MixIllustriousmerge5:
Use online: https://tensor.art/models/842520876911061717
Model created from merges with the models:
Recommended settings:
Sampler: Euler or UniPC/uni_pc
Negative Prompt :
bad quality, worst quality, worst detail, low quality, low res, bad anatomy, mutated, deformed, fused, conjoined, extra tail, bad hands, bad eyes, ugly, jpeg artifacts, text, watermark, artist name, username, logo, signature, patreon,
MixIllustriousmerge4:
Use online: https://tensor.art/models/832779800889321218
Model created from merge sum twice in SD.Next of models:
mixillustriousmerge1_mixillustriousmerge3
merge_mode: "sum_twice", alpha: 0.7, beta: 0.3
Recommended settings:
Sampler: Euler or UniPC/uni_pc
Negative Prompt: bad quality, worst quality, worst detail, low quality, low res, bad anatomy, mutated, deformed, fused, conjoined, extra tail, bad hands, bad eyes, ugly, jpeg artifacts, text, patreon, signature, title, username,
MixIllustriousmerge3:
Use online: https://tensor.art/models/825070261578530827
Model created from merges in SD.Next:
Final: mixillustriousmerge33__1 + mixillustriousmerge32_2 + mixillustriousmerge4_2
merge_mode:"sum_twice" alpha: 0.3, beta: 0.7
mixillustriousmerge4_2: mixillustriousmerge1_mixillustriousmerge2 + rouwei_v07Epsilon + mixillustriousmerge32_2
mixillustriousmerge32_2: indigoFurryMixXL_noobaiEPS + rouwei_v07Epsilon + mixillustriousmerge31
merge1: mixillustriousmerge1_mixillustriousmerge2 + rouwei_v07Epsilon + fifthMixIllustrious_absinthe
MixIllustriousmerge2:
Use online: https://tensor.art/models/823763513483796223
Model created from merge sum twice in SD.Next of models:
merge_mode: "sum_twice", alpha: 0.7, beta: 0.2
it may be necessary to use solo in the prompt, so that the model does not generate several or 2 in some cases
MixIllustriousmerge1:
Model created from merge similarity add reference in SD.Next of models:
merge_mode: "similarity_add_difference", alpha: 0.5, beta: 0.5
The model sometimes tends to generate people without this being in the prompt.
The generated images may be a little different from the uploaded ones because I am using SD.Next to generate the images