Комментарии:
Thanks Sir! You make my day great!!!
ОтветитьIt's a real pain to update comfyui, and the missing modules NEVER appear, I really don't understand what they do when they "update" because they manage to ensure that everything that is useful no longer works.
ОтветитьCan we use SD3 in normal A1111 mode, ComfiUI is not really for me...
ОтветитьGreat information as usual, but I'll be sticking with SDXL until they get a few fine tunings out there.
ОтветитьIs there any lightning or LCM model for it?
ОтветитьCan you run this within Automatic 1111? If I place the safetensors in my models folder, my SD stops working and gives me an error. It goes back to normal once more when I remove the model.
ОтветитьThis model is simply not capable of creating even the simplest human anatomy, even the 1.5 model is significantly better for human anatomy, and this is not an exaggeration. I don't understand why they released this in the first place, this model only makes sense for creating images that don't contain people. How this was not immediately apparent to those who test these models long before the official release, as Olivio Sarikas and other ''SD Streamers'' is beyond me, they are just as credible in their "presentations" as Stability AI.
Ответитьbeautiful bro
ОтветитьBody horror model
ОтветитьCan it be used without ComfyUI?
ОтветитьThanks for leaving out all the fluff and just getting to it facts. Much appreciated.
ОтветитьThank you so much for the simple tutorial! Unfortunately the model seems to be terrible. I hope they will fix it with the bigger one.
ОтветитьThanks!
ОтветитьThis serves as an empirical clue of why Stability AI might be failing.
ОтветитьSD3 sux...
ОтветитьExcellent video, what great news! Now I'm going to wait for you to release a video on how to make a LORA with SD3 so I can create my LinkedIn profile picture 😅
ОтветитьAbout the agreement:
"You own your derivative works, but Stability AI owns the original software and any derivative works they create". ?
I would strongly advise against updating all nodes like suggested. This is because of the AppleBotzz/ComfyUI_LLMVISION hack. I would be more carefull about which node is updated to minimize risk.
ОтветитьWhy use SD3 if SD1 not only works really well but has thousands if not tens of thousands of LoRAs already created?
ОтветитьThe background music is so calming. Perfect for winding down.
ОтветитьYes!!!
Ответитьrecently there's a new model, which include clips + t5xxl fp16, it's around 15GB. it's released an hour ago.
ОтветитьCould you explain more of ComfyUI
ОтветитьAbsolutely disaster for anything pose/anatomy related — like eldritch horror level disaster. It’s also really bad at hands. On the other hands, it does well in prompt adherence and text generation but if I want to do text, I will just use photoshop or CN with the text. SD3 Medium launch feels like 2.0 all over again… dead on arrival.
ОтветитьWhy when I generate a picture in 16:9 do I have artifacts on the sides?
Ответить"Unable to find workflow in demo" after the update he swears at all the pictures
Ответитьplease also a video for automatic1111! <3
ОтветитьThanks for the update! The generations with the RAW version of SD3 are absolute trash, let's hope the fine-tuned models will be actually an improvement from previous versions.
ОтветитьHas anyone gotten img2img working yet? The VAE nodes in ComfyUI don’t appear to be compatible at this time.
ОтветитьThanks for video, Olivio!
ОтветитьGreat video Olivio thank you. Unfortunately, StabilityAI's SD3 model can't be used commercially, unless you pay a hefty fee of minimum 20 USD per month (also applies to creative freelancers). To use SD3 commercially (=anytime you sell images) there is no way around the monthly payment.
Stability AI scrapped the web for images without paying any fees (supposedly also scrapping the Midjourneys image pool), but are charging us now? These Open Source AI projects are "open source" and "research only" while they are scrapping the web for images without paying any license fees to copyright holders. When that's done, they magically transform into "for-profit" only companies (;
BTW, all images created with OpenAI's ChatGPT and Dall-E can be used commercially, no matter weather you are using their subscription or FREE plan! Pretty cool...
This also means, that StabilityAI is currently the most "expensive" and "commercial" AI platform of them all, even surpassing OpenAI. That decision I think was a big mistake, as they could have chosen the "Wikipedia" path, allowing them to stay a truly open-source research lab that is funded primarily via campaigns and donations. Instead, StabilityAI decided to go full-steam ahead with a for-profit only model, transforming into a commercial tech company.
I would say that's a pretty drastic metamorphosis for a company that started out "Research" and "Open Source".
As long as this doesn't change, I'm afraid the SD3 model will remain a non-starter for me!
Keep in mind the prompting needs to be different. I've seen much better results from people using full sentences. So no SD1.5 or SDXL style prompting.
ОтветитьPretty straightforward to run it, thanks again!
Not so happy with first results, but I hope it's just experience and prompt adjustment.
Can you run it via stable the old way or must you use comfyui to run SD3?
ОтветитьPlease....Automatic1111 setup!
Ответитьhave error pressing promt. Prompt outputs failed validation
CheckpointLoaderSimple:
- Value not in list: ckpt_name: 'sdv3/2b_1024/sd3_medium.safetensors' not in ['sdv3\\2b_1024\\sd3_medium.safetensors']
It is so bad lol. Back to SDXL and Pony.
Ответить30 steps? nah, thanks
ОтветитьThanks, Olivio, great share!
ОтветитьMy Stable Cascade images are better than SD3 (for a same prompt).
ОтветитьJust in case you don't want to give your data away: Civitai has the models, too.
edit: Also just in case you don't want to give your data away: Just don't download it as it is absolute hot garbage (unless you are into creating Cthulhu abomination type body horror)
NSFW capable or censored like 2.0?
Ответитьi cant figer out where to place the TripleCLIPLoader files (OpenCLIP-ViT/G, CLIP-ViT/L and T5-xxl) any ideas ??
ОтветитьSo, I can't use it for commercial use unlike the previous versions?
Ответитьcool. ! thanks. hope you are doing well!
ОтветитьAm I the only one that doesn't like ComfyUI? 😥
ОтветитьLet's go!!
Ответитьi'm having an error when trying to load sd3 checkpoint, any idea for: Error while deserializing header: InvalidHeaderDeserialization. at the end says "safetensors_rust.SafetensorError: Error while deserializing header: InvalidHeaderDeserialization"
edit: easy fix, do the same thing in the video for the problem he had.
whats the difference between previous models?
Ответить