If you want to donate towards costs and don't want to subscribe:
https://ko-fi.com/DUSKFALLcrew
If you want to monthly support the EARTH & DUSK media projects and not just AI:
https://www.patreon.com/earthndusk
Discord: https://discord.gg/Da7s8d3KJ7
This Model IS GREAT AT:
PORTRAITS
EATING YOUR LUNCH BEHIND YOUR BACK
SMACKING YOU IN THE FACE AT MIDNIGHT
Neko, because FFXIV. Don't ask. You were warned.
Problems this model when you don't use certain samplers:
Wild proportions
BARELY PAYS ATTENTION TO CLOTHING
Can't even do a bikini
Can't decide on a style, so it's a wild nightmare fuel of every manga from 1950 until now.
Bites people for looking at it.
Demands you pay it not me.
Might need psychological therapy
THERE ARE 3 versions to this and soon coming a merge of all 3.
They all work best at your discretion, and faces etc work a lot better now - but it could be dynamic prompt, it could be we just .. the AI hated us last night?
Data it was trained on all three times:
Extremely retro manga (first run)
Hands, faces, in all sorts of matter in the second run
BOTH sets of data with out the transparent hand PNGs, added in extra realism to keep the faces from borking. Turned out this wasn't needed.
SOME Backgrounds, will still train a background model at some stage.
Duskfall's Manga Aesthetic is a highly specialized Image generation AI Model of type Safetensors / Checkpoint AI Model created by AI community user duskfallcrew. Derived from the powerful Stable Diffusion (SD 1.5) model, Duskfall's Manga Aesthetic has undergone an extensive fine-tuning process, leveraging the power of a dataset consisting of images generated by other AI models or user-contributed data. This fine-tuning process ensures that Duskfall's Manga Aesthetic is capable of generating images that are highly relevant to the specific use-cases it was designed for, such as anime, character, girl.
With a rating of 0 and over 0 ratings, Duskfall's Manga Aesthetic is a popular choice among users for generating high-quality images from text prompts.
Yes! You can download the latest version of Duskfall's Manga Aesthetic from here.
To use Duskfall's Manga Aesthetic, download the model checkpoint file and set up an UI for running Stable Diffusion models (for example, AUTOMATIC1111). Then, provide the model with a detailed text prompt to generate an image. Experiment with different prompts and settings to achieve the desired results. If this sounds a bit complicated, check out our initial guide to Stable Diffusion – it might be of help. And if you really want to dive deep into AI image generation and understand how set up AUTOMATIC1111 to use Safetensors / Checkpoint AI Models like Duskfall's Manga Aesthetic, check out our crash course in AI image generation.
This one was an 8 hour one with a few realistic faces thrown in, some backgrounds.
Go ahead and upload yours!
Your query returned no results – please try removing some filters or trying a different term.