Forgot to mention I used flux dev for comparison. ALSO looks like Jug v12 (XII) will drop very soon too and rundiffusion (team behind Juggernaut models) look to have engaged black forrest for training with Flux model 😮 Happy days ahead 🎉
There is also another very big advantage of Juggernaut XI over flux. Speed. And yes, you can get faster flux, but with some big quality sacrifices. Flux is the iPhone and Juggernaut is the Android of the SD world. But they both have their plance in our hearts.
Well it is nice, but no idea where they sourced the "training material" so I guess it is the same as using Flux with its license limitations. And you can't prompt Flux and SD based models the exact same way, adding detail to Flux.1-dev prompts makes a difference. And "quality" of generations is also dependent on subject matter, whatever was included into or removed from training data of each specific model, will decide if such things will be generated better or won't be generated well if at all. Like if you want to generate scantily clad women, Flux probably will generate "not so good" images.
Excellent video and comparison. I think that at the moment Flux is very far from ideal. Yes, the anatomy is a little better, but everything else is currently at a weak level and requires a lot of improvements and training. Perhaps over time this model will reach the level of quality xl. And I'm not saying that the model is bad, no, it is not bad, it is different and this is the base on which you will have to work hard. And yes, I myself am trying to slowly work on improving this model, but it is very difficult.. Thanks for the video
Are you disrespecting Juggernaut by beeing ironic with your comparisons? Flux is the new standard. Nothing can compare yet. But I will always have fond memories of my days with juggernaut. (and still use it a lot because wel.. Ip-adapter and controlnet )
I wish , I still think Flux is much better overall as my comparison very limited. Hands text feet WAY better with Flux but SDXL still very useful ,(Apache 2 license) keen to test v12 (XII) and their Flux trained model when it comes out.
Are you using the same prompts for both? If so Juggernaut will come out better as you need to prompt differently for Flux so using it with SDXL style prompting is putting it at a disadvantage.
true. You can't test different models with the same prompting. ALso, he didnt mentionned which version of flux. Is that dev full or a water down version
Naa... best Model since long time: Dreamshaper Turbo SDXL. Best Model for Photorealism, only 6-9 Steps, superfast, 10 seconds on 8 GB VRAM in ComfyUI for 1024x1024. Upscaling very fast via Upscayle (Open-Source-Software). Flux sucks. Dreamshaper Turbo ist King.
You haven't used many SDXL models, have you buddy? Dreamshaper has to be one of the worst models available on SDXL. The creator has said multiple times that they aren't interested in SDXL as a model platform and in my experience anything that they have released for it is just half-assed. No offense, his SD1.5 model is one of the best, hands down. But the only thing his half-baked XL models have done is taken away potential downloads from creators who actually had the passion and drive to work with SDXL long-term.
I have my personal preference issues with older Juggernaut models, but no questions between JuggernautXL and DreamShaperXL which of the 2 projects was most heavily invested into. I have nothing but respect for the work that's been done on Juggernaut as the range of content it's been trained with effectively is beyond that of most models and it's prompt adherence is very decent. There are definitely better models, at least compared to older juggernaut versions I have tested. But most of them still fail to reach the same level of variation that Jugg has, only beating it in output quality or consistency, rather than knowledge base.
![Blox Fruits Dragon Rework Update [Full Stream]](http://i.ytimg.com/vi/EqDAp8udhm0/mqdefault.jpg)
Forgot to mention I used flux dev for comparison. ALSO looks like Jug v12 (XII) will drop very soon too and rundiffusion (team behind Juggernaut models) look to have engaged black forrest for training with Flux model 😮 Happy days ahead 🎉
@AI_Made_Simple. wait so your saying juggernaut Xi is trained on flux images? Will there be an sd1.5 version?
@@shareeftaylor3680 not sure how they trained Xi but I saw they said they were in discussion with Black Forrest about future fine tuned models
SDXL wil never have the same prompt understanding that Flux has, least I don't see it ever having it.
Flux images at the moment feels like they was taken by a super expensive camera and the models has a layer of make-up on them.
That's the only issue right now. You can't get anything but perfection...
SDXL will never be dead!! We have Pony for anime 😊
Amen 🙏
I love JuggernautXL.
They never surrender, dude! Let them fight! BTW, I still prefer Flux dev ;)
:D
Glad to see Juggernaut kick ass. Been a big fan of Juggernaut
There is also another very big advantage of Juggernaut XI over flux. Speed. And yes, you can get faster flux, but with some big quality sacrifices.
Flux is the iPhone and Juggernaut is the Android of the SD world. But they both have their plance in our hearts.
Nice analogy
Did you try realvis v5?, if so will you made a video of it?
I haven't seen that. What is it ?
@@AI_Videos_111 Lol, I meant realvisxl, it has a new version wich is the v5.0, im pretty sure you know that checkpoint
@@danielc121 coolio will check it out. Thanks
hands holding feet 😂, that's all you need to test
🤣I gotta try that now!
Yeah but nobody wants to see hands holding feet... other than the feet fetish community.
for super heroes it is going to be based off the comic book data so for that one it was better there
Kandoo and RD basically said their now focused only on Flux so.....
Literally every example you showed Flux won. How much did you get paid omg?
$1 million dollars 💸😆
Those born to walk cannot fly, Xl in the past
Well it is nice, but no idea where they sourced the "training material" so I guess it is the same as using Flux with its license limitations. And you can't prompt Flux and SD based models the exact same way, adding detail to Flux.1-dev prompts makes a difference. And "quality" of generations is also dependent on subject matter, whatever was included into or removed from training data of each specific model, will decide if such things will be generated better or won't be generated well if at all. Like if you want to generate scantily clad women, Flux probably will generate "not so good" images.
Flux is better at realism. Also we will have a flux juggernaut someday
Excellent video and comparison. I think that at the moment Flux is very far from ideal. Yes, the anatomy is a little better, but everything else is currently at a weak level and requires a lot of improvements and training. Perhaps over time this model will reach the level of quality xl. And I'm not saying that the model is bad, no, it is not bad, it is different and this is the base on which you will have to work hard. And yes, I myself am trying to slowly work on improving this model, but it is very difficult.. Thanks for the video
Are you disrespecting Juggernaut by beeing ironic with your comparisons? Flux is the new standard. Nothing can compare yet. But I will always have fond memories of my days with juggernaut. (and still use it a lot because wel.. Ip-adapter and controlnet )
What? I think all the examples from flux looks much better realistic than juggernaut
I don't think Juggernaut will come close to FLUX. There are big differences in the generated images and FLUX is the better model
??? Is this a Juggernaut advertisement ???
I wish , I still think Flux is much better overall as my comparison very limited. Hands text feet WAY better with Flux but SDXL still very useful ,(Apache 2 license) keen to test v12 (XII) and their Flux trained model when it comes out.
The presentation would have been more engaging if you could have made the comparisons by keeping the images from two models side by side.
lmao, is this a troll? Are you being sarcastic here? I can't tell. This must be some kind of joke, right?
Are you using the same prompts for both? If so Juggernaut will come out better as you need to prompt differently for Flux so using it with SDXL style prompting is putting it at a disadvantage.
true. You can't test different models with the same prompting. ALso, he didnt mentionned which version of flux. Is that dev full or a water down version
@@thibaudherbert3144, I tried Dev and Schnell when it first came out and quickly discarded Schnell.
I think this guy has bad taste there's clearly something wrong with his eyes how flux get 0 and sdxl 6😅
🤣
the problem with flux is nsfw not much nsfw
Naa... best Model since long time: Dreamshaper Turbo SDXL. Best Model for Photorealism, only 6-9 Steps, superfast, 10 seconds on 8 GB VRAM in ComfyUI for 1024x1024. Upscaling very fast via Upscayle (Open-Source-Software). Flux sucks. Dreamshaper Turbo ist King.
for hands flux is unmatched
You haven't used many SDXL models, have you buddy? Dreamshaper has to be one of the worst models available on SDXL. The creator has said multiple times that they aren't interested in SDXL as a model platform and in my experience anything that they have released for it is just half-assed.
No offense, his SD1.5 model is one of the best, hands down. But the only thing his half-baked XL models have done is taken away potential downloads from creators who actually had the passion and drive to work with SDXL long-term.
I have my personal preference issues with older Juggernaut models, but no questions between JuggernautXL and DreamShaperXL which of the 2 projects was most heavily invested into. I have nothing but respect for the work that's been done on Juggernaut as the range of content it's been trained with effectively is beyond that of most models and it's prompt adherence is very decent.
There are definitely better models, at least compared to older juggernaut versions I have tested. But most of them still fail to reach the same level of variation that Jugg has, only beating it in output quality or consistency, rather than knowledge base.