--- tags: - text-to-image - stable-diffusion - lora - diffusers - template:sd-lora widget: - text: >- a medieval village with a castle on top, there's a river and a forest on the sides output: url: images/Ok0TN2t1lDZ0YtvvuHJEv_111ca5a41f8f467bb22d0414d3713418.png - text: >- A sprawling metropolis built from brass and iron, with towering clockwork skyscrapers adorned with massive, rotating gears and steam vents. The streets are lined with gas lamps and cobblestone, bustling with steam-powered carriages and people in Victorian attire. Above, airships with billowing sails and massive propellers drift through the smog-filled sky. The central feature of the city is a colossal clock tower, its intricate mechanisms visible as it chimes loudly across the city. The atmosphere is vibrant with the hum of machinery and the hiss of steam. output: url: images/iGiC0wbWIYiLunFv2wT6B_3ba16a190fd94915b487a66fe5ddfde6.png - text: '-' output: url: images/Dvi-gJz2IIY-nMpMGZM7q_0ebd854b97f643a5964697e79d913c59.png - text: >- A vast, otherworldly plane where the ground is a perfect, reflective mirror, stretching endlessly in all directions. The sky is an abstract swirl of colors—blues, pinks, purples, and golds—constantly shifting and changing like a living painting. Floating above the mirrored surface are massive, translucent orbs filled with swirling galaxies and nebulae, each one reflecting and refracting the colors of the sky in a dazzling display of light. Occasionally, the mirrored ground ripples as if touched by an invisible hand, sending waves of color across the landscape. There are no horizons, no up or down, just an endless expanse of color and reflection, where the only sounds are the faint echoes of distant, celestial music. output: url: images/_899e4CUxJ8E9QyyGWRGo_6d109c962d014782a16a3eefff15cc88.png base_model: black-forest-labs/FLUX.1-dev instance_prompt: wh3r3sw4ld0 license: mit --- # FLUX - Where's Waldo LoRa ## Model description FLUX.1 Dev LoRa aiming to generate Wimmelbilder Where's Waldo style images ## Tips - Describe your scene naturally - Trigger might be necessary but always test without - Strength at 1.0 without trigger and 0.7/0.8 with trigger - This model really likes landscape aspect ratios - At 1.0 strength, the style is way better, but the model tends to generate a lot of malformed people ## How to use it - Used best with a Comfy fp16/bf16 checkpoint, use it as any other Lora - Use it with FAL FLUX with Loras: https://fal.ai/models/fal-ai/flux-general . Just point to the .safetensors file in this repo ## How to get the best results - Generate your base image with txt2img - Upscale with something like **AuraSR** - Do a second img2img pass with ~0.3-0.5 denoising strength, same prompt - 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 ## Contact https://twitter.com/nerijs ## Trigger words You should use `wh3r3sw4ld0` to trigger the image generation. ## Download model Weights for this model are available in Safetensors format. [Download](/nerijs/flux-waldo1024-v1/tree/main) them in the Files & versions tab.