[SD 1.5][Checkpoint]Lomo Diffusion lomo-1.0
<p>This is a dreambooth model trained on a diverse set of stylized photographs.</p><p>Use the activation token <strong>lomo style</strong> in your prompt (I recommend at the start)</p><p>This model is inspired by the Lomography movement, which embraces the imperfections and style of old LOMO cameras. The model excels at producing bright saturated colors as well as a variety of film artifacts that add to the illusion of a real photograph. When using most models, I typically use <strong>blur haze</strong> in my negative prompt. I encourage you to experiment and see what works well for you.</p><p>Trained from 1.5 with VAE.</p><p>Please see <a target="_blank" rel="ugc" href="https://huggingface.co/wavymulder/lomo-diffusion/resolve/main/paramets_for_samples.txt">this document where I share the parameters (prompt, sampler, seed, etc.) used for all example images.</a></p><p>You can <a target="_blank" rel="ugc" href="https://i.imgur.com/cfIj3iq.jpg">see here a non-cherrypicked batch of 49 images here.</a></p><p>And you can <a target="_blank" rel="ugc" href="https://i.imgur.com/ugdFzPI.jpg">see here a direct comparison between Analog Style and Lomo Style.</a><br /><br />For safetensors or diffusers version, visit the huggingface page for this model here: <a target="_blank" rel="ugc" href="https://huggingface.co/wavymulder/lomo-diffusion">https://huggingface.co/wavymulder/lomo-diffusion</a></p>
页:
[1]