Model is taken off-site until V1.0

Esmaysia

Put slight NAI in here like 7% then simple merged in a Illu V2.0 Stable + LoRA mix I did, which some of that 7% of NAI Eps is probably gone but the merge version is how I want it to be. Just hope to fix this to be by default not be a mix of ages without specific tags, on base generation eventually with LoRA training now for future versions.

esmaysia_v05.safetensors

V0.5

V0.98

V0.9

V0.8

V0.3

<h2 id="disclaimer:-this-model-is-pretty-wild-so-don't-expect-perfect-generations.-newer-versions-will-probably-fix-the-issues-but-over-time.-future-versions-i-will-have-1k-image-datasets-of-the-images-i-get-without-a-lora-ontop-inside-of-a-lora-that-will-be-trained-on-the-current-model-version-and-put-onto-the-model.-also-every-version-after-v1-won't-be-purely-illustrious-v2.0">Disclaimer: This model is pretty wild, so don't expect perfect generations. Newer versions will probably fix the issues but over time. Future versions I will have 1K image datasets of the images I get without a LoRA ontop inside of a LoRA that will be trained on the current model version and put onto the model. Also every version after V1 won't be purely Illustrious V2.0</h2>The only two checkpoint models put into this are both Illustrious V2.0. Rest of the models ontop are LoRAs.<h1 id="recommended-settings-v2.0:">Recommended Settings V2.0:</h1>Steps: 20+ CFG: 3+ Sampler/Scheduler: Whatever works best Must have Pos Tag:<pre><code>aged_up</code></pre>Must have Neg Tags:<pre><code>loli, shota, child, young, aged_down</code></pre>Note: Only because this is Illustrious V2.0 mainly with LoRAs that only effect style mainly, and if you've seen the Danbooru tags you'd know why.<h1 id="recommended-settings-v1:">Recommended Settings V1:</h1>Steps: 20+ CFG: 4+ Sampler/Scheduler: Whatever works best Must have Pos Tag:<pre><code>aged_up</code></pre>Must have Neg Tags:<pre><code>loli, shota, child, young, aged_down</code></pre>Note: Only because this is Illustrious V2.0 mainly with LoRAs that only effect style mainly, and if you've seen the Danbooru tags you'd know why.

Esmaysia - [ILLU V2]

&lt;p&gt;Put slight NAI in here like 7% then simple merged in a Illu V2.0 Stable + LoRA mix I did, which some of that 7% of NAI Eps is probably gone but the merge version is how I want it to be.&lt;br /&gt;&lt;br /&gt;Just hope to fix this to be by default not be a mix of ages without specific tags, on base generation eventually with LoRA training now for future versions.&lt;/p&gt;

Files with SHA256: 2d3787362661d513d98b211e9dbf781bb192596cf8acebf51b3dbff615943f6d