Appreciate you reaching out to share your experience. Do you have any specific examples I can share with the team?

There's not much detail to go on here. It would be really helpful to see some examples of your prompts and the output you didn't like. Otherwise, we can't be sure what should be changed

Thanks for the response. I understand the need for more context, so here’s a bit more detail.

I’ve built two custom GPTs specifically to work with v0. One is focused on UI design, and the other on development structure. I’ve studied how v0 works and crafted my prompts based on that. These GPTs generate highly tailored instructions meant to get the best out of the system.

Even with all of that, the output has become consistently generic. The sections feel disconnected, the components look like basic UI kits, and there's barely any animation or structure. It's just stacked blocks with placeholder text and colored backgrounds. Even when I reference modern design, strong brands, and ask for high-level creative layout, the results still fall flat.

When I first started using v0, the designs had more depth. There were better font choices, spacing, animations, and a clear sense of structure. Now that feeling is gone. I noticed the shift around the same time the pricing moved from a monthly subscription to the new usage-based token model. I’m not saying it’s directly related, but that’s when the drop became noticeable.

That said, I don’t want to just blame the tool. Maybe there’s something I’m missing. Maybe there’s a new way of structuring prompts or designing workflows that your team knows and we don’t. If you’re part of the team or close to it, I’d really appreciate it if you could share how we can structure the best possible UI outputs using v0 right now. If there's a better method than using custom GPTs, I’m open to learning it.

At the end of the day, we just want to create great results. So if you have insight, we’re listening.

Hi Amy,

rather than relying on examples from users, why not try running prompts yourself and see what the GPT delivers? I've had so many experiences of the GPT failing to follow instructions and I even had it state that it did so because it was being lazy...still took money from my tokens.

I'm sure like my fellow users, I don't really have the time to supply Vercel with specific examples, but I think you can surmise from the numerous forum posts on this that it exists and is a real issue. I've had a month break from V0 and this still has not been resolved.

Kind regards,

Brian

Useful feedback @animerezz-1240! Thank you for sharing that. I'll hand it over to the team to help guide future iterations.

There's some great tips in the community handbook if you want to learn more about prompting strategies. I think the topics on theming, design mode, and strategic forking would be useful for you.

https://community.vercel.com/docs?tags=v0

We also have an upcoming live session with Claire Vo where you can ask questions and learn more.

@brianmrobinson50-733 We use v0 every day at Vercel. Dogfooding is very much part of the culture here.

When we ask for examples, it's because "it's not good" doesn't give us enough detail to know what should be changed. Imagine going to a doctor, telling them "I feel unwell", and expecting them to be able to fix you with no other details. In the absence of actual telepathy, of course, we need to ask for more information.

Remember that every message you send in a chat teaches the AI to respond in a way that it expects you want. If you call it stupid and tell it that it's lazy, then the responses you get will start to match that expectation. The community handbook topics about v0 linked above can help you learn how to get LLMs to give the output you want.

Hope that helps!

Hi Amy,

thanks for the reply, it is much appreciated. I also appreciate what you are saying, but if I was a doctor and I had 100 unconscious patients, I would run all sorts of tests to see if I can identify/triage the root cause of the problem and not rely on accompanying evidence. There is obviously an issue, as I have 100 unconcious patients! In the same way, there are numerous complaints on these forums that payment is taken despite the GPT failing to actually carry out the prompt.

I always follow the advice in the community handbook and work with LLM's at my place of work...I run my prompts via ChatGPT before inputting to V0, yet it often takes a payment but doesn't apply any meaningful changes to the code.

Kind regards,

Brian

Personally I think v0 performed very well just before the transition into .app and the agent approach.

The ability to choose model, and even better, the gpt 5, usually performed well and according to what I wanted. The new implementation creates worse results and takes longer.

I think one potential cause is that the agent aims to do “too much” before confering me. I also used to leverage the heavier models for complex tasks (lg and gpt 5) and I did experience huge differences on those. Now it seems to use md for everything.

Amy, is this just issues “right now” due to not having had the new version fully tested? I miss the version of v0 a few weeks back!

Hi all,

I’m having pretty insane issues with v0 now too where it can’t even complete simple tasks that it used to cut through with ease. Right now, I’m experiencing the model getting stuck in infinite loops where it refuses to make any code changes even after I repeatedly point out that nothing has been written. It then gets mad at itself and infinite loops again telling itself to read the existing code before trying to write new code again.

I tried opening a new chat, changed my prompts, and still it’s getting stuck in a loop. Now it’s a loop of not updating the code and it trying to create a page.tsx.

What happened to v0? It was the best AI model I used a few weeks back and now it’s unusable.

the quality is definitely down. The output provided has nothing to do with the actual implementation.

Some common issues i’ve had is classical stopping of execution. Basically resisting executing really simple commands like (increase font size for a section) which typically it does with no issue.

I’ve also had a few times complete design rehauls when prompting it specifically and clearly not to update anything as i’m just brushing up before production.

I would venture to even boldly claim that the full redesign always happen when asked for only simple updates.

When prompted to explain and show what’s done, it puts together an imaginary list of actions and goes ahead to rewire API calls and mess up the entire connection. This then causes run-time errors which it fixes by removing entire elements in the app. Really wild and highly unpredictable. It’s scary…

Ill tell you the true, its realy gotten worse, I used it before and the new version doing wrong staff,

also the payment is higher, I lost money on same request again and again and got not the right thing I requested.

I dnot know why, or what happened but now its worst that it was.

I completely agree with this. For me it’s not just that the UI quality has dropped — it honestly feels like the whole system is now engineered to burn credits without delivering anything useful.

A few months ago, spending $20–30 a month gave me results that were at least workable. Yesterday I burned through $40 in a single day and got nothing but garbage. Most instructions are ignored, and worse, the ones that are supposed to optimize costs and reduce pointless “work” are blatantly disregarded.

Just today, the model needed 10 iterations to (still unsuccessfully) change button text color to white. $10–12 wasted on a single, trivial task. That’s ridiculous.

And when I tried to request a refund through the official form, the moment you select the invoice the Submit button is conveniently greyed out. Pure coincidence, I guess.

I’m preparing to file a chargeback because I genuinely don’t believe the service is being delivered properly. Honestly, I think more people should consider doing the same. Only real financial pressure will ever push them toward customer-friendly changes.

It’s not you, this is a serious issue now, read my thread: https://community.vercel.com/t/urgent-feedback-on-v0-transition-user-experience/21203

I don't know if they connected it to GPT five but since the day GPT five came out the results has been horrible

V0 doesn’t care about its users anymore, only about its own profit just like every other company.

At the beginning it was cheap to attract customers, but then they showed their real face. What used to cost 0.02 or 0.05 now costs 0.20 as if nothing. The community team always gives the same copy-paste answers and nothing ever changes.

They only added the -sm mode after the whole mess about high prices and limited usage just to calm people down. Now they launch this agent mode that charges whatever it wants, whenever it wants, however it wants.

And the HR response? “We’ll forward it to the team” bla bla bla, just lies. If we can’t even trust the few people who are supposed to listen to us, what’s left? Look for other options because trust is gone.

Before agent mode, $30 gave you more than 100 prompts, now you’re lucky if you even reach 100. The reality is clear: prices keep rising, while users get less and less.

Well, let’s hope they address it before too many users leave.

Very much the case, it used to produce top notch UI. Especially if you asked it to use ShadCN, after Agent was introduced quality went significantly down. Buttons are no aligned, quite strange page architecture, tables that don’t make any sense, coloring that is just awful. Not sure what they’ve done, but it’s not good. Their evals might be good on paper but practically it’s pretty bad.

@amyegan here’s good example pictures attached. I’ve been a paid customer of v0 since April and I remember how I could consistently send v0 Mockup images and v0 would make an exact replica in ShadCN/Tailwind code. Then in June-July I believe this ability to generate a UI that at all resembled the screenshot sent in diminished. Even when I used the expensive large model instead of medium, it failed to make anything similar. Despite the fact that just 2-3 days before, even medium model could reliably clone screenshots.

Takeaway TLDR: You & other vercel employees probably don’t try to clone UI design screenshots much in your daily dogfooding of the product. I think any user who often clones screenshots with v0 will attest the quality randomly decreased dramatically one morning around the time of June-July. And these screenshotted sites are often using ShadCN and Tailwind & v0 still fails to generate a design at all similar in style to the pictures.

My pictures are attached below. This is an expensive UI and it’s value to me was that it could previously design better than other AIs. if the model doesn’t get smoothed out soon I’m going to cancel my subscription.

The reference screenshot provided to v0

The 1st output (I did one more attempt after this)

The 2nd output

This is disappointing, the pictures look nothing like the reference picture and the steps 1-2-3-4 in the 2nd output are aligned to the right end of the page, when in my reference picture it’s super clear it’s in the middle of the page.

The prompts I’ve been feeding v0 are no less descriptive than before when v0 worked. In fact, I clicked v0’s button to clone a screenshot and it still looks this disappointing. I try explicitly mentioning Tailwind CSS because that’s what the reference site uses, no luck there either.

I’m getting better results when I use other AI companies that don’t advertise themselves as design AIs. This quality change was instant overnight and I expected it was probably just a tuning update Vercel would soon revert or train to be corrected. Yet we’re now more than 2 months later and the quality is just as poor as that day the model worsened.

@swarnava Is this true? source is GPT 4.1

Looks like it got the general vibe right. Enough to use as a starting point for your own work.

Why do you need to make an exact copy of someone else's site?

In my case it’s my own design, for me at least, as I’m using adobe XD and not Figma There is also the possibility that we might need to migrate a website from a stack to another etc. Anyway, it seems that your response is slightly off. v0 has a clear difference in understanding and the result has nothing to do with the need of copying or not someone else’s website.

Just today I’ve spent almost $20 in trying to build a simple onepager with at least half of this going in v0 repairing it’s own mistakes… In the end I have nothing great. This is something I usually solved within 4-6 hours in the past.

Even so all the feedback that comes from long standing users seems to be ignored or treated disrespectful, most of the time. Like you did just now, with someone showing how the results differ and your response being “well it worked for me” like a typical development clichée. Not great customer support.

Trying to have a conversation to collect practical info to show the team how people are trying to use the product. I asked a question to understand the use case to figure out if I knew an alternative solution.

It's really helpful when people share chat IDs or screenshots so I can flag them for further review. For example, the screenshots above were already shared with the team. Additional context (like what you shared about Adobe XD) helps give a better perspective on what "it doesn't work for me" actually means.

Hope that makes sense!

It really didn’t get it right at all, there’s a black-to-grey background divide, the active step numbers are not pink when highlighted in the original picture, and I could go on about 10 other problems. I’ve submitted follow-up messages to v0 and it still doesn’t tackle it when directly queried.

You claim your replies are just to get an understanding, however many of your replies in this thread appear as bad-faith minimizations of the problem. How is it any of your business the reasons I need to clone a UI? This is extremely unprofessional and discounting customer’s needs that pay you $20/mo.

Simple question you never answered: Were v0’s capabilities on cloning screenshots changed 2+ months ago?

Also you never gave confirmation to me or others our chats would be reviewed and improved on. So the communication is really lacking and isn’t demonstrating to us any meaningful progress is happening

Fair use allows extremely similar visual appearances as long as the code to get to that point was different. We’re incorporating our own components into the UI and it’s going to make a distinctive product in the end.

You would think Vercel with it’s large legal budget would know this simple rule of law.

Oh and I’d like to note, these pictures were not made with v0. v0 in it’s current state is inadequate and could never make something that looks like this. v0’s pictures all blend in, lacking unique characteristics or originality. every v0 generation looks like the same bland, emotionless page.

Good of you to openly share your screenshots so I could show the team what didn't work like you expected. Please keep in mind our code of conduct in future posts.

In this thread, I've been trying to collect usable info for the v0 team and offer suggestions that might help people right away. Any more specific examples are welcome and appreciated.

Were v0’s capabilities on cloning screenshots changed 2+ months ago?

Please comment on this, and did v0 add copyright restrictions relatively recent?

I’m not aware of any new design or copyright restrictions being added to the app

It’s been absolutely getting worse. In fact I would describe it as dog ****. It went from the place where I would go to in order to get a good first draft for a layout, to a place where I come to get perpetually disappointed. And it seems like Lovable is in a similar spot (though I used that way less) so it’s possible that it’s more related to the underlying model.