BAM!
1970s - 1990s Fantasy / Sci-fi illustrations for SDXL.
changelog
8/5/24 v2.0_lightning_8step:
Uploaded 8step Lightning version of BAM v2.0 by request (See About this version for more info)
Features
High-resolution images: Trained on 1024x1024 images (default for XL).
Various art-styles: Multiple artists/illustrators from the 1970s - 1990s. A list of artists tags can be found bellow.
Easy to prompt: Stylization of simple prompts can be achieved with as little as one special token (trigger) appended to the end of your prompt.
True to source: Special attention was payed to insure that the artstyle(s) being generated are as close to the individuals artstyle as possible.
Flexible: Can be easily merged with other SDXL checkpoints / LoRAs for more expansive generations.
Full parameter fine-tune: This is a full parameter fine-tune of the original SDXL base 1.0 model. Both the U-Net and both text-encoders were tuned during training.
General Information:
Base model - SDXL v1.0
VAE - SDXL-vae-fp16-fix
Type - Full-parameter fine-tune, including text-encoders, bfloat16 (bf16).
Style - Painting, Drawling, Illustration, digital painting
Usage
Note: BAM_V2 includes hundreds of artist tags and no longer requires the special token. The model description will be updated to reflect these changes (and more) soon.
Special Tokens:
BAStyle, a general prefix that is not strictly required but can help maintain the models style.Place at beginning of your prompt.
Artist Tags: Appending these tags to the end of your prompt will guide the model to generate an output in the style of the artist that's being tagged.
by Boris Vallejo
by Brom
by Caza
by Chris Foss
by Clyde Caldwell
by Col Price
by Dave Dorman
by Frank Frazetta
sketches by Frank Frazetta
by Kelly Freas
by John Berkey
by Gimenez
by Ken Kelly
modern art by Kirsi Salonen
modern art by Kyu Yong Eom
by Luis Royo
by Michael Whelan
by Mike Hoffman
by Milo Manara
by Moebius
by Philippe Druillet
by Sanjulian
by Ted Nasmith
With more to come in the future!
Random Style Generation (RSG) Tag: The following token (trigger) is a made-up artist that generates an image in the style of a random artist. It's not perfect but can yield interesting results
by Gladius
Wildcard: A wildcard that includes the various artists can be found here.
Limitations
BAM! inherits some (not all) of the limitations from the original SDXL v1.0 model. Specific limitations:
Bias: This model is bias towards paintings, drawings, and illustrations from the 1970s - 1980s.
NSFW: NSFW generations, while possible, are limited. Improved when run alongside a LoRA or merged with another SDXL checkpoint.
Buy me a coffee ❤
https://ko-fi.com/ndimensional
All donations will be used to fund the creation of new Stable Diffusion fine-tunes and open-source AI tools.
Future updates are already in the works to bring SDXL up to — and beyond SD1.5 standards. If you want to contribute, DM me at the discord thread linked above. My goal is to create fine-tunes on unique styles or concepts SDXL struggles with, expanding the pool of models for merging.
Checkout my other models
SDXL
SD1.5
Doomer Boomer - https://civarchive.com/models/118247/doomer-boomer
Lomostyle - https://civarchive.com/models/109923/lomostyle
Another Damn Art Model (ADAM) - https://civarchive.com/models/104898/another-damn-art-model-adam
Based Model - https://civarchive.com/models/83991?modelVersionId=89262
Electric Eden - https://civarchive.com/models/64355/electric-eden
Cine Diffusion - https://civarchive.com/models/50000/cine-diffusion
ProjectAIO - https://civarchive.com/models/18428/project-aio
WonderMix - https://civarchive.com/models/15666/wondermix
Experience - https://civarchive.com/models/5952/experience
Elegance - https://civarchive.com/models/5564/elegance
VisionGen - Realism Reborn -https://civarchive.com/models/4834/visiongen-realism
LoRA
Pant Pull Down - https://civarchive.com/models/11126/pant-pull-down-lora
Run BAM on Tensor Art: https://tensor.art/models/740739326046066989?source_id=nj2-r1nnnUO3ovUiaHf19Bgn
Description
Initial Release
FAQ
Comments (11)
Boomer Art LOL. Gotta love the oldies man!
I have such an appreciation for the fact that people (you included) keep venturing off the beaten trail and making things with cool and interesting styles. The 70s Sci-Fi vibe isn't my thing, but I can tell from the sample images that you hit the nail on the head perfectly. Kudos.
I loved Doomer Boomer so I look forward to fun with this one!
Love the idea of this model, as I grew up with "boomer art". My dad was into it, and of course a lot of these artists did work for DnD and other things. But I have not been able to get anything good out of this model yet. It's been a mess. It's definitely trying to do the styles, but the renders are coming out deformed or ugly etc. I'll play around with it more, but early impressions are very disappointing for me.
For ugly faces, I would recommend using ADetailer. Not all, but many of the artists from that era which are featured in the dataset didn't draw/paint the most attractive faces.
Deformed outputs shouldn't be happening though. Do you mind sharing your generation settings and VAE?
This is the only model that works for me when I play with older artists and art styles (like merging Jean Delville with Gustave Moreau). It also isn't afraid of (artistic!) full frontal male nudes.
I would love a new version of this. I get very muddled and incomplete renders with this.
The new hyper lora appears to improve this model substantially for whatever reason and I'm all about it lol
hyper lora?
As an autist of culture who has witnessed many AutismMix abominations, I'm both intrigued and terrified by the implications of combining this checkpoint with a "hyper" LoRA.
@Mister_Kaos It's a LoRA that uses Distillation to compress the inference steps down to 1 - 8 steps.
Useful for speedy generation, and I imagine with the original version of BAM. It probably increased the aesthetic quality.
For the latest version (BAM v2), I wouldn't recommend using it with the Hyper LoRA as it's not needed.
Unless the goal is speedy inference.
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.