#bot-feedback
1 messages · Page 3 of 1
There isn't a way to add a video file as a reference, it's just going to be 1 image-to-video.
Yup, this is an experiment, meaning it's going to be random if you get the feature or not.
The request failed to generate in these cases. It isn't going to be something wrong with your prompt. You'll have to just try again.
What is this new function?
That's Auto-Modality, basically it'll automatically detect what modality you should be in based off of the prompt. It's an experiment so is also going to be random if you see it or not.
Wow
Currently, if you're in say the Text modality but prompt "generate a picture of a dog", that's going to still keep you in Text even though based on the prompt it's pretty clear you should be in Image modality. Auto-modality will do that automatically.
Yeah it's pretty cool, I'm a big fan.
I think it was something for programming and etc
But it's more powerful Of what I thought
@solar tide you'll want to use /image-to-video in #video-arena-1 . More info can be found in #1397655624103493813
Thank you for the feedback 😊
Lm arena best 💪
Best
hi, is it possible to have more than 5 attempt a day ?
I am trying to generate a video here but cant get my way
evolution session error whyyyyyyyy😭
There is not.
I'd recommend restarting the Discord app and trying again. 
It's an experiment on the site currently, so that means it'll be random if you get the feature or not.
Will just need to retry. Restarting the Discord app may help.
May I have creator access so that I can train an avatar for a project?
Can I generate a test to Video?
can i generate video?
If you check out #1397655624103493813 you can find information in there @tepid gulch @ember dune
@uneven jackal Hello! Please read the info posted here 👉 https://discord.com/channels/1340554757349179412/1397655624103493813 to learn how to generate videos or images using the bot.
Hi LM Arena team, I’m working on a controlled text‑to‑video pipeline and need access to model‑specific generation (particularly Veo‑class models such as Veo 3.1). The public Video Arena channels are useful for comparative evaluation, but the randomized model assignment prevents deterministic generation, which is required for my workflow.
My use case involves generating identity‑stable talking‑head footage for downstream model training (HeyGen). This requires:
• consistent facial identity across multiple generations
• stable lighting and camera parameters
• repeatable outputs from the same model
• the ability to run controlled prompt experiments
The blind‑arena setup makes it impossible to isolate model behaviour or reproduce outputs, so I’m requesting access to the creator/researcher tier or whichever role enables model‑specific channels (e.g., Veo 3.1).
If this is feasible, I’d appreciate the upgrade. I’m happy to provide additional technical details if needed.
Thanks.
Hello
our current plans are to keep Video Arena in Battle only, but it's possible this changes over time. We don't currently have a creator/researcher tier program, but this is something we've put thought into. I'll be sure to share with the team.
Looks like you found it in #january-3rd-contest
Cant create video please fix the problem
@sand dawn Please head to #1397655624103493813 for a detailed guide on how to use the bot
Looks like there is an issue with the video generation. All requests are stuck.
I'm seeing videos be generated, I'm testing out now
My last 2 video genertion requests are still pending for over 30 min and previous one for over an hour. There seems to be an issue.
Generations are going to be a bit slow right now, but should eventually generate.
My video generation request started yesterday at 21:48, and it’s now 17:20—it’s still processing.
can i ask you a question?
is the video generator official in lmarena.ai àn always appear in the website? @cedar silo
My video generation doesn't work anymore, I don't know why.
I only generated 3 times yesterday.
It's not the photo since no photo works none works
lm is down
Everything is working except video generation
Omg LM is broken
no it isn't
LM IS DOWNNN
Hey @tribal pilot @abstract path would recommend you check out this Help Center for advice on what to do if you're running into this error - https://help.lmarena.ai/articles/1645798556-lmarena-how-to-something-went-wrong-with-this-response-error-message
Note that the 2nd half of the article explains how to best get us more inforamtion so we can get a better idea of what is happening. Also would ask that if you run into this problem to post in #1417174113092374689 . This thread is for feedback on the Discord bot.
You may sometimes see the error message: “Something went wrong with this response, please try again.”This is a general error message. It can
As of yesterday, this feature has fully launched to all users, so you should see on the site right now. https://lmarena.ai/?chat-modality=video
only chatgpt is fixed, Opus Claude still not working
Then I'd encourage you to follow the steps in the 2nd half of that help center article.
Can you create a bug post in #1343291835845578853 and provide more info on what is going on?
no it isn't a bug i just cleared a cache ...
And that fixed the issue?
But it's not a error with my device, it's the website itself, since everything is working perfectly.
The reason why we ask for users to submit more information is so we can get a better understanding of what is causing this error. Think of the Something went wrong error as a car's check engine light. It's the generic error message that can be flagged for different reasons.
I need Frame1 to frame2 option. When it will work on Arena?
why do i allways get this message??
Can you try this help center: https://help.lmarena.ai/articles/1645798556-lmarena-how-to-something-went-wrong-with-this-response-error-message ?
You may sometimes see the error message: “Something went wrong with this response, please try again.”This is a general error message. It can
You're only able to upload 1 image into Video Arena
ok, thank you very much
It could be a future idea if you want to add
@chilly solar Where is the model gemini-3-pro-image-preview-2k(nano-banana-pro) in direct chat or side by side?
The sad truth is that I don't think the server can stand the same here on Discord, it keeps giving an error, but it was working just now.
The site probably crashes due to the amount of people trying...
they removed it because of too many errors
YAYYY CLAUDE OPUS 4.5 GOT FIXED
thanks
oh i found it on the beta website
can you share for me?
does the video generator on lmarena.ai website has a limit?
@white swallow