UPDATE: v2-pynoise released, read the Version changes/notesLORA based on the <a target="_blank" rel="ugc" href="https://www.crosslabs.org//blog/diffusion-with-offset-noise">Noise Offset post</a> for better contrast and darker images.Weighting depends often on Sampler, kept it in the low-middle range (Maybe i will put up a stronger one).Custom weighting is needed sometimes.Works better if u use good keywords like: <code>dark studio, rim lighting, two tone lighting, dimly lit, low key</code> etc.Didn't like the color saturation and image compositions from the <a target="_blank" rel="ugc" href="https://civarchive.com/models/8765/theovercomer8s-contrast-fix-sd15sd21-768">theovercomer8sContrastFix_sd15</a> so i made this one.UPDATE: v2 is slightly stronger in the whole compositionUpdate 2: added safetensor fileQuick Comparsion<img src="https://imagecache.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/af07d184-3f37-40bb-526e-a6cf9d41bf00/width=525/af07d184-3f37-40bb-526e-a6cf9d41bf00" />

epi_noiseoffset

epi_noiseoffset.pt

v2-pynoise

UPDATE: v2-pynoise released, read the Version changes/notesLORA based on the <a target="_blank" rel="ugc" href="https://www.crosslabs.org//blog/diffusion-with-offset-noise">Noise Offset post</a> for better contrast and darker images.Weighting depends often on Sampler, kept it in the low-middle range (Maybe i will put up a stronger one).Custom weighting is needed sometimes.Works better if u use good keywords like: dark studio, rim lighting, two tone lighting, dimly lit, low key etc.Didn't like the color saturation and image compositions from the <a target="_blank" rel="ugc" href="https://civitai.com/models/8765/theovercomer8s-contrast-fix-sd15sd21-768">theovercomer8sContrastFix_sd15</a> so i made this one.UPDATE: v2 is slightly stronger in the whole compositionUpdate 2: added safetensor fileQuick Comparsion

Files with SHA256: ec8d4b39b5f74ed12171173d01fa0955f98b9c5ea9729f3d530dbd456369722f