V3-V4 info: Two more versions trained with more recent features. Both was trained with T5 and clip-l encoders. V3 was trained with long prose from joycaption. V4 was trained with trimmed captions from <a target="_blank" rel="ugc" href="https://huggingface.co/Minthy/ToriiGate-v0.3">torii</a> captioner. Between those two I personally prefer V3.V1-V2 info: Two versions, first one is trained with 512 res and booru captions for 2000 steps and second is 768 res trained for 5000 steps with nlp captions. Can't say which one of them is strictly better, probably second one, since it's transferring style more harder even with another char lora. Haven't tested it with anything else than base checkpoint in fp16/fp8 mode and afaik rn it will not work with some quantization types in popular ui's.Workflows with prompts are right inside the images, you can just drag them into your comfyui browser window, probably could work better with "anime screencap" in pos and "realistic, 3d" in negs", negs unavail with 1 cfg, but you could hack it with <a target="_blank" rel="ugc" href="https://github.com/mcmonkeyprojects/sd-dynamic-thresholding">this extension</a>, settings for which is also into the flow already.

Fkey style (Flux dev test version)

Version trained with encoders and trimmed captions from <a target="_blank" rel="ugc" href="https://huggingface.co/Minthy/ToriiGate-v0.3">torii</a> at 768 res.

Files with SHA256: b40cc9dd226fad54e674901ade10a7fe1b792d84a357e423d9184adbd9be0346