Hello everyone!
This is the first model I make based on Checkpoints Merge.
For this merge I did a lot of tests with different values, which I don't remember exactly. What I do know is the "recipe" for merge:
talmendoxlSDXL_v11Beta (by talmendo) + xl6HEPHAISTOSSD10XLSWF_v10 (by Afroman4peace) = MiaModel_v1
altxl_v30 (by altron) + MiaModel_v1 = MiaModel_v2
The idea of the merge is to get the maximum power from the models used until reaching a model that offers incredible results in almost all the generations carried out.
UPDATE!!! Model v3.0 recipe:
NightVision XL (by socalguitarist)
TalmendoXL (by talmendo)
GalaxyTimeMachine's (by galaxytimemachine)
Cherry Picker XL (by tkvier)
XL6 - HEPHAISTOS (by Afroman4peace)
AltXL (by altron)
sdxlbase_nsfw_faces (by sevenof9247)
WyvernMix - (by wier)
Positive prompt tips to get higher quality images:
Example 1:
(best quality), (masterpiece), (best lighting), (high detailed skin:1.0), detailed eyes, 8k uhd, dslr, soft lighting, best quality, film grain, Fujifilm XT3, ........ ............
Example 2:
detailed and realistic close portrait of ................... portrait photography, magical photography, dramatic lighting, photo realism, ultra-detailed, intimate portrait composition, Leica 50mm, f1. 4
Example 3:
masterpiece, best quality, (colorful), cinematic lighting, extremely detailed CG unity 8k wallpaper, ....................
As always, all your criticisms and advice will be taken into account, since they help me to continue learning and growing!
Do not forget to visit my guide to create Textual Inversion for SD 1.5
https://civarchive.com/articles/692/my-method-to-create-a-textual-inversion
If you like what I do and you would like to support me, you can do it with a coffee, link below ♥
Description
In version 3.0, I made a combination based on these models:
NightVision XL (by socalguitarist)
TalmendoXL (by talmendo)
GalaxyTimeMachine's (by galaxytimemachine)
Cherry Picker XL (by tkvier)
XL6 - HEPHAISTOS (by Afroman4peace)
AltXL (by altron)
sdxlbase_nsfw_faces (by sevenof9247)
WyvernMix - (by wier)
FAQ
Comments (10)
hey,
thx for adding my lora, which one you have choosen? ;)
seems that the weight is very low...
how to handle negative prompts
here you can read ;)
Hello! Thanks for commenting, part of the merge recipe is with your checkpoint sdxl_nsfw_faces03.
I liked that it gives more realism to some expressions, on the other hand I want to thank you for the article about the new SDXL prompts in difference with SD1.5! I hadn't really done those tests and now I have a lot to be able to test again!
@mv_ia thx, and please play and maybe you will find some good options ;)
This is excellent, I'm getting much better photoreal results with this than almost anything else so far, combined with the FineNude lora that greatly helps anatomy (base SDXL has very strange clavicles...). Many thanks for sharing!
Do you have any tips for merging new models with this as they come out (e.g. Juggernaut now has SDXL version)? Can I just use kohya scripts to do a simple merge at ~25% weight, or do you need to be more careful?
Thank you very much for your comments, I am glad that the model works for you!
Honestly, I did a lot of % tests until I got the result.
In my case, to perform the merges I use ComfyUI and there I am doing tests. Feel free to carry out all the tests and merge that you want, I plan to use Juggernaut XL in a future version of MiaModel, because it is a model that I used a lot in its version SD1.5
@mv_ia Good to know, thanks, I shall experiment!
does this have VAE baked in? or just use sdxl vae
it is recommended to use the sdxl vae
i seem to be getting the "blue avatar output" when using the SDXL vae from here: https://huggingface.co/stabilityai/sdxl-vae/tree/main
any advice?
this model is great at blending with my sdxl lora characters. it's powerful and flexible. thank you.
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.