Home trained FLUX, SDXL and Z-IMAGE Turbo Lora on a RTX 5070 ti graphics card.SDXL version 1.0: Trained with Image Dataset (using OneTrainer)FLUX version 1.0: Trained with Image Dataset (using FluxGym)FLUX version 2.0: Fine-tuned Lora <span style="background-color:rgb(26, 27, 30);color:rgb(193, 194, 197);font-family:-apple-system, BlinkMacSystemFont, &quot;Segoe UI&quot;, Roboto, Helvetica, Arial, sans-serif, &quot;Apple Color Emoji&quot;, &quot;Segoe UI Emoji&quot;;font-size:16px">more refined oriental illustrationsFLUX version 3.0: Fine-tuned Lora to add <span style="background-color:rgb(26, 27, 30);color:rgb(193, 194, 197);font-family:-apple-system, BlinkMacSystemFont, &quot;Segoe UI&quot;, Roboto, Helvetica, Arial, sans-serif, &quot;Apple Color Emoji&quot;, &quot;Segoe UI Emoji&quot;;font-size:16px">Illuminated manuscript borders and more refined oriental illustrationsZIT version 1.0: Trained with Image Dataset (using musubi-tuner)

Indies vintage illustration [SDXL/FLUX/ZIT]

4 repeats, 20 epochs, 41 images = 3280 stepsLearning Rate : 8e-4, Seed : 42, Guidance_Scale : 1, Repeat trains per image : 4, Max Train Epochs : 20, Save every N epochs : 4, Sample Image Every N Steps : 50, Resize dataset images : 1024Training time: 06:00:24

Files with SHA256: cfe6330a95270571f4c680589e3d20774ae3a2d065d56cbbba34c912bcc46712