Note: This model was originally posted <a target="_blank" rel="ugc" href="https://huggingface.co/aixonlab/flux.1-lumiere-alpha">here</a>, and is created by <a target="_blank" rel="ugc" href="https://www.aixonlab.com/">Aixonlab.</a> Note: While the results are exceptional, potentially better than base Flux.1 Dev, beware that combining with existing Flux LoRAs does not produce fantastic results! - Ally<h2 id="lumiere-alpha-1se45txkt">Lumiere Alpha</h2>We are excited to announce Lumiere Alpha, A model focusing on improving realism without compromising prompt coherency or changing the composition completely from the original Flux.1-Dev model.<h2 id="text-to-image-lweuyczx1">Text-to-Image</h2>For the best results, we strongly recommend using a <code>guidance scale</code> of 3.0 and setting <code>steps</code> between 28 and 35, with <code>Euler Beta</code>.<h3 id="attribution-notice-df4ud9034">Attribution notice</h3>The FLUX.1 [dev] Model is licensed by Black Forest Labs. Inc. under the FLUX.1 [dev] Non-Commercial License. Copyright Black Forest Labs. Inc.Our model is released under the FLUX.1 [dev] Non-Commercial License.

Lumiere Alpha from Aixonlab

Files with SHA256: b4b9be799db7340cebe67fe7c6e3203980e181da77eefd6b04b2cb7593a6d049