The first few days of using SeeDream 4 in ComfyUI were trouble-free. But a few days later, ByteDance included a default content pre-filter switch in all APIs. This switch ("Content pre-filter") can be disabled by all users by accessing BytePlus.com in the "Online Inference" section; however, we can't configure the API we use in the ComfyUI node ourselves, and the enabled censorship is too sensitive. Is there any way to return to the initial situation by disabling this switch? Thanks in advance.
Yes, there is a method to override censorship; but it depends on the ComfyUI team. ByteDance has a toggle to disable censorship in the API you use to generate and edit images. But the API that ComfyUI provides with ByteDance can only be configured by the ComfyUI team. The same thing happened with FreePik, and they disabled censorship in less than 48 hours. Let's hope ComfyUI does the same.
I confirm that Freepik also had the same issue due to not disabling censorship in its API; however, they fixed it in less than 48 hours. We hope ComfyUI follows the same steps; it's simply a matter of unchecking the box in the API settings on ByteDance (BytePlus.com).
i, I’m kind of new to ComfyUI and I’m running Seedream 4.0 via API. I want to use the LoRA Power Loader, but I can’t get Seedream 4.0 to run with LoRA in any way. Do you have any idea
Hi! We’d like to produce a large amount of AI-generated videos on ComfyUI and sent you an email asking for more info, but nobody reponded us. Could you please give us the email of your bussiness manager? Thank you in advance.
The first few days of using SeeDream 4 in ComfyUI were trouble-free. But a few days later, ByteDance included a default content pre-filter switch in all APIs. This switch ("Content pre-filter") can be disabled by all users by accessing BytePlus.com in the "Online Inference" section; however, we can't configure the API we use in the ComfyUI node ourselves, and the enabled censorship is too sensitive. Is there any way to return to the initial situation by disabling this switch? Thanks in advance.
Hey we are fixing this now.
News?
It should be fixed!
It seems to work, yes.
We'll test it further.
Thanks!
also waiting for the news...
please let us know when it's fixed. thanks!
it's still not working...
Any update on this? I also tried it, and it's not working for me. Always getting errors.
This should be fixed. Can you try again?
Done , Thank you !
same problem here, is there's any way to disable the censorship on ComfyUI?
Yes, there is a method to override censorship; but it depends on the ComfyUI team. ByteDance has a toggle to disable censorship in the API you use to generate and edit images. But the API that ComfyUI provides with ByteDance can only be configured by the ComfyUI team. The same thing happened with FreePik, and they disabled censorship in less than 48 hours. Let's hope ComfyUI does the same.
same problem here, ComfyUI team please fix this. I know Freepik has already fixed it days ago, why are you guys taking so long?
I confirm that Freepik also had the same issue due to not disabling censorship in its API; however, they fixed it in less than 48 hours. We hope ComfyUI follows the same steps; it's simply a matter of unchecking the box in the API settings on ByteDance (BytePlus.com).
i really hope they see our comments and fix it asap, like you said, it's just a matter of unchecking a box which takes 5 minutes maximum
What is perameter to disable filter? I turn off "Content pre-filter" on Online Inference already but still got refuse from time to time
It should be fixed now
ComfyUI has to disable the filter on their end... we're all waiting for them to do this...
What is the best way to combine images like in blog post when node only has one input?
You will have to use a "batch images" node to pass 2 (or more) inputs at once.
It's not available in the USA?
what's the best method of using multiple images with this node?
Batch Image Nodes. You can either use a core node or a custom node that allows more inputs.
i, I’m kind of new to ComfyUI and I’m running Seedream 4.0 via API. I want to use the LoRA Power Loader, but I can’t get Seedream 4.0 to run with LoRA in any way. Do you have any idea
it is possible ?
For now it is not possible because the model is provided througth API.
Thank you so much for replay
Sweet. How much does it cost please?
$0.03 per image
Hi! We’d like to produce a large amount of AI-generated videos on ComfyUI and sent you an email asking for more info, but nobody reponded us. Could you please give us the email of your bussiness manager? Thank you in advance.
Not sure what we can help but you can send email to jo@comfy.org : )
Thank you!
Hi noela can u reach out to me @itssmattewai on IG I can help you out.
@itsmathewai