We are continuing with the most open-source Stable Diffusion fine-tuning series. This time we decided to address the issues of the Vodka v3 model using custom LoRAs, and the results look interesting! Check out the full post here <a target="_blank" rel="ugc" href="https://followfoxai.substack.com/p/getting-started-with-loras-vodka">https://followfoxai.substack.com/p/getting-started-with-loras-vodka</a> LoRA trained on realistic portrait shots on top of <a target="_blank" rel="ugc" href="https://civarchive.com/models/61086/vodka-by-followfoxai">Vodka V3</a>. Adds photorealism to all kinds of generations when used in combination with the Vodka model. Overall observations so far:<ul><li>The model can generate very high-quality photorealistic images</li><li>It also introduced many issues; in some generations, fingers are now extra deformed, and we observe some forgetting of subjects they knew before.</li><li>The model's diversity decreased, generating more similar images within the same prompt.</li></ul>

Files with SHA256: eb1e77419bb57d3971b6121b85903068de323f5141f2d0291786c15c8b9976fc