<h1 id="heading-7">BeyondImaginationXL_V0_005_Fix</h1>Fixed the issue with model metadata, preventing it from loading in some UIs. Thahks to <a target="_blank" rel="ugc" href="https://civarchive.com/user/S1LV3RC01N">S1LV3RC01N</a> for help!<h1 id="heading-7">BeyondImaginationXL_V0_005</h1>Update: I changed the terms of license. It is now OK to use the model on other generation services. Please, don't forget about crediting me.Here is the new version of the model. Major update is still coming, but I decided to publish this checkpoint, which has two improvements:<ul><li>Higher details in images,</li></ul><ol><li><s>Fixed the issue with metadata</s> (actually, no, will have to do some further research)</li></ol>Recommended settings are the same as before.<h1 id="heading-7">BeyondImaginationXL_V0_003</h1>New version is coming soon! Stay tuned!BeyondImaginationXL is my first attempt to train an SDXL checkpoint. Sure, it's a rookie, but hey, even rockstars had to start somewhere! This checkpoint is like the rebellious offspring of a commercial model I've been cooking up for a few months. It's got attitude, focusing on keeping it real, rocking various visual vibes, finding that sweet spot between work-appropriate and, well, more adventurous content.<h2 id="heading-434">Recommended settings are:</h2>Sampler: DPM 2m or 3mScheduler: karrasSteps: 30 - 60CFG: 3-7Refiner: Not neededVAE: Baked inThis is a starting point, so feel free to try it, comment, make suggestions, etc. I will be developing it further. The more you try it and comment, the better new versions get!<h2 id="heading-2">Further plans:</h2>Looking at the results of my tests here is what I am planning to do:<ul><li>improve people (both SFW and NSFW), hands and feet</li><li>add interior and landscape design styles. That's a part of a commercial project I'm a founder of and future public releases of the model will get some (but not all😉) cool elements from the commercial model</li><li>enhance the level of control over the composition of an image</li><li>fix the issue with metadata - I've got reports that the model is not properly recognized in some UIs (I use ComfyUI and my own pipeline based on comfy - it works like a charm)</li><li>I will not be working on SDXL Turbo models due to inferior quality and licensing policy</li><li>what else? - please write in the comments section</li></ul><h2 id="heading-435">About me:</h2>I am a data scientist and I am a founder of startups related to Computer Vision and Generative AI. Please feel free to contact me if you have any commercial ideas to discuss.

BeyondImaginationXL

Slightly improved detailes.Hopefully, fixed the bug with lacking metadata (please, let me know if the model is recognised in webui 1.6, 1.7dev, and webui-forge, where there was an issue in v003)

Files with SHA256: beba1d4baa07135c75d565f53e4f457f18c40b5f6aac516909be5844175106b2