<a target="_blank" rel="ugc" href="https://rentry.org/8btyp">High-Res-Fix and Dynamic Thresholding</a>This model will no longer be updated as I feel like its starting to regress, I will be training LoRA's from now on. If you have any ideas for LoRA's <a rel="ugc" href="https://forms.gle/thh88dtsvLMfn8Ra7">let me know</a>. I only have an RTX 2060 6gb so they might not be the best, the max resolution that I can train is around 600x600.This model's goal is to generate photo like images.<a target="_blank" rel="ugc" href="https://huggingface.co/Virt-io/Eden/tree/main">Inpainting version on HuggingFace</a>All images where generated using High-Res-Fix with 4x-UltraSharp upscaler.vae-ft-mse-840000-ema-pruned

Eden

This version has minor improvements.<ul><li>I made lora for skin textures and merged into Eden. Should give better skin, you can use "detailed skin, brown skin, dark skin, veins, veiny skin, pores" to enhance the effect.</li></ul><ul><li>I also made a lora for photography and merged it. this should improve the realism of landscapes, you can use<ul><li>landscape</li><li>portrait - for upper body generations</li><li>full shot - should give you the full subject </li></ul></li></ul> Please let me know if this breaks anything as well as suggestions.If anyone wants it I may try and train a lora for other skin colors (like blue and green) and see if works.

Files with SHA256: 652bbbf23bafddb02d9179492530a9d9302a269638c1740fba306990c892bcda