Type | |
Stats | 178 |
Reviews | (10) |
Published | Dec 28, 2023 |
Base Model | |
Usage Tips | Clip Skip: 1 |
Hash | AutoV2 EA0FC05810 |
Hi
this is clean and sharp mix of base Stable Diffusion 1.5 model
v1.4.2 (tuned on walking robots mini-lora, full dataset available on huggingface) has best performance, better visual quality, stable old prompts works better, others changed entirely. To better understand changes check full size1 full size2
currently working on glitches lora. if tune will success, next release will contain several tunes with general concepts, that works really bad. the main goal is to tune bad performing concepts while keeping model clarity.
____________________________________________________
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