Introduction
The Illustrious Realism Experiment (IRE) is an attempt at a realistic Illustrious model that does not sacrifice its character knowledge, prompt adherence capabilities, and compatibility with Illustrious-based LoRAs. This was mostly accomplished by block merging an Illustrious model, WAI-illustrious-SDXL v17.0, with SDXL models, namely RealVisXL v5.0 and UltraEpicAi Realism v2.0, with the help of Hako-mikan's SuperMerger; in addition, I merged in (at half strength) some LoRAs trained on a personal dataset of around eight hundred photos. My hope is that the IRE will serve as a foundation for better ones in the future.
Usage
Summary:
VAE: already baked in
Prompts: use Booru tags
Sampler: euler a
Scheduler: karras
Steps: ~30
CFG: 2-5
Resolution: 1024x1024, 896x1152, and 832x1216
For the best results, you should use Booru tags, placing the following tags at the start of your positive prompt:
masterpiece, best quality, realistic, photorealisticIncluding the tags below in the negative prompt may also lead to better quality:
bad quality, worst quality, sketch, flat color, lowresThe preview images used the euler a sampler with the karras scheduler at 30 steps, but feel free to experiment with other options (the DPM++ 2M SDE sampler, for example, can produce sharper images). The recommended CFG scale is 2-5, with a lower CFG tending toward more realism, in my opinion. Good resolutions include 1024x1024, 896x1152, and 832x1216.
While the model should be compatible with most Illustrious-based LoRAs, results will vary depending on the LoRA, and you may need to lower the LoRA's strength and/or the CFG scale.
The model has the default SDXL VAE baked into it.
Credits
IRE is based on block merge of WAI-illustrious-SDXL v17.0, RealVisXL v5.0, and UltraEpicAi Realism v2.0. You are welcome to create new merges using this model without crediting me, but please do not use them for commercial purposes.
Version History
v2.0: Some improvements to visual fidelity by incorporating RealVisXL V5.0 and training on a higher quality dataset for the LoRA merged into the model.
Description
FAQ
Comments (4)
holy sh*t this is SO good...
For a photo portrait, the best beginning is:
masterpiece, best quality, very aesthetic, incredibly detailed, newest, photo-referenced, (realistic:1.2), photo, (raw photo:1.2) BREAK [..description of the character] BREAK (subsurface scattering:1.1), (ray tracing:1.1), (softbox lighting:1.2), (rim lighting:1.1), 8k, fujifilm, macro lens.
Add to Negative Prompt: ...,(anime:1.3), (cartoon:1.3), (illustration:1.3), (drawing:1.2), digital art, cg, 2d, smooth skin, plastic skin, doll, lowres, wrinkles, blurry, (flat color:1.2), ....,
Sampler: euler_ancestral
Scheduler: Karras
CFG: 5.5
Thank you for the suggestions. For the positive prompt, it's not clear to me whether many of those tags make much a difference, since this is fundamentally an Illustrious model that relies on booru tags, and my personal preference is to keep the CFG below 5. But I'm always happy to see how people experiment with things! ^_^
Your model handles the physical interaction between two characters well, and most importantly, it correctly creates male anatomy. Many models do this with just one character, but when there are two in the frame, more than half of the models fail. Your checkpoint, however, makes almost no mistakes and knows almost all the Kama Sutra positions. :)