MJ52_v2.0 is a continuation of main model 1.2, they complement each other, using two versions at the same time you will get stunning results. Use v1.2 with 0.1 - 0.8 of weight and add v2.0 to additional micro details with 0.3 - 1 of weight.
best with DPM++ 2M SDE, DPM++ 3M SDE
LoRa mimicking midjourney slyle v5.2 This LoRA works as:
v.1.2 - Color enhancer (adds contrast and colors)
v.1.2 - BG depth improver (adds depth on the background)
v.1.2 - Composition improver (change composition)
v.2.0 - Detail tweaker (make little changes and supplements the picture with MICRO details)
CFG Scale 4 - 6.
Use v1.2 with 0.1 - 0.8 of weight and add v2.0 to add micro details with 0.3 - 1 of weight.
Description
1.2 version
more accurate, improve BG depth
FAQ
Comments (32)
Very nice model, using it together with the DPO lora gave me more detail and higher saturation and contrast, this lora takes sdxl to a whole new level.HopefullyI hope the authorI hope the author willI hope the author will continueI hope the author will continue to optimizeI hope the author will continue to optimize it.
ThankU!
Thank you for this.
That's really great. For users like me with low graphics card configurations, using the Turo model and this Lora can almost achieve the quality of a normal model. Thank you very much!
great job, best "lora" ever used, thank you very much
Really good job man, this lora is excellent.
Simply gorgeous work, thank you
oh my god 2.12 gygas xD but it looks so goooodd...
omg. this is wonderfull
I'm getting pretty good results with this. The colors are more vivid and the extra details flow nicely.
why it's not showing in lora tab, please tell me how to fix this problem.
It will only show up in the Lora tab when you have a SDXL checkpoint loaded up.
hi, try this: https://civitai.com/images/6928367
@typhoonpurpoise @kintome thanks for reaction, I solved it , there was setting that unchecked and the problem has resolved now.
@savanthakur What setting was it?
thx. cool lora. waiting MJ mimic v6. and u shocked me 2gb
Outstanding, works like a charm, huge improvement.
Very good! I'm still testing it and I really like the results.
Hi, very impressive work!
BTW, how to train some a versatile lora, could u give me some tips? Many thanks
i hope that you'll release a new model soon cause now you've power of both mj v6 and sd3
Amazing works. Cool Lora. Very helpful
this has to be my favourite lora yet. Amazing work
Real masterpiece! A great addition to any SDXL workflow. Thank you!
cool, helps a lot, thank you!
Please please 🙏 make this for sd 1.5 version or make it a sd 1.5 checkpoint please it's big enough to be a checkpoint for sd 1.5.
I see this LoRA a lot in the resources, but 2GB damn, that's big, I'll give it a try! 👌
Why is this LoRA so big?
2.0 will be smaller
@AndrexSel wating for v2
Dude if its better quality then I don't mind a lora the size of a ckpt
Great Result
Midjourney mimic v1.3 - IT`S NOT FINAL VERSION! U can test it, but remember v2.0 will be done soon
Details
Files
MJ52.safetensors
Mirrors
MJ52.safetensors
MJ52.safetensors
MJ52.safetensors
MJ52.safetensors
MJ52.safetensors
XLMidjourneymimic.safetensors
MJ52.safetensors
MJ52.safetensors
MJ52.safetensors
2MJ52.safetensors
MJ52.safetensors
MJ52.safetensors
mj52_mimic_v12.safetensors
MJ52.safetensors
MJ52.safetensors
2ac68c15-7d9b-49e0-a4a2-796d3093a555.safetensors
MJ52.safetensors
MJ52.safetensors
MJ52.safetensors
MJ52.safetensors
MJ52.safetensors
mimic.safetensors
mj.safetensors
MJ52.safetensors
MJ52.safetensors
MJ52.safetensors
MJ52.safetensors
MJ52.safetensors
Available On (3 platforms)
Same model published on other platforms. May have additional downloads or version variants.