Fluently - one model for all tasks (Fluently XL)
I would like to introduce my model - Fluently! This model was made by merging. I crossed a lot of checkpoints and loras.
About this model
In a nutshell, I took a few checkpoints and a bunch of Loras, I crossed through an extension in AUTOMATIC1111 - SuperMerger (available in extensions). Many factors were taken into account such as: eye quality, correct anatomy, reductions in required promt for a good result.
What makes my model different from others
Correct anatomy: my model has the correct anatomy
Face details: my model generates beautifully detailed faces and eyes even without AfterDetailer
Artistic: my model activates beautiful artistry when it needs it
Inpainting: my model is pretty good at Inpainting/Outpainting and I don't need to put in a specially designed model
Anime & Comic Book style: my model can draw great Anime and Comic Book art
Merge details
Below is a severely truncated list of models and loras of this model merging:
Models:
and more models...
Loras:
and more loras...
How to use this model
Quick Start
Install this model and start the AUTOMATIC1111
Select this checkpoint
Generate images!
Optimal Parameters
Steps: 20-30
Sampler: DPM++ 2M Karras/Euler a
CFG Scale: 5-7
CLIP-skip: 1
Negative Prompt: practically unnecessary
Addion for this model
style.csv for this model: click
License
Familiarize yourself with the points of the license:
You can earn money on images generated by the model
You can only mix this model with a link to this one
You can train your model on this one and post with a link to that model
You can earn money by selling your models based on this one with a link to this model
The author is not responsible for the images you generate
The author is not responsible for your mixes of this model
The author is not responsible for your models based on this model
This model refers to open source software
Description
FAQ
Comments (6)
This looks fantastic. Can't wait to try it, though I have to go to a dental appointment so it will have to be later. I wanted to post here though because I wanted to advise you to ignore any random, nonsensical "laughing" or "sad face" emojis you might get. There seems to be a few bored people going around doing that on images or models that don't seem to warrant it at all. Not sure why, but neither of your example images are laughable or sad. They both look great! I look forward to trying this!
This model is extremely good, like shockingly so. I'm even getting great hands with no loras no embeddings and no negative prompt. I didn't even know that was possible in a 1.5 model.
Other SD 1.5 model creators should study you and copy whatever it is you're doing. Great work!
version 2.5 listed after version 3.0? are they out of order in the UI or should 2.5 be 3.5?
Hello, this ranking of versions makes sense, the fact is that version 3 is quite crude and I’m not very confident in it yet, but version 2.5 definitely gives a good result, soon I will change this ranking to the standard one when I carry out a few more tests and comparisons. Thanks for your interest in the model!
Is 2.5 preferred over 3? The versions list is out of order, not a problem, just wondered if there was a reason.
Hello, this ranking of versions makes sense, the fact is that version 3 is quite crude and I’m not very confident in it yet, but version 2.5 definitely gives a good result, soon I will change this ranking to the standard one when I carry out a few more tests and comparisons. Thanks for your interest in the model!