Online generation
DREAMBOX is a model based on illustriousXL_v01 and trained with over 17000 images. It utilizes Danbooru tags and natural language for labeling and includes over 100 trigger words. When using DREAMBOX , it is recommended to experiment with different combinations of trigger words to achieve various art styles.
DREAMBOX是基于 illustriousXL_v01为底模，并使用 17000 多张图片进行训练而成的，同时使用了danbooru tags和natural language进行打标并设定了超过 100 个触发词。在运用DREAMBOX时建议通过对不同触发词的排列组合，以获取不同的画风。
Recommended Settings:
Sampling Method: DPM++ 2M SDE
Schedule Type: SGM Uniform
CFG Scale: 6-4
建议设置:
采样方法：DPM++ 2M SDE
Schedule type：SGM Uniform
CFG Scale：6-4
Art Style Tag List:
- https://huggingface.co/rim0/GENESIS/blob/main/Art%20StyleV2.txt
Nji Style Tag List:
- https://huggingface.co/rim0/GENESIS/blob/main/Nji%20StyleV2.txt
Lighting Effect Tag List:
- https://huggingface.co/rim0/GENESIS/blob/main/Lighting%20Effect.txt
Character Tag List:
- https://huggingface.co/rim0/GENESIS/blob/main/CharacterV2.txt
Here are some combinations I use, feel free to try them out:
下面是几个我在使用的几个组合，欢迎各位尝试:
- (kuroduki (pieat)),(alzi xiaomi:1.1),(rei (sanbonzakura):1.1),(koujuan:1.1),nose,lips, (chromatic aberration:1.1),(colored inner hair), eyeshadow,(shiny),(shiny hair), multicolored hair,glowing eyes,
- (xilmo:1.3,)(nj (imai):1.2),(wenjun lin:0.9) (nj (aoai):1.1), 
- (wanke:1.2),(mon (monmon2133):0.9),(mochizuki kei:0.95), (tira 27:0.7),
- (akizero1510:1.25),(am314:1.15),(agoto:1.05),((bai qi-qsr:0.9),
- (tianliang duohe fangdongye:1.35),, (asagina gi:1.55),(kaneni:0.9),,
(zukky:0.75),((jazz jack:1.2)), (nep:0.9),(urakata (uracata):0.75),(tira 27:1.2),chibi,
- (alzi xiaomI:1.3),(mogumo:1.2),(fukuro daizi:1.2),(starshadowmagician),
- (esuthio:1.2), (k-suwabe:1.2),(nj (aicd):1.4),(john kafka:0.9), 
- (nj (aifh):1.25),(yaziri:1.1),nj (opai),(nj (aicd):1.1),(photorealistic),(game cg),(so-tora,cuso4 suiwabutu:0.9), 
- (jima:1.35),(ohisashiburi:0.9),(kupuru (hirumamiyuu):1.2) (fukuro daizi:1.15),
Description
FAQ
Comments (9)
whats new?
just switched the base model to Illustrious XL 1.1 for this version.
any chance you will change to illustrious 2.0 for the next version?
Yes, I'm already preparing the next version based on Illustrious XL 2.0.
@EWIGKEIT0 So v4.0 is based on IL 2.0? Or even 3.0? Have you tried to raise the native pre-upscaled resolution for generation to 2mp ? IL 3 are afaik trained on upscaled images and kinda work vanilla better with 2mp+ native resolution settings. Wonder what will happen if we utilize this in your finetune?
@deitychaser Yep, v4.0 is based on ILL 2.0 (v3.0 isn't open-source yet, afaik).
And yes, since it was trained with ARB up to 1536, it can handle high native resolutions quite well. I personally find Hires. Fix is often still the safer bet for quality.
@EWIGKEIT0 true, 3.0 still not open-source. Well, different resolutions impact the compositional output dramatically even if the ratio doesn't change but just the pixels. In terms of upscaling I started to experiment with just low step generation and high denoise hirefix. Especialyl with models that work good with dpm++ 2m SDE sampler I find you get a really good picture already with 10-15 steps and the artifacts that remain get cleaned by upscaling. With 10 steps a model is very flexible and can produce pretty cool and interesting compositions (you know like the placement of objects = the relation to them, image composition) that often get lost with higher steps. Try it!
太强，太好看了
please make a vpred