The module already has VAE. Unless you have specific coloring requirements, it is recommended to use the VAE inside the module. Currently, personally recommend NoobAI ( 1.7, 1.9, 2.4, 2.8, 3.3) . If the FP32 upload fails multiple times, stop attempting to upload.Buy a Coffee for me☕️
Suggested: Txt2img 720p+ with Hires fix. Upscaler recommended Remacri setting to 1080p+.
Prompt Prefix:
masterpiece,best quality,perfect quality,absurdres,newest,very aesthetic,vibrant colorsNegative Prompt:
shiny skin, shiny clothing, worst quality, low quality, lowres, signature, username, logo, bad hands, mutated hands
V3.0, V2.9 Variant suggested: forge and use latent modifier integrated
Suggested Resources: Eyeful, adetailer, remacri, Face_finder
Simplified instructions for the standard guidelines of NoobAI
Character and artist tags Prompts achieve reliable performance when applied to NOOBAI CSV files with the Danbooru+e621 dataset exceeding 300 images in the official records. ( NoobAI huggingface csv).
The illustrious checkpoint pre-release beta version for testing must be used in accordance with the illustrious XL standard usage guidelines.This illustrious checkpoint is not stable, and the background sometimes disappears
Description
FAQ
Comments (11)
请问v2.9 variant相比v2.9有什么改变呢？😮
有做些颜色上的微调与修正，让颜色看起来更自然，调整方向是以forge使用 latent modifier integrated 模式为主
Hey there! The Checkpoint is really cool, but "Latent" doesn't work with the V2.9 Variant, despite the description suggesting it. Every image becomes an interlaced mess. Remacri and ESRGAN works, but they don't correct mistakes sadly.
It's not referring to the latent upscale technique, it refers to the Latent Modifier module in the Forge/reForge webUI located in the expandable box below the main controls, which allows for dynamic CFG and noise controls. It's not necessary but it does make a difference in results. Generally for NoobAI models, Remacri is the best upscaler.
@something287771 Oooh, my bad then, Thank you!
this has been my GO TO model for MONTHS now and it has yet to disappoint. Thank you, genuinely.
我想知道这里有哪些画师的画风，learning
NoobAI huggingface csv 里面有写,但不一定会很像,如果要很像建议去载lora
@ok_furry_image 豪的谢谢
I’m actually quite curious why my model has a relatively high online usage rate, but comparatively low downloads and engagement metrics such as likes.
i dont think most people realize that they can actually do this all locally on their computers, so they resort to generating images online. if not that then it's either 1. they have really outdated computers or 2. they don't have a computer