I've spent the last while carefully balancing merges in order to achieve what I believe to be the most realistic model currently available. Please, if you like what I'm doing, support me down below!
https://www.buymeacoffee.com/tripleheadg
Buy me that Pizza!
I recommend using it in ComfyUI for best range, either with the extreme detail Ksampler or with one of Searge's workflows that make use of CFG Tone Map Rescaling. Higher CFG = less realism, however without tone map rescaling it results in blotchy outputs to go that high. I generated the anime style image using a CFG of 28 and most of the other images were generated with a CFG of 7.5.
However, it should be great at doing realism specifically on normal CFG, so don't worry about that too much all you non-comfy users.
Prompt for most of the images:
goldenhour serene backlit contrast ruleofthirds Photograph of A beautiful woman with intricately detailed pupils, captured on a (Hasselblad H5D-50c)
Negative: night, chaotic, frontlit, brightness, centered, lack of detail, color inaccuracy,
Run16K
Version Detail
SDXL 1.0
Project Permissions
Use in TENSOR Online
As a online training base model on TENSOR
Use without crediting me
Share merges of this model
Use different permissions on merges
Use Permissions
Sell generated contents
Use on generation services
Sell this model or merges
Commercial Use
Comments
Related Posts
Describe the image you want to generate, then press Enter to send.