I'm working on a small AI Discord Community you can join here: <a target="_blank" rel="ugc" href="https://discord.gg/ehhMrD4PQT">https://discord.gg/ehhMrD4PQT</a><hr />My Very First VAE Merge, which is found in one of my models on my old account. Feel free to test and/or use them. V3 is what I originally wanted the VAE to be, a VAE that adds subtle contrast/saturation/brightness.This will not fix an already overfitted/overbaked image as it's a VAE. Also the VAEs may effect images a bit too much for you personally, especially if you're doing hires/upscale/etc with IMG2IMG, but if you like the those images go for it. Works best for TXT2IMG. I personally like the VAEs for TXT2IMG mainly, and IM2IMG if the image is washed.Also VAE has a tendency to fix some minor background stuff sometimes, due to it properly doing that artifact/noise in that spot. Finetuned VAE basically has slightly different lighting contrast is pretty similar. Finetune V2.0 settings from the script vibe-coded by Claude Sonnet 4.5 that I used:<pre><code>- GPU: RTX 3060 12GB
- VAE Used: The Base Crystal VAE Merge on this page
- Dataset Total: 251 images (Overkill but Good for Variety)
- Resolution: 1024x1024
- Batch size: 2
- Epochs: 5 - Ended up choosing epoch 1 on testing, due to PC shutting off at epoch 3/5)
- Learning rate: 5e-6 (0.000005)
- Training mode: Decoder-only
- Optimizer: AdamW
- Loss: MSE reconstruction</code></pre>Note: Still doesn't do well in hires only for dark lighting images.All Finetune V2.5 settings:<pre><code>- GPU: RTX 3060 12GB
- VAE Used: The Base Crystal VAE Merge on this page
- Dataset Total: 55 images
- Resolution: 1024x1024
- Batch size: 1
- Epochs: 1
- Learning rate: 1e-5 (0.00001)
- Training mode: Decoder-only
- Optimizer: AdamW</code></pre>Note: Was gonna make a SD1.5 version but decided not to since they'd be extremely similar. Re-Categorized due to tool due to me wondering what the Google AI overview thought was a asset. This is what the AI Overview thought is a asset: <img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/99a2abee-85b2-4e91-9db2-a8bac201f8bb/width=525/99a2abee-85b2-4e91-9db2-a8bac201f8bb.jpeg" />This is what the AI Overview thought is a tool:<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/1295fbd3-a19d-4bef-b3eb-15889c94d2a9/width=525/1295fbd3-a19d-4bef-b3eb-15889c94d2a9.jpeg" />

Crystal - VAE [SDXL/Illustrious]

First attempt at finetuning a VAE, and first time finetuning it with MSE reconstruction loss. Finetuned with 251 images I generated with the first file which is the VAE merge. This has slightly lighter saturation/lighting but still darker than base SDXL.

Files with SHA256: 1a4f46d1397dc9d136aec19e5aa333d7998a833540822d990b23e8805e9d9312