SDXL
To clarify: this is an epsilon-prediction model, although some of the model used in merging is v-predThis checkpoint merge is positioned as an epsilon-pred adaptation of the v-pred model catTowerNoobaiXL while keeping its high quality, so if you can run a v-pred model please also check that one out : )v1.8_re is built on catTowerNoobaiXL_v18Vpred and waiIllustriousSDXL_v160v1.5 is built on catTowerNoobaiXL_v15Vpred and waiNSFWIllustrious_v90v1.4 is built on catTowerNoobaiXL_v14Vpred and waiNSFWIllustrious_v70v1.0_fix is built on catTowerNoobaiXL_v11Vpred and waiNSFWIllustrious_v70This is my first checkpoint merge, an experimental attempt to turn a V-prediction model into eps-prediction model.It's mainly built on catTowerNoobaiXL (v-prediction) and the final merge is in eps-prediction format so that you can use it in vanilla webui.It was achieved by gradually shift its output layers to other eps models. The chosen model to replace those parts was (90% waiNSFWIllustrious + 10% ebara_pony_2.1). The converted model was further merged with waiNSFWIllustrious at 9:1 ratio so roughly speaking, it's about 70% CatTower + 28% wai + 2% ebara, that's why I call it CatWai.The merge was done in ComfyUI. You can drag the model file or the json workflow into ComfyUI to see the detailed merge work flow. The json can be found in the zip uploaded as "training data". With the ComfyUI workflow you can save 6GB downloading if you have the mentioned 3 models on disk : ) The text version recipe is also included below.Many thanks to source models' authors, especially the catTower model which is so nicely crafted that makes me excited on AI painting stuff again! The license for this merge is the same as catTower one as required: commercial use is prohibited.Originally I wanted to post this one as some patch LoRA on catTower but it failed. I did get something close but the quality drop is significant even at dim=conv_dim=512.SettingsI'm new to IL / Noob so this setup may not be optimal.Positive Prompt:masterpiece, best quality, absurdres, safeNegative Prompt:lowres, worst quality, low quality, bad anatomy, bad hands, 4koma, comic, greyscale, censored, jpeg artifacts, overly saturated, overly vividSampling method: EulerSampling steps: 30Resolution: personally I recommend 1024 x 1536 but people use 832 x 1216 more oftenCFG Scale: 5Clip skip: 2Recipev1.4 has the same merge workflow where catTowerNoobaiXL_v11Vpred is replaced by catTowerNoobaiXL_v14Vpredv1.5 has the same merge workflow where catTowerNoobaiXL_v11Vpred is replaced by catTowerNoobaiXL_v15Vpred and waiNSFWIllustrious_v70 is replaced by waiNSFWIllustrious_v90You can also drag the model file or the json workflow into ComfyUI to see the detailed merge work flow. The json can be found in the zip uploaded as "training data".A = 0.9 * waiNSFWIllustrious_v70 + 0.1 * ebara_pony_2.1 B = x * catTowerNoobaiXL_v11Vpred + (1 - x) * A where x is [1.0, 1.0, 1.0, 0.7, 0.5, 0.25, 0.1, 0.0, 0.0, 0.0] for output_block 0-8 and remaining out blocks. x is 1.0 for other blocks (i.e. input_blocks + mid_blocks + others) result = 0.9 * B + 0.1 * waiNSFWIllustrious_v70LicenseLicense is the same as catTower: commercial use is prohibited.
