--- tags: - text-to-image - lora - diffusers - template:diffusion-lora widget: - text: ArsMJStyle, Stained Glass, Leafy themed scene in art noveau style of a woman parameters: negative_prompt: 'Steps: 20 Seed: 48504304160196' output: url: images/ComfyUI_00019_.png - text: ArsMJStyle, Stained Glass, parameters: negative_prompt: 'Steps: 20 Seed: 3054258899304' output: url: images/ComfyUI_00008_.png - text: >- masterpiece, beautiful oriental demon woman, sexy attire, ArsMJStyle, Stained Glass, perfect lighting parameters: negative_prompt: 'Guidance: 3.5 Steps: 25 Seed: 142516030' output: url: images/27722440.jpeg base_model: black-forest-labs/FLUX.1-dev instance_prompt: ArsMJStyle, Stained Glass license: unknown --- # Stained Glass (SD1.5, SDXL, Pony, Flux) 354 3.4k 3.4k 178 Updated: Oct 22, 2024 style midjourney stained glass midjourney v6 ## Model description FROM https://civitai.com/models/553811/stained-glass-sd15-sdxl-pony-flux Trigger ArsMJStyle, Stained Glass Strength 0.8 The Lora is trained on MidJourney Images that use my "Personalised Style" + Stained Glass. Works without the trigger words ArsMJStyle, Stained Glass Have a good effect in the 0.4 - 0.8 range Starts to melt a little bit at 1 in some checkpoints. 0.8 is a good starting point. SD1.5, SDXL, and PonyV2 are trained on a 100% larger dataset. Flux update: Same dataset as PonyV2 , but with different capture. Check the version description for recommended settings. About this version Recommended range is 0.6 - 1.2 strength . Some prompts seem to work just fine without the trigger words, but I will recommend starting with them and around 1 strength. ## Trigger words You should use `ArsMJStyle` to trigger the image generation. You should use `Stained Glass` to trigger the image generation. ## Download model Weights for this model are available in Safetensors format. [Download](/Jonjew/StainedGlass/tree/main) them in the Files & versions tab.