Choose SDXL or SD 1.5 version from the menu on the top.Rate, like, and review to help people find the model on the site. It will also benefit the project significantly, as the models themselves required over 20 hours of training. Sandstone Natural Texture LoRA, created from an in-house photo dataset of textures taken on a field trip (from a different dataset than <a target="_blank" rel="ugc" href="https://civarchive.com/models/61437/sandstone-weathered-texture">Sandstone Weathered Texture</a>). The Lora is intended to use as a texture creation helper and works in scenes to texture objects. The goal was to create a set of LoRAs to add randomness and structure usable for various textured photos. Works also well for tileable texture creation. 1024x1024. Try to use weights 0.1-1 (for SDXL you can go much higher). Higher values will generate texture tiles, in scenes use values around 0.4. Soft and Medium variants have slightly different outputs.<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/6f74683d-6746-4b6c-a2ea-b2442acb4ca1/width=525/6f74683d-6746-4b6c-a2ea-b2442acb4ca1.jpeg" /><ul><li>For higher resolutions, use ControlNet Normal or Depth models to keep the composition (not available for SDXL yet)</li><li>You can render directly into target resolution, or use Hires. fix for an even more intricate structure</li><li>You can use it flexibly for scenes containing various subjects (not only stones or sandstones) for a textured look, the use is similar to <a target="_blank" rel="ugc" href="https://civarchive.com/models/78940/entropy">Entropy</a></li></ul>For my notes on training, research, and use of stable diffusion models, check <a target="_blank" rel="ugc" href="https://sandner.art/articles/ai/">https://sandner.art/articles/ai/</a>If you can afford it, support my work and experiments: <a target="_blank" rel="ugc" href="https://ko-fi.com/airesearch">https://ko-fi.com/airesearch</a>If you can not, review and/or rate the model to help others to find it.Have fun rendering!

Sandstone Natural Texture

Expanded dataset. 50s/5250s, 3ep, 12h, fin 2ep

Files with SHA256: 7c66b5bc4b6652b56c79c55cf58844ef3ecd6df40e8f340202096b26223574e6