Hithis is clean and sharp mix of base Stable Diffusion 1.5 model which can do 3d/illustrations/photo etc and there are no analogues, made to be close to original model so no surprises here<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/b696fecf-b721-431f-995c-999594c7cd7b/width=525/b696fecf-b721-431f-995c-999594c7cd7b.jpeg" /><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/758b7d0a-32df-4da8-951c-cf8cfb2241b0/width=525/758b7d0a-32df-4da8-951c-cf8cfb2241b0.jpeg" /><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/fef55bca-5de3-4e56-9981-1751843526e3/width=525/fef55bca-5de3-4e56-9981-1751843526e3.jpeg" /><hr /><h3 id="styles-comparison-dynnwggma">Styles comparison</h3><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/d8d5400a-35a6-48e0-811e-fbaa7dc9c2d8/width=525/d8d5400a-35a6-48e0-811e-fbaa7dc9c2d8.jpeg" />vector illustration<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/01c25501-66ad-48ce-815d-a3538f07c6d9/width=525/01c25501-66ad-48ce-815d-a3538f07c6d9.jpeg" />3d render<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/60c4eff0-3c69-41af-aef7-a9647aaae76e/width=525/60c4eff0-3c69-41af-aef7-a9647aaae76e.jpeg" />photo<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/04cc0cbe-d254-47a0-ba38-b4214f58744a/width=525/04cc0cbe-d254-47a0-ba38-b4214f58744a.jpeg" />STABLE v2.2 - fix for v2 for illustration bias shift in some cases, also overall quality improvements, check comparison gridsUPD: there are still some small misbehaviours occurring occasionally due to influence of loras, should be fixed in next iterations____________________________________________________previous checkpoint changes <a target="_blank" rel="ugc" href="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/bea8ac77-5b17-4094-b83c-4db81fe4357f/original=true,quality=90/40267873.jpeg">full size1(ezra)</a> <a target="_blank" rel="ugc" href="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/c49b062e-7efc-4b20-a0bb-e0c8594f7488/original=true,quality=90/ComfyUI_temp_fuxyz_00001_.jpeg">full size2(santa)</a>STABLE v2 - starting new version of checkpoint based on test mix <a target="_blank" rel="ugc" href="https://huggingface.co/iiibax/STABLE_1.4/blob/main/STABLE_src.safetensors">STABLE_src </a>with step-by-step tuning. now it's tuned with <a target="_blank" rel="ugc" href="https://civarchive.com/models/1276661?modelVersionId=1579771">samdoesarts_v2</a> lora which gave this mix nice illustrations, but the bias shifted to art where it's not needed and will be fixed with next release soonSTABLE v1.5.1 - tuned with <a target="_blank" rel="ugc" href="https://civarchive.com/models/1276661?modelVersionId=1440224">samdoesarts lora v1</a>, improved quality of illustrationsSTABLE v1.5 - tuned with <a target="_blank" rel="ugc" href="https://civarchive.com/models/243945?modelVersionId=1345318">girls showing tongue lora v2</a>, better overall qualitySTABLE v1.4.2 - tuned with walking robots lora, slightly better overall qualitySTABLE v1.4.1 - slightly better overall qualitySTABLE v1.4 - more realism, more art, more overall quality improvementsSTABLE v1.3 - one of the test mixes gave overall improvements, so I made another releaseSTABLE v1.2 - made another merge with sd 1.5 (due to <a target="_blank" rel="ugc" href="https://civarchive.com/models/243945/tongue">tongue v1.1 lora</a> merge, all girls looked more like bimbo then natural beauty)STABLE v1.1 - now it's more sharpSTABLE v1 - starting new mix with fine tuning by own loras

drrjdj

drrjdj_jjc2.safetensors

jjc2

STABLE v2.2

STABLE v2

STABLE v1.5.1

STABLE v1.5

STABLE v1.4.2

STABLE v1.4.1

STABLE v1.4

STABLE v1.3

STABLE v1.2

STABLE v1.1

STABLE v1.0

jjhdc3

v1.0

Files with SHA256: 74f742b380a632ec944d21beffafc824c02693a3c44691a07336ba57fd98946e