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!
NightVision XL 0.7.4.3 Release Notes
With this version of NightVision XL, you should notice more natural and normal looking bodies, a bit more facial variety, and much more balanced color output vs 0.7.0.2. Bodies also look better naked, with less noticeable shoulder bone caps on very thin subjects, more natural ribs on less thin subjects, and even more natural features on skin like moles, blemishes and stretch marks, and old people actually look old. Something I've noticed anecdotally but haven't tested in detail is that blood on skin (like a bloody lip or a cut for example) looks much more natural and realistic, and water looks more wet and less like painted on glue, however YMMV.
Bodies should now look much better proportioned and much less waifish and stretched out, especially in tall AR images. To be clear, while it's not 100% fixed, I've put a lot of work into trying to fix the stretchy giraffe necks, weirdly long legs and freaky torsos that all of the community models have inherited from base. While I haven't banished it completely, it seems body balance is MUCH better. Further, while the default output of this model continues to be photorealism biased, the model is much less rigid now, and you should be able to achieve other styles such as line art or anime (and more) with just a bit of style prompting.
TLDR Improvements
body shapes are much more natural, even in non-square ARs
more natural looking skin
less rigid, can produce other styles than photoreal much easier now
less close up portrait bias
Output is less contrasty than 0.7.0.2 and colors are more balanced than 0.6.8.1
09/11/23 Changelog
Backmerges into 0.6.8.1 and 0.6.5.0, and differential merges with (internal only version) 0.7.3.3 which was a WIP model. Added 2 new community loras and an internal fixer lora.
New Community LORAs added
polyhedron_all_sdxl
NaturalBody
New Internal LORA Added
nf_v3-test
Internal LORA Rebalance
Nightshift
Files
nightvisionxl_v0743ReleaseBakedvae.safetensors