Illustrious XL 1.0 Based High Quality ???? Realism Model
Description
GR-Illustrious Semi Realistic (ILv1.0)
This is a Illustrious XL 1.0 based photorealism model that can generate both ???? and SFW. Since realism is new subject for Illustrious models, it can struggle to generate very complex poses but it can still can generate most of the things with accurate details. Since it's realism model, anime characters are mostly removed from dataset. You need to use LoRAs to generate anime characters but i think it's not a problem for a realism model. You can improve quality of your results with realism keywords and lighting keyword. Please don't use Style and Quality LoRAs that made for anime models with this model, this model focuses on photorealism. This model can work with various samplers and they have different effects on style
. Please check below to learn samplers and use what you liked most.
If you liked model, you can favourite it and give it a 5 star rating. It keeps me motivated. Thanks!
Recommended Resolution
This is the most important part so please read carefully. This model is based on IL1.0 base model and resolution choices are higher than standart models. If you use 768x1152 like standart resolutions offered by SeaArt, quality will significantly drop and you won't be able to see actual quality of model. Please use these resolutions for generation.
1:2 - 2:1 768x1536 - 1536x768
9:16 - 16:9 864x1536 - 1536x864
2:3 - 3:2 1024x1536 - 1536x1024
3:4 - 4:3 1152x1536 - 1536x1152
4:5 - 5:4 1152x1440 - 1440x1152
1:1 1536x1536
Recommended Positive: masterpiece, best quality, amazing quality
Recommended Negative: lowres, bad quality, worst quality, bad hands, bad ???????, sketch, jpeg artifacts, ugly, poorly drawn, censor,blurry, watermark, artistic failure, artistic error, bad proportions, bad perspective, displeasing, very displeasing, oldest, child, childish
Recommended Settings
You can use CFG value between 3~7, CFG 5 is Recommended for standart usage.
25~40 Steps, 30 is sweetpoint for model.
You can use Euler, Euler a, DPM++ SDE Karras and DPM++ 2M Karras with this model. Karras method is recommended for both Euler and DPM type samplers if you use ComfyUI.
Model has baked-in vae, no need to use any vae.
ClipSkip must be 2.
Use Creative Upscale to adjust small details and refine image.
Thank you for reading!




