Version names includes the base model it was trained from, use appropriate version for each model. Rouwei version wont work well with noob, the opposite is also true. Old noob versions would be too weak on a fresh noob checkpoints also, eps and vpred should also be used with their dedicated versions. Don't forget to check version descriptions for more specific info and list of supported style tags.Anima v5 info: Version trained from <a target="_blank" rel="ugc" href="https://huggingface.co/circlestone-labs/Anima/blob/main/split_files/diffusion_models/anima-base-v1.0.safetensors">base anima 1.0</a>. <a target="_blank" rel="ugc" href="https://files.catbox.moe/stdpkl.txt">List of styles</a> and <a target="_blank" rel="ugc" href="https://safe.manu.moe/ai1HRUST.png">grid</a>.Anima v4 info: Update for recent <a target="_blank" rel="ugc" href="https://civarchive.com/models/2458426?modelVersionId=2836417">anima preview 3</a> version. <a target="_blank" rel="ugc" href="https://files.catbox.moe/p28icg.txt">List of styles</a> is same.Anima v3.5 info: Same version as anima-p2_v3, but trained of full range of blocks. Should™ just work better overall. Out of dataset test <a target="_blank" rel="ugc" href="https://safe.manu.moe/O0K1Rjl0.png">still fine</a>. <a target="_blank" rel="ugc" href="https://files.catbox.moe/pmd33i.txt">List of styles</a> the same, <a target="_blank" rel="ugc" href="https://safe.manu.moe/cMN8iazQ.png">grid</a>Anima v3 info: V3 is version trained from and for <a target="_blank" rel="ugc" href="https://civarchive.com/models/2458426/anima-official">anima preview 0.2</a>. Still <a target="_blank" rel="ugc" href="https://safe.manu.moe/VaqCDLua.png">won't affect</a> data outside of dataset so much. <a target="_blank" rel="ugc" href="https://files.catbox.moe/pmd33i.txt">Style list </a>is same with v2, <a target="_blank" rel="ugc" href="https://safe.manu.moe/EtCsPs15.png">grid with styles</a>.Anima v2 info: A bit late, since 0.2 preview is already out, but whatever. It was trained from <a target="_blank" rel="ugc" href="https://huggingface.co/circlestone-labs/Anima/blob/main/split_files/diffusion_models/anima-preview.safetensors">0.1 version of preview model</a>. Catastrophic forgetting was addressed and improved, at least it's <a target="_blank" rel="ugc" href="https://files.catbox.moe/196jew.png">not so disastrous </a>now. Mixing between styles was also a little bit improved from empirical tests. <a target="_blank" rel="ugc" href="https://files.catbox.moe/pmd33i.txt">List of all styles</a> and <a target="_blank" rel="ugc" href="https://files.catbox.moe/att98h.png">grid</a>. It would not work as well with 0.2 preview.Anima v1 info: <a target="_blank" rel="ugc" href="https://huggingface.co/circlestone-labs/Anima">Anima</a> version of lora comes with limited dataset. <a target="_blank" rel="ugc" href="https://files.catbox.moe/mp72qa.txt">List of styles</a> that comes with it. More like a test version. Model is in early stage and too incoherent at something above 1mp. If you decide to upscale, you would need to use tiled methods, unless you're okay with artifacts. Style tags should be invoked with @ before them. Mixing somewhat works, but not how it was with default xl weighting, rather like compel mode.MIO - mix in one versions with mix of ai styles and some real artists in dataset.BIO - best in one versions, containing only artificial images in dataset. 90% filled with naiv3 or styles from local models with very distinctive look only.

AI styles dump (Anima/Illustrious/RouWei/Noob)

Version trained from <a rel="ugc" href="https://civitai.com/models/833294?modelVersionId=1190596">Noob-vpred-1.0 checkpoint</a>. One of the cleanest from artifacts version due to edm2, simple <a rel="ugc" href="https://files.catbox.moe/qsflb1.png">example</a> of that. Should work fine with cfg++ and classic samplers. Some of previous version styles was dropped for various reasons. <a rel="ugc" href="https://files.catbox.moe/wwv3wn.txt">List of all styles</a> in this version. <a rel="ugc" href="https://files.catbox.moe/z48jza.png">Hello Asuka example grid</a> of all styles.

artists_v6.zip

ai_styles_collection_noob_vpred-1.0-v6-edm2-pass.safetensors

AIO-noob-vpred1.0_v6-edm2

MIO-anima-b1_v5

MIO-anima-p3_v4

MIO-anima-p2_v3.5

MIO-anima-p2_v3

MIO-anima-p1_v2

MIO-anima-p1_v1

MIO-nb-vp1.0_v3.22-d-edm2

MIO-nb-vp1.0_v3.221-edm2

BIO-nb-eps0.5_v2.217-edm2

BIO-rw-vp0.8_v2.217-edm2

BIO-nb-vp1.0_v2.217-edm2

BIO-rw-vp0.7_v1.337-edm2

BIO-nb-vp1.0_v1.337-edm2

AIO-noob-vpred1.0_v5

AIO-noob-vpred-v29_v5

AIO-noob-eps1.1_v5

AIO-rouwei-0.6.1_v5

AIO-noob-vpred1.0_v4.02

AIO-rouwei-0.6.1_v4.01

AIO-noob-vpred0.7.5_v3.2

AIO-rouwei-0.6.1_v3.1

AIO-noob-eps1.1_v3.1

AIO-noob-vpred0.6_v3

AIO-noob-vpred0.6_v2

AIO-rouwei0.6-vpred_v2

youmuanon-noobvpred0.1_v2

AllinOne-noob-vpred0.5_v1

all-in-one-pony_v1

all-in-one-noob-eps1.0_v1

mm_type_one_noob_vpred_v1

flutecocktail_noob_vpred

flutecocktail_noob_eps_v2

dj_sloppa_noob_vpred_v2

dj_sloppa_illust_v2

hstoigaf_illust_v1

hstoigaf_pony_v3

ymbstssh_pony_v2

idkwtsibili_pony_v1

AI styles dump (Illustrious/RouWei/Noob)

All art styles list: https://files.catbox.moe/wwv3wn.txt

Vpred_v6

Version names includes the base model it was trained from, use appropriate version for each model. Rouwei version wont work well with noob, the opposite is also true. Old noob versions would be too weak on a fresh noob checkpoints also, eps and vpred should also be used with their dedicated versions. Don't forget to check version descriptions for more specific info and list of supported style tags.Anima v4 info: Update for recent <a target="_blank" rel="ugc" href="https://civitai.com/models/2458426?modelVersionId=2836417">anima preview 3</a> version. <a target="_blank" rel="ugc" href="https://files.catbox.moe/p28icg.txt">List of styles</a> is same.Anima v3.5 info: Same version as anima-p2_v3, but trained of full range of blocks. Should™ just work better overall. Out of dataset test <a target="_blank" rel="ugc" href="https://safe.manu.moe/O0K1Rjl0.png">still fine</a>. <a target="_blank" rel="ugc" href="https://files.catbox.moe/pmd33i.txt">List of styles</a> the same, <a target="_blank" rel="ugc" href="https://safe.manu.moe/cMN8iazQ.png">grid</a>Anima v3 info: V3 is version trained from and for <a target="_blank" rel="ugc" href="https://civitai.com/models/2458426/anima-official">anima preview 0.2</a>. Still <a target="_blank" rel="ugc" href="https://safe.manu.moe/VaqCDLua.png">won't affect</a> data outside of dataset so much. <a target="_blank" rel="ugc" href="https://files.catbox.moe/pmd33i.txt">Style list </a>is same with v2, <a target="_blank" rel="ugc" href="https://safe.manu.moe/EtCsPs15.png">grid with styles</a>.Anima v2 info: A bit late, since 0.2 preview is already out, but whatever. It was trained from <a target="_blank" rel="ugc" href="https://huggingface.co/circlestone-labs/Anima/blob/main/split_files/diffusion_models/anima-preview.safetensors">0.1 version of preview model</a>. Catastrophic forgetting was addressed and improved, at least it's <a target="_blank" rel="ugc" href="https://files.catbox.moe/196jew.png">not so disastrous </a>now. Mixing between styles was also a little bit improved from empirical tests. <a target="_blank" rel="ugc" href="https://files.catbox.moe/pmd33i.txt">List of all styles</a> and <a target="_blank" rel="ugc" href="https://files.catbox.moe/att98h.png">grid</a>. It would not work as well with 0.2 preview.Anima v1 info: <a target="_blank" rel="ugc" href="https://huggingface.co/circlestone-labs/Anima">Anima</a> version of lora comes with limited dataset. <a target="_blank" rel="ugc" href="https://files.catbox.moe/mp72qa.txt">List of styles</a> that comes with it. More like a test version. Model is in early stage and too incoherent at something above 1mp. If you decide to upscale, you would need to use tiled methods, unless you're okay with artifacts. Style tags should be invoked with @ before them. Mixing somewhat works, but not how it was with default xl weighting, rather like compel mode.MIO - mix in one versions with mix of ai styles and some real artists in dataset.BIO - best in one versions, containing only artificial images in dataset. 90% filled with naiv3 or styles from local models with very distinctive look only.

Files with SHA256: b0719ececc00649ad9f103ebe05edb59261271b7220c752586b9bb05966daea8