This model is a merge between a private model I haven't released (a lot of loras mixed in, mostly scenery focused but all of the loras that were merged into the private model is all created by me.) and <a target="_blank" rel="ugc" href="https://civarchive.com/models/545628?modelVersionId=778308">Ether </a> This isn't going to be the final version, I will be making updates to slowly turn the outputs to what I personally prefer. I make a lot of style loras so the final will definitely be way different but I still want to keep the quality. <a target="_blank" rel="ugc" href="https://civarchive.com/models/545628?modelVersionId=778308">Ether PDXL</a> was created by gamerdan69 Relhv1: <a target="_blank" rel="ugc" href="https://civarchive.com/models/545628?modelVersionId=778308">Ether PDXL - A3</a> A model that I also haven't published on Civitai. Multiple scenery loras that I made that hasn't been published on Civitai. Relhv2 added: <a target="_blank" rel="ugc" href="https://civarchive.com/models/364971/shiratakimix-xl">ShiratakiMix XL</a> 1 Lora that was trained on images from <a target="_blank" rel="ugc" href="https://civarchive.com/models/693181?modelVersionId=791028">Fn-Mix Pony XL</a> + ai images found 2nd Style Lora was also trained on different type of style of Ai images Relhv3 added: A little bit of Relhv1 <a target="_blank" rel="ugc" href="https://civarchive.com/models/269232/aam-xl-anime-mix">AAM XL (Anime Mix)</a> 2 loras were merged into model that I have created. Relhv4 added: A little bit of Relhv3 <a target="_blank" rel="ugc" href="https://civarchive.com/models/591749?modelVersionId=863526">PixivPonyEpitaMix</a> <a target="_blank" rel="ugc" href="https://civarchive.com/models/260267/animagine-xl-v31">Animagine XL V3.1</a> <a target="_blank" rel="ugc" href="https://civarchive.com/models/401963/aesthetic-quality-modifiers-absurdres">Aesthetic Quality Modifiers - Absurdres</a> <a target="_blank" rel="ugc" href="https://civarchive.com/models/402544/omega-pony-xl-anime-style">Omega Pony XL anime style</a> <a target="_blank" rel="ugc" href="https://civarchive.com/models/481765/ai">AIイラストおじさん</a> <a target="_blank" rel="ugc" href="https://civarchive.com/models/402462/detail-slider-lora-or-ponyxl-sdxl">Detail Slider LoRA | PonyXL SDXL</a> Two loras that I have created that hasn't been uploaded to civitai, mostly trained from AI images and backgrounds. I cherry pick the images so I doubt there will be any issues with hands. What has changed within Relhv4: Brighter images, more anime type of style which I prefer personally. There is no "better" model within Relh, it is personally what I enjoy. You can checkout each model version and choose what you like the most. Please share your creations, would love to see your creations.

RELH | Checkpoint

RelhV1 Models/checkpoints in the merging process: Used <a target="_blank" rel="ugc" href="https://github.com/bbc-mc/sdweb-merge-block-weighted-gui">MBW</a> MODEL A: <a target="_blank" rel="ugc" href="https://civitai.com/models/674674/takio">Takio</a> (with a lot of loras that I merged before hand)<ul><li>MODEL C: Ether PDXL<pre><code>1,1,1,1,1,1,1,1,1,1,1,1,1,1,0.25,0.25,0.25,0.25,0.25,0.25,0,0,0,0,0</code></pre>Output Model: Relhv1</li></ul>

Files with SHA256: 2ce6a9aec068c5edd50dfa2da9cb7c190e52764228eaf50df24216f9cc96dfd5