Launching today

SurgePix
AI visuals. Edit every layer. Agent-callable.
152 followers
AI visuals. Edit every layer. Agent-callable.
152 followers
Most AI image tools stop at one-shot generation. SurgePix keeps going: edit any layer, swap text, repaint a region, and stay on-brand with your brand kit. Or skip the UI — open-source agent skills let Claude Code & Cursor generate and edit visuals for you.







Free Options
Launch Team / Built With

Render: Get up to $100K in startup creditsCloud infrastructure for founders who want to move fast and NOT break things
Promoted

Hey Product Hunt 👋
I'm Yichi, the maker behind SurgePix.
SurgePix puts the whole job in one place — no juggling a dozen tools. Its built-in design agent can even search the live web and design straight from what it finds.
It started with a simple frustration: every AI image tool I tried was great at generating something new, but the moment I wanted to tweak a color, swap a headline, or keep things on-brand across a whole set of visuals, I was stuck starting over.
The latest models — GPT Image 2.5 and friends — are genuinely amazing at generating that first image, or that first slide.
The problem starts after: I'd generate a whole deck in one click, then spend an hour fixing headlines, swapping charts, and getting every slide back on-brand. That redo-from-scratch gap is exactly what SurgePix is built to close — for decks, and for every visual you make.
So we built SurgePix around three ideas:
Edit, don't regenerate: brush over any area to repaint it, split a flat image into editable layers, or pull the text off an image to retype it
Upload your brand assets once, and every output stays on-brand
For developers: SurgePix ships as open-source agent skills, so Claude Code, Cursor, or any AI agent can generate and edit visuals for you — right from your terminal, no browser needed
We're still early and shipping fast. Would love to hear what you think, and what you'd want SurgePix to do next.
👉Try it free: https://surgepix.ai
@eeeeeach Congrats Yichi can I edit parts of an image without regenerating the whole thing?
@shivam_kushwaha16 Thanks, Shivam! Of course, you can use the inpainting image to circle the part you want to refine without even prompting a lot. Try it and tell me what you think!
@eeeeeach thankx Yichi i will try out and see how well it works
@shivam_kushwaha16 Looking forward!
@eeeeeach Nice job, Yichi!
Congrats to the Surge team on launching SurgePix! 🎉 @eeeeeach Yichi !!
As the founder of Surge team, seeing this product evolve to where it is today is genuinely emotional. Seeing it launch on PH today brings back a lot — the late nights, the messy whiteboards, the endless iterations, and the whole team pushing together to make it real. I'm no longer with the team, but I'm truly so proud of the Surge team — going from the v1 to here is a beautiful arc 👏
SurgePix tackles the exact pain I felt when building v1: generating with AI is fun, but editing is painful. Now you can edit every layer, repaint regions, swap text while staying on-brand, and even call agent skills from Claude Code / Cursor to generate visuals — this direction is spot on 🔥
Everyone, go try it and share your feedback !!!
how this edit layer is better than regenerating the images using the comments for specific areas in other LLMs
@harini_mukesh Good question, Harini! In Surgepix canvas, you can select any image or elements and use the Inpainting Image Quick button to draw any area without limitations or a large paragraph prompt. However, the most common function needs to recognize and isolate an item. Did it make sense, or can you try!
How many layers can one generation make??
@tomzoe Thanks, Zoe! Up to 500 layers per canvas and 100 canvases per project.
Editable text is the detail that makes this interesting for decks. A late headline change should be a small edit, with the rest of the slide staying put.
@oleksii_sekundant Thanks, Oleksii! Generating and refining decks is one of our popular use cases among our early-stage users. You can even extract text from your deck and edit it!
Hi everyone! I’m one of the product designers behind SurgePix, and I’m excited to share it with you here on Product Hunt! 👋
As a designer, I’m exploring how AI can fit into my own creative process while helping shape the product. I’d love to see SurgePix take on more complex, multi-step workflows, like creating full slide decks or cohesive image series.
We’ve also added AI editing tools, including an assistant that lets you edit images through natural language—just describe what you’d like to change.
Give it a try! We’d love to hear your thoughts and feedback as we continue building SurgePix.
👋 Hey Product Hunt! I’m HAIZHU, one of the makers behind SurgePix, serving as the Data Analyst.
We’re launching SurgePix today — an AI visual generator with full layer‑based editable canvas. You can let the Designer Agent turn ideas into visuals, modify cut‑outs and layers manually, or call SurgePix programmatically within your agent workflow.
Many AI visual tools lock you into flat final images after generation. We wanted to build something you can keep editing, remixing and publishing‑ready.
Feel free to share your thoughts, pain‑points with AI visual tools, or ask anything data‑related. Really appreciate your feedback!