Type | |
Stats | 878 |
Reviews | (140) |
Published | Oct 4, 2023 |
Base Model | |
Usage Tips | Clip Skip: 1 |
Hash | AutoV2 D11F66D31A |
LomoXL
Similar to LomoStyle for SD1.5; LomoXL is trained on a dataset consisting of images taken with analog tech.
Features
High-resolution images: Trained on 1024x1024 images (default for XL) manually captioned and cropped for optimal outputs.
Photorealism: While still lacking (compared to SD1.5), everything that went into this model was intended to create more authentic photorealistic images. This includes data selection, processing, captioning, and training parameters.
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.
Limitations
LomoXL unfortunately, inherits some of the limitations from the original SDXL model. While improvements to photorealism were made in LomoXL, it still does not compare to what we get with SD1.5 models. Notably, skin texture and nudity. NSFW generations are possible but it's not ideal. To address this, I recommend using additional networks (such as LoRA's and Textual Inversions) as a temporary fix until SDXL base models have been trained enough to overcome this hurdle.
Usage
VAE - https://huggingface.co/madebyollin/sdxl-vae-fp16-fix
+ Prompt: Natural language, with the addition of two special tags:
lomostyle
, a prefix you can put at the start of your prompt.in lomostyle
, a suffix that can be added at the end of your prompt.
Note: These tokens are not required.
For more information regarding other special tokens (tags) that can be used with LomoXL, please refer to Lomostyle.
- Prompt: This one I'm not sure about yet. I mostly used the following negative prompt:
kid, child, 3D render, cartoon, watermark, text, signature, distorted, bad, exaggerated limbs, fake
Although, feel free to experiment with other negative tokens. Generally, less is more with diffusion models.
Questions/Feedback/Updates?
Visit my thread on the Unstable Diffusion Discord
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.
Checkout my other models
SDXL
Boomer Art Model - https://civitai.com/models/163139/boomer-art-model-bam
SD1.5
Doomer Boomer - https://civitai.com/models/118247/doomer-boomer
Lomostyle - https://civitai.com/models/109923/lomostyle
Another Damn Art Model (ADAM) - https://civitai.com/models/104898/another-damn-art-model-adam
Based Model - https://civitai.com/models/83991?modelVersionId=89262
Electric Eden - https://civitai.com/models/64355/electric-eden
Cine Diffusion - https://civitai.com/models/50000/cine-diffusion
ProjectAIO - https://civitai.com/models/18428/project-aio
WonderMix - https://civitai.com/models/15666/wondermix
Refined - https://civitai.com/models/8392/refined
Experience - https://civitai.com/models/5952/experience
Elegance - https://civitai.com/models/5564/elegance
Clarity - https://civitai.com/models/5062/clarity
VisionGen - Realism Reborn -https://civitai.com/models/4834/visiongen-realism
LoRA
Pant Pull Down - https://civitai.com/models/11126/pant-pull-down-lora