views + 1,000))
- 25% freshness: 0/100 with a 14-day half-life
- 20% momentum: 15 views/day vs 3 channel baseline (6 comparable uploads), with the same view-evidence factor
- 10% engagement: 80/100; likes + 4× comments, smoothed with a 500-view neutral prior