Like the work I do and want to say thanks? Buy me a coffee or Support me on Patreon for exclusive early access to my models and more!
NightVisionXL started as a lightly trained, photography focused SDXL model that specialized in photographic output. Over the past few months, NightVision has received dozens of trainings and tunings chasing the dragon that is pleasing aesthetic output. With the release of version 8.X, I feel like I'm much closer to my goal of effortless beautiful output that is aesthetically pleasing without requiring confusing negatives or comma separated nonsense.
NightVisionXL speaks natural language. Prompt it like you would describe a scene to a human being, and you'll be surprised by how well it can understand and comprehend your prompts.
I'm trying something new with V8 of NightVision, and I hope the results show in the output. I continue to scrape beautiful imagery that I think will train well, and this particular update is no exception with hundreds of beautiful license free AI images that I've sourced from MJ, Dalle3, Civit, Playground and my own outputs. On top of that, I'm also utilizing HF datasets for license free photography and the LAION-POP dataset, filtered to remove low quality images prior to training. Captioning is done using my own Spicy Burrito captioning tool (available to my Patreon subscribers on discord!) that creates incredibly verbose and effective captions that are essential for good coherent output.
On a final note, I've had multiple requests to "turbo-ize" this model. I have no plans to mix turbo into NightVision, as the licensing on NightVision is nice and open right now with the SDXL licensing, and I'd like to keep it that way. NightVision isn't fast, but I promise you the longer gen times are worth the wait!
This is NightVision XL, a lightly trained base SDXL model that is then further refined with community LORAs to get it to where it is now. NightVision XL has been refined and biased to produce touched-up photorealistic portrait output that is ready-stylized for Social media posting! NightVision XL has nice coherency and is avoiding some of the weird body issues and biases that are starting to plague some of the other photorealistic models. Further, NightVision XL produces rich deep blacks and great evening/night time scenes. It can also produce ridiculously bright output as well!
NightVision XL is capable of both SFW and NSFW output. As with all of my other models, tools and embeddings, NightVision XL is easy to use, preferring simple prompts and letting the model do the heavy lifting for scene building.
NOTE - This version includes a baked VAE, no need to download or use the "suggested" external VAE.
WARNING - DO NOT USE SDXL REFINER WITH NIGHTVISION XL
The SDXL refiner is incompatible and you will have reduced quality output if you try to use the base model refiner with NightVision XL.
Follow me here by clicking the heart ❤️ and liking the model 👍, and you will be notified of any future versions I release. I also need your help with feedback, please please please post your images and your honest feedback below, I will use your feedback and your output to help guide future revisions!
Patreon coming soon!
NightVisionXL v0.7.9.1 Release Notes
With all the hype around the turbo models lately, it may seem a bit silly to be releasing a "plain jane" model, but I think you will find that NV791 is absolutely worth it. NightVisionXL v0.7.9.1 is my most coherent version yet. It is very good with long, complex prompts and mostly gets hands right now, including holding objects and getting the fingers in the right place on the other side of an object. o_O face is mostly fixed now, though it can still come back in the XL 'non-standard' aspect ratios. NV791 is VERY responsive to photography keywords, and you'll find its very easy to get photorealistic analog style photography with beautiful film grain, natural lighting and subjects that are responsive to pose and emotion keywords. I've also added a large amount of widescreen training, so NV791 handles 16:9 and 21:9 ultrawide output very well, especially wildlife and nature photography styles.
Finally, NightVision is very good at inpainting its own output (YMMV inpainting other model output). Whether you're using adetailer, face editor, face detailer or one of the other "auto-inpainters" it works decently well with those, but where it really shines is in direct inpainting with a mask. If you have no clue what I'm talking about, or you are struggling with inpainting, come join my discord community SCG-Playground where we have many expert artists and developers who are happy to share their secrets and help you hone your stable diffusion skills.
Changelog 12/2/23
Multiple fine tunings focusing on analog photography style (NV's specialty)
Added another training on many widescreen (16:9, 21:9, etc.) ratio images focusing on photography and cinematic styles
Known Issues
Hands are much better, but still not completely reliable yet
Male Genitalia
distant faces, eyes and teeth can still be problematic, tho easy enough to inpaint
Still can get wacky on very complex busy scenes, like a group of people playing volleyball, or an orchestra of people playing instruments for example
Files
nightvisionxl_v0791Bakedvae.safetensors