Verified: 8 months ago
SafeTensor
Type | |
Stats | 347 |
Reviews | (41) |
Published | Jul 16, 2024 |
Base Model | |
Hash | AutoV2 EA716C5BCB |
I prohibit companies like PixAI, Tensor, etc. and their users from uploading my checkpoints to websites outside of Civitai. I will do it myself if I want!
☕ Buy me coffee, if you want to support me: https://ko-fi.com/tzigoai
Please rate, comment and post your results with my model! Thanks!
TzigoAllInOneXL is a general purpose model. It can create photorealistic, anime and semi-realistic images.
In essence, it is a fusion of my realistic model with my anime model, based on the great Juggernaut XL and DreamshaperXL.
Sampler: DPM++ 2M Karras, but it also produces good results with other samplers.
Steps: 30 and more if necessary
CFG: for Realistic ~5 for Anime ~7 or higher if necessary
Merge recipe:
1 DreamShaper XL + (SDXL FaeTastic - sd_xl_base_1.0)*1, Add difference(trainDifference)
2 [1] + (TzigoRealMixXL - sd_xl_base_1.0)*1, Add difference(trainDifference)
3 ZavyChromaXL + (WildCardX-XL-Fusion - sd_xl_base_1.0)*1, Add difference(trainDifference)
4 [2] include TzigoAnimeXLStyle Lora
5 [3] + [4]*1 Weight sum(cosineA)
6 include sdxl_vae_fp16_fix