<hr />A heavy finetune with nearly 500k samples on strictly a smaller liminal dataset to refine BeatriXL into an artistic and tasteful liminal image generating monster.This tool is far beyond simply generating depictions of interesting areas or sectors of an image; you have advanced control of your world in many shapes and forms. Albeit stubborn at times, this beast can be tamed; as it's compatible with most loras if you set the lora to low strength from most SDXL models.You won't just get regurgitated art from a list with this one. It's generating unique cross-entropic contaminated sectors more often than not; and the outcomes reflect high complexity differences - beautiful differences if you want them to be.Euler or Euler A usually works, but I advise using the RES4LYF sampler pack to really make this model's showcase powerful.<a target="_blank" rel="ugc" href="https://huggingface.co/AbstractPhil/Liminal-Full/tree/main/Beatrix-LORA">https://huggingface.co/AbstractPhil/Liminal-Full/tree/main/Beatrix-LORA</a> <a target="_blank" rel="ugc" href="https://huggingface.co/AbstractPhil/Liminal-Full/tree/main/Beatrix-LORA-V2">https://huggingface.co/AbstractPhil/Liminal-Full/tree/main/Beatrix-LORA-V2</a>You can pick the mix out yourself if you want. It's a few loras; where one was merged into the core and then the final lora epochs trained from that.<pre><code>liminal, no humans, stuff</code></pre>The dataset was trained with a multitude of timesteps for a long time with multiple different datasets. Careful though, BeatriXL is still fairly unstable - the refinement helps a whole lot, but if you aren't careful you'll see things you don't want to see. However, this version is a lot more SFW by default than the others - meaning it's more likely to default to a SFW topic than a NSFW topic, but there are no guarantees.If you use humans you're probably going to see something you don't want to see, so be careful with those.Roughly 5k different images; so not many. However, those 5k images were issued a series of different captions from plain English to full description.Joycaption 2 + siglip, GPT4o, LLAMA2 LLAVA B-OMEGA + Siglip500, CLIP_L interrogation, CLIP_G interrogation, and pure raw tags from the WD14 systems.The curriculum training went really well.<hr /><h3 id="for-the-fp8_e4m3fn-higmn31ax">For the fp8_e4m3fn</h3><ul><li>if your ComfyUI gives you any major errors place these in your gpu launch bat;</li></ul><pre><code>--fp8_e4m3fn-unet --fp8_e4m3fn-text-enc --fp32-vae</code></pre>It's not a true fp8 utilization; as ComfyUI did not autocast to fp8, but instead cast to bf16 manually for me.<pre><code>model weight dtype torch.float8_e4m3fn, manual cast: torch.float16</code></pre>Yet I definitely launched with float8_e4m3fn as the unet. I really don't know what to say about that, other than it's likely not supported by a 4090 so it'll only run on higher-end cards.The text encoders run just fine on fp8.<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/5bf16cd5-050d-41cf-b901-8979d32919d5/width=525/5bf16cd5-050d-41cf-b901-8979d32919d5.jpeg" />Likely in this code here, as it's running "should_use_bf16", which probably forces it into bf16 mode. Until I have a proper workaround it'll have to be upscaled to bf16, but at least the size is tiny.

BeatriXL Huge Liminal V1 SDXL [fp8/bf16/fp32]

If ComfyUI gives you any major errors; run it with these as your launch commands.--bf16-unet --bf16-text-enc --fp32-vae

Files with SHA256: beb40f9af1cf7396400e12211d02e0750601f8c435d1f7fc78db923cb7783ccd