drrjdj

Hi

this is clean and sharp mix of base Stable Diffusion 1.5 model

STABLE v1.5.1 now tuned with stunning artworks, serene changes

currently starting checkpoint from scratch with new test mix STABLE_src. that includes training old loras on new mix. i'm still on a way to the best approach to keep model stable and produce as best results as possible and it takes time, so the next release should be much more different and better from all previous iterations and will get v2

Portrait photo of muscular bearded guy in a worn mech suit, light bokeh, intricate, steel metal, rust, elegant, sharp focus, photo by greg rutkowski, soft lighting, vibrant colors, masterpiece, streets, detailed face, eye iris

photo of a man, natural background with forest, warm light, selective focus

illustration, portrait of a mean Gangster, wearing a black Bandana

oil painting of a girl

STABLE v1.5 has best performance (tuned on girls showing tongue lora, full dataset available on huggingface (336mb))

To better understand changes check full size1(ezra) full size2(santa)

____________________________________________________

STABLE v1.5.1 - tuned with samdoesarts lora v1, improved quality of illustrations

STABLE v1.5 - tuned with girls showing tongue lora v2, better overall quality

STABLE v1.4.2 - tuned with walking robots lora, slightly better overall quality

STABLE v1.4.1 - slightly better overall quality

STABLE v1.4 - more realism, more art, more overall quality improvements

STABLE v1.3 - one of the test mixes gave overall improvements, so I made another release

STABLE v1.2 - made another merge with sd 1.5 (due to tongue v1.1 lora merge, all girls looked more like bimbo then natural beauty)

STABLE v1.1 - now it's more sharp

STABLE v1 - starting new mix with fine tuning by own loras