Any one manage to get flux to work? When I run the exactly example in the documentation it errors wi
Any one manage to get flux to work? When I run the exactly example in the documentation it errors with NSFW:
F
FAm I the only one that can't get
@cf/black-forest-labs/flux-1-schnell to work? Even the short example at https://developers.cloudflare.com/workers-ai/models/flux-1-schnell/ is broken for me.
DHey, is anyone else still seeing this with flux?
IWe're going to try escalating it
DIsaac has escalated this, we'll let you know if we have any updates
CLooks like the example is categorized as nsfw but most other inputs aren't
RThe example code doesn't work. Flux returns a json object with the image encoded as base64. So you need to decode it.
FThank you, got it working now. 
RA lot of prompts triggers the NSFW error. "cyber", "bar", "toe", "arm", "nose", "drill", "boot", "spy", "cow", "chicken" just from trying a few random one word prompts. "a cyberpunk cat" is ok, "cyberpunk cat" isn't.
DThe team is looking into the filter, for the time being they recommend using longer prompts as they are less likely to be caught - they recommend at least 4-5 words
Aany ideas?
RThis. Although I wish https://developers.cloudflare.com/workers-ai/privacy/ were more clear. It feels well-intended and as if it is written to provide peace of mind, but "Cloudflare does not use .. to" can be read as "does use, except for these two things" in the same way that "may be stored by Cloudflare if you specifically use a storage service" can be read as "does not store, except if".
RRight now, however, I'm more concerned about Cloudflare throwing NSFW errors and wonder if this filter is Cloudflare's own doing, because if so then IMO Cloudflare is on a slippery slope of engaging in content moderation, and I can't find anything about NFSW in terms and conditions. So I would very much like to have some clarity regarding this. Might be raising an "unpopular option" thing here, but well.. I feel it is important.
F?pings
FPlease do not ping community members for non-moderation reasons. Doing so will not solve your issue faster and will make people less likely to want to help you.
FThe link you posted defines all input/output as Customer Content. This is a term specified in their Self-Serve Subscription Agreement. Specifically 2.5.1 states Subject to the terms of this Agreement, you hereby grant us a non-exclusive, fully sublicensable, worldwide, royalty-free right to collect, use, copy, store, transmit, modify and create derivative works of Customer Content, in each case to the extent necessary to provide the Services. With the current trend of excessive data retention among AI providers, I would be very hesitant to assume any sort of privacy regarding the use of these services. At least I find it hard to read it any other way.
AI am noticing a large number of AiError: 3001: Unknown internal error s when doing some AI/Vectorize queries (I believe when creating embeddings). Is there any way to get more insight into what these are? I have no clue if it's not able to get the model, if I'm getting rate limited, or if it's something I can control
RThat's very helpful and reassuring. Thanks for replying!
Athank you!
Aalread been trying this on and off for months, another week wont hurt 
Awhat is the format of the output?
Rbase64-encoded WAV. (
{ audio: "UklGRl4VAQBXQVZFZm10 ...... " })
PHi I need someone to help me connect my API endpoints with Adobe Express
JWould love to see the Huggingface Model NousResearch/Hermes-3-Llama-3.1-8B instead of @hf/nousresearch/hermes-2-pro-mistral-7b
Since it is newer, more used and i see no reason why you should not use it instead. Thanks
Since it is newer, more used and i see no reason why you should not use it instead. Thanks
Bis there a way to check the context length of models hosted on cf? Or the quantization? Are they extra quantized than regular models of the same name on huggingface/ollamaa?
Chi guys is there a way I can add like 80KB worth of text as instructions to the AI -- KV, D1 maybe?
FIn a constant variable If those instructions change only on build time at worst? Otherwise D1, KV, R2 depending on your needs.
AHey guys, we're using the Workers AI REST API (
llama-3.1-70b-instruct) and, for some reason, I'm currently unable to see in Cloudflare dashboard how much we've been consuming. Any ideas?
Bhow to generate custom sized images instead of square shaped using flux in cloudfare ai?
MHow to check models accuracy which has been provided by cloudflare as in analytics it provides me request and errors of api call
MYou can pass it as chunks
BWould Workers AI allow cross-origin request?
0do workers stay online after a request is made to handle further requests or do they get shutdown instantly?
FUsually workers exit when they have done their work
I^ they can stay online for a little bit but different users will likely hit different servers (meaning they won't hit the same Worker) and Workers are not guaranteed to stay online at all.
ACan we please get... Qwen2.5-Coder-32B-Instruct on cloudflare AI?
SCan anyone make LoRA adapters work? I'm constantly getting
{"errors":[{"message":"AiError: AiError: Unknown internal error","code":3028}],"success":false,"result":{},"messages":[]} . The example from the docs doesn't work either https://developers.cloudflare.com/workers-ai/fine-tunes/public-loras/ . Tried the cURL command using my token, same error. Saw a few messages related to this before, but seems like there aren't any solution yet.Cloudflare Docs
Cloudflare offers a few public LoRA adapters that are immediately ready for use.
�the ony one supports function: @hf/nousresearch/hermes-2-pro-mistral-7b so terrible?
it even retrieves kind of tool_calls which is not in pre-defined list
it even retrieves kind of tool_calls which is not in pre-defined list
�