<h2 id="heading-304">Disclaimer</h2>v3 showcase images are done with full Dreambooth, but model provided is an extract. Some inconsistencies with them are expected, but not major.XL version - <a target="_blank" rel="ugc" href="https://civarchive.com/models/276075">https://civarchive.com/models/276075</a><hr />Kofi - <a target="_blank" rel="ugc" href="https://ko-fi.com/anzhc">https://ko-fi.com/anzhc</a><hr />And i guess im opening my request form - <a target="_blank" rel="ugc" href="https://forms.gle/8bhruFiecpy5szNf6">https://forms.gle/8bhruFiecpy5szNf6</a><hr />v3.1 watermark fix: This version improvement is cleaned up dataset. Some bad images were removed, 209 watermark apparitions were erased. Training was also done more finely.v3: Training done as a Dreambooth, and then extracted to rank 128 locon.v2.5: more images that are meant for <code>aesthetic</code> purposes(tagged accordingly). Training changed.v2 update: 682 image training, but only 10 epochs, and on other base model. Should work quite good.Full version update: Training on 682 images, vs 200 in Lite version. More dreamy, more abstract, better eyes, for whatever reason. But composition is less, let's say, tangible, in a way. But that's the point of this model i guess :D General instruction: try some bullshit, random words, something dramatic, use wildcards. It will react differently. By default style is not very interesting(unless it is), it needs some prompting to get going.<h2 id="heading-12">--FOOTER--</h2>Model provided strictly for non-commercial use.Reprint(repost, reupload to other sites) is prohibited.

Abstract Dreamwave

200 image dataset. Full version will have 682.

gpts4 lite dreamwave_278580.safetensors

GPTS4 Lite

Files with SHA256: c8d375e4dca0474356904a4f718418bc00fdfda3758ba49237d22ea115744ef3