Try GPT-Image-2, Nana Banana 2 in ONE place | Full AI Design Workflow Test (Not Just Image Gen)

Mervin Praison · Beginner ·🎨 Image & Video AI ·1w ago
Built a Work-Ready Brand Kit in 5 Minutes. Try it yourself (20% off): https://skywork.ai/p/gWho5T Banner posters, product mockups, logos, and infographics — all from a single prompt, with every layer fully editable afterwards. That's Skywork AI Images. You pick GPT Image 2 or Nano Banana (or let it auto-select), describe what you want, and get a multi-layer design you can edit like a real design file — text, fonts, colors, positions, individual elements, all separated. In this video I walk through the full feature set: generating a skateboarding poster, splitting it into editable layers, swapping fonts and colors, adding generated assets from the library, in-painting to recolor specific objects (like changing shoe colors), removing backgrounds, upscaling, erasing unwanted parts, and exporting either as separate layers or a merged file. Then I move into the other formats — a labelled photographic camera infographic, an aluminum soda can product shot, a cold brew coffee logo for the brand Luma, a photosynthesis educational infographic, and finally using an existing image as a reference so it follows your brand guidelines. The interesting part is the layer separation. Most prompt-to-image tools give you a flat PNG. Skywork gives you something closer to a Figma file you can keep iterating on. Thanks to Skywork AI for sponsoring this video. Link to sign up below. 🕒 Chapters 0:00 What Skywork AI Images can do 0:49 Picking GPT Image 2 vs Nano Banana 1:54 Generating a skateboarding poster 2:32 Splitting an image into editable layers 2:58 Asset library — generating elements to add 3:16 In-painting — changing the shoe color 3:50 Removing the background 4:11 Upscale and erase tools 4:36 Exporting layers separately or merged 5:08 Infographic — labelled camera parts 5:24 Product image — aluminum soda can 5:40 Logo design — Luma cold brew 5:56 Educational infographic — photosynthesis 6:05 Using a reference image for brand consistency #SkyworkAI #AIImageGe
Watch on YouTube ↗ (saves to browser)
Sign in to unlock AI tutor explanation · ⚡30

Related AI Lessons

I Thought AI Image Tools Were Broken… Until I Realized My Prompts Had No Structure
Learn how to improve AI-generated images by structuring your prompts, a crucial step for reliable results
Medium · ChatGPT
I built a Stable Diffusion playground in 200 lines and zero API keys. Here's how.
Build a Stable Diffusion playground in under 200 lines of code without needing API keys, and explore AI image generation
Dev.to · Devanshu Biswas
What makes an AI image workflow useful for real commercial output?
Learn how to create a useful AI image workflow for commercial output, focusing on repeatability, versatility, and clarity
Dev.to AI
How to Write Better AI Image Prompts for Midjourney (With Examples That Actually Work)
Learn to write effective AI image prompts for Midjourney with actionable examples and techniques
Medium · ChatGPT

Chapters (14)

What Skywork AI Images can do
0:49 Picking GPT Image 2 vs Nano Banana
1:54 Generating a skateboarding poster
2:32 Splitting an image into editable layers
2:58 Asset library — generating elements to add
3:16 In-painting — changing the shoe color
3:50 Removing the background
4:11 Upscale and erase tools
4:36 Exporting layers separately or merged
5:08 Infographic — labelled camera parts
5:24 Product image — aluminum soda can
5:40 Logo design — Luma cold brew
5:56 Educational infographic — photosynthesis
6:05 Using a reference image for brand consistency
Up next
Introducing Gemini Omni
Google for Developers
Watch →