MeinaPastel aims to make illustrations with a 2d feeling to like pastel or colorful images!
I have a discord where you can share images, discuss prompt and ask for help. https://discord.gg/meinaverse
我有个可以让你分享图片和参与讨论与询问问题的discord群。
I also have a ko-fi and Patreon page where you can support me or buy me a coffee <3 , it will be very much appreciated:
https://ko-fi.com/meina and https://www.patreon.com/MeinaMix
MeinaPastel is officially hosted for online generation in:
- Mage.space ( with animate feature )
- SeaArt
---------------------------------------------
Recommendations:
Sampler: DPM++ 2M Karras/SDE Karras/euler a: 20 to 40 steps.
Resolutions: 512x768, 512x1024 for Portrait!
Resolutions: 768x512, 1024x512, 1536x512 for Landscape!
CFG Scale: 4 to 11.
Hires.fix: R-ESRGAN 4x+Anime6b, with 15 steps at 0.4 denoising.
V6(Pastel) Hires.fix: Latent (Nearest-exact) with 10 to 15 steps at 0.55 denoising.
Clip Skip: 2.
Negatives: '(worst quality, low quality:1.4), monochrome, zombie, (interlocked fingers)'
---------------------------------------------
Description
This version have Baked VAE
( all of the images in the samples are upscaled by 2x using SDwebui extras tab.)
If you have any questions related to the model or its samples, how to get started or just want to share your creations, feel free to join the newly created discord: https://discord.gg/F6yeQtEQ98 <3
V4 have improved eyes and hands, It no longer does pastel by default when using Hires.fix latent, but i like the 2d feeling it gives and its eyes.
---------------------------------------------
Recommendations:
Sampler: DPM++ 2M Karras: 20 steps.
Resolutions: 512x768, 512x1024. ( other resolutions may work).
Hires.fix option 1: Latent, with 10 steps and 0.55 denoising.
Hires.fix option 2: R-ESRGAN 4x or +Anime6b, with 15 steps at 0.1 up to 0.3 denoising.
Clip Skip: 2.
Negatives: ' (worst quality, low quality:1.4), monochrome, zombie '
Prompt: ' colorful ' and ' high contrast ' makes the model look more 2d and with colors more vivid.
---------------------------------------------
FAQ
Comments (5)
Man I don't know how you do it but your colors are always so punchy. Great job.
There seems to be a tendancy for the model to create collages, what prompts or neg prompts do you use to avoid it?
I see that I'm super late here but since it was never answered: I've noticed some effect from adding "panels," "comic," and "multiple views" to the neg prompt. Anecdotally, "panels" seems to be most effective but all three seems to work a bit more than just "panels."
Is the VAE baked into this checkpoint merge or should I use a specific one?
If I should use a specific one, which one should it be?
I might be super duper late but it's already baked in, since there's a separate ckpt one
Details
Files
meinapastel_v4AnimeIllustration.safetensors
Mirrors
11866_meinapastel_V4.safetensors
MeinaPastelV4.safetensors
meinapastel_v4AnimeIllustration.safetensors
meinapastel_v4AnimeIllustration.safetensors
meinapastel_V4.safetensors
meinapastel_V4.safetensors
meinapastel_V4.safetensors
meinapastel_V4.safetensors
meinapastel_v4AnimeIllustration.safetensors
meinapastel_V4.safetensors
meinapastel_V4.safetensors
meinapastel_v4AnimeIllustration.safetensors
meinapastel_V4.safetensors
meinapastel_V4.safetensors
meinapastel_V4.safetensors
meinapastel_V4.safetensors
meinapastel_v4AnimeIllustration.safetensors
meinapastel_v4AnimeIllustration.safetensors
meinapastel_v4AnimeIllustration.safetensors
meinapastel_V4.safetensors
meinapastel_V4.safetensors
meinapastel_v4AnimeIllustration.safetensors














