FLUX.1 Dev LoRa aiming to generate Wimmelbilder Where's Waldo style images<h2 id="tips-7wv3gwvtt">Tips</h2><ul><li>Describe your scene naturally</li><li>Trigger might be necessary but always test without</li><li>Strength at 1.0 without trigger and 0.7/0.8 with trigger</li><li>This model really likes landscape aspect ratios</li><li>At 1.0 strength, the style is way better, but the model tends to generate a lot of malformed people</li><li>If you really want to get the best quality possible, try generating at 1664x1216</li></ul><h2 id="how-to-use-it-u39ic5f6q">How to use it</h2><ul><li>Used best with a Comfy fp16/bf16 checkpoint, use it as any other Lora</li><li>Use it with FAL FLUX with Loras: <a target="_blank" rel="ugc" href="https://fal.ai/models/fal-ai/flux-general">https://fal.ai/models/fal-ai/flux-general</a> . Just point to the .safetensors file in this repo</li></ul><h2 id="how-to-get-the-best-results-52wk43uve">How to get the best results</h2><ul><li>Generate your base image with txt2img</li><li>Upscale with something like AuraSR</li><li>Do a second img2img pass with ~0.3-0.5 denoising strength, same prompt</li><li>At the time of this release, tiled upscale is not possible yet with FLUX, but that would be really beneficial for this kind of outputs</li></ul><h2 id="contact-yfhqelhor">Contact</h2><a target="_blank" rel="ugc" href="https://twitter.com/nerijs">https://twitter.com/nerijs</a>

Files with SHA256: 571567c2e48720f99a84f5584d8646dfe9d45cd203144621228b2d535fd0c184