You can now get all my LoRAs in one single package if you subscribe to my Patreon (including those not on CivitAI):
The Complete Catalog Download | Patreon
Warning! Read this before asking why you can't replicate the samples.
All the pictures you see above have been created using only this model and no other LoRAs. A few of the pictures above, have been created using an IP-Adapter picture as an input as the first step of the workflow, this is useful to give the picture an interesting composition before processing it multiple times using img2img without the controlnet. The reason why I'm putting this as a warning is that you won't be able to replicate the same pictures you see above without some effort. (here's an explanation) If you want to learn my workflow you can find it here.
If you want to take a look at pictures generated without controlnets or external edits check this post.
Mistoon_Diamond is a variant of my SD model Mistoon_Anime_v2 which creates pictures trying to look like a modern anime screen cap.
The starting point for this model was my blend. From there, I then added a few of my custom LoRAs in the mix to change the esthetic.
This merge has been created using a lot of different models. In the start I've used popular models (and nieche ones), but now I'm mostly using my custom LoRAs to finetune the model in the way I like.
This model is oriented towards creating girl portraits, but it is also capable of creating male characters in a convincing way.
There are 5 other variants of this model available, check out my profile:
The idea behind Mistoon_Diamond is to achieve the modern Anime style without losing the original Mistoon style and colors.
It creates realistic and expressive characters with a "cartoony" twist. Unlike other anime models that tend to have muted or dark colors, Mistoon_Diamond uses bright and vibrant colors to make the characters stand out.
This works well for horizontal picture.
This model can easily do both SFW and NSFW stuff
Learn more about how I create the examples here: From Noise to Illustrations: How I Generate AI Pictures with Stable Diffusion | Civitai
In the past few months I've had a lot of people asking me why their pictures are not as detailed or clean as mine. I've written a few articles about SD, but if you want to learn my exact workflow I highly recommend you to check out my latest one: My Workflow
If you want to test this (or other models), I have made an extension to help me create pictures using a variety of different tags. The previews images have been generated using my custom extension Ranbooru which scrapes tags from random images on gelbooru, safebooru and rule34.
If you want to learn more about my workflow, check out the guides below.
Do you like my art? Also check out my DeviantArt and Redbubble Shop!
Learn how to create pictures like mine with my step-by-step tutorials:
I've got a lot of models here on CivitAI (and even more on Patreon), here's some of them:
Initially I used to release every LoRA here on CivitAI, but after a while it became very time-consuming, so I started releasing only my favourite new LoRAs here on CivitAI while still releasing all the models for free on Patreon.
So if you don't want to miss a release be sure to follow me on Patreon (for free you don't need to sub if you don't want to) here:
https://www.patreon.com/Inzaniak
If you want to check out my other models you'll find them here:
Civitai: Civitai | Share your models
Patreon (Free): Inzaniak | Generative Art and Tech Blogging | Patreon
Patreon (All): Inzaniak | Generative Art and Tech Blogging | Patreon
I've started developing custom models for myself a few months ago just to check out how SD worked, but in the last few months it has become a new hobby I like to practice in my free time. All my checkpoints and LoRAs will always be released for free on Patreon or CivitAI, but if you want to support my work and get early access to all my models feel free to check out my Patreon:
https://www.patreon.com/Inzaniak
Also check out my Redbubble shop:
I'm also open to commissions for pictures or LoRAs. Check out my Deviant Art commissions page:
If you want to support my work for free, you can also check out my music/art here:
Description
FAQ
Comments (14)
the link to your workflow is dead, I've tried every trick I know and can't anything that isn't a washed-out mess of a image with abysmal detail
I've fixed the link. It should work now.
The sample image you are using as a preview could not be generated identically using PNGINFO in WEBUI (1.6.0). (I could not generate it using TextureEmbedding called hotify and badpic)
Presumably you used I2I to upscale the image, am I correct?
I use a workflow that makes it hard to replicate the exact same pictures i make. You can find it in the description.
@Inzaniak Understood. I've read all the available free sections, but I'll check out the paid sections later. Thanks for your replay.
What happened to the underscore?
I actually made a mistake naming the model, now it should be fixed. Thanks for pointing it out!
If not upscale to beyond 4k image like example, this model generates very bad quality.
Hi! My pictures are not 4k at all (they are 1920x1280), but you will still be able to get good results even at 1152x768. If you don't know how, check my workflow here: Stable Diffusion Ultimate Guide pt. 6: Workflow | by Umberto Grando | Medium
For transparency sake I've also made a post of pictures with lower resolutions and no edits: Mistoon_Diamond low resolution prompts | Civitai
@Inzaniak seem like your article is for paid to read...
@Inzaniak Btw your second examples is still to large (1024p) because of you not using upscaler. It not different from your main examples (1080p upscale to beyond 4k). I mean usually I alway use 512p and use Hires upscaler x2 to 1024p like a Counterfeit's example
My pc can't up scale beyond than that it will be take long time to generate and end up to occurred error.
@infrezz721 the samples from Counterfeit are 1024x2048 while the ones in my new post are 576x1152, so mine are way smaller unless I'm mistaking something. You can still get good results at even lower resolutions (512x1024): Image post by Inzaniak | Civitai
You should be able to see 3 articles on Medium for free by creating an account (if they have not changed anything), or you can also check the workflow here: https://civitai.com/articles/3318
@Inzaniak Thanks for discussing anyway. I found this model is one of the best for merging with Counterfeit, like a your Mistoon v1 Don't you mind if me trolling your model for private use?
@infrezz721 You are free to merge my models to use it privately or even share them publicly.
Details
Available On (2 platforms)
Same model published on other platforms. May have additional downloads or version variants.