Anime from HaDeS XL

Anime From HaDeS XL Lightning This checkpoint is a merge of Anime from HaDeS XL v1.0 and the 8-steps release of SDXL Lightning (ByteDance/SDXL-Lightning · Hugging Face). The idea was obviously to release a version of Anime from HaDeS XL that everyone could use, even users with less powerful hardware. But in practice, maintaining a dual balance between an 8-step checkpoint and a normal SDXL 1.0 checkpoint without losing quality has not been an easy task. Recommended Settings for the Lightning Version: Width/Height: 1024x1328 Sampler: DPM++ 3M SDE Steps: 8-10 CFG: 1-2 VAE: Already baked in. Negative Prompt: No negative prompt needed, add afterwards the things you don´t want to see in the image. HiRes: 4x_NMKD-Siax_200k with 5 Steps and 0.15 Denoise + 1.5 Upscale The use of FreeU and SelfAttentionGuidance is optional but highly recommended due to the great improvement in Lightning models. Next, a little help about some settings that works especially well in this checkpoint, from here you can tweak it to your liking: FreeU B1: 1.34 B2: 1.19 S1: 0.67 S2: 0.27 SelfAttentionGuidance Scale: 0.5 Blur Sigma: 2 Recommended Settings for the Standard Version: Width/Height: 1024x1328 Sampler: DPM++ 3M SDE Exponential Steps: 32-40 CFG: 4-12 (A CFG around 10 gives the best results in my opinion.) VAE: Already baked in. Negative Prompt: No negative prompt needed, add afterwards the things you don´t want to see in the image. HiRes: 4x_NMKD-Siax_200k with half the regular steps and 0.15 Denoise + 1.5 Upscale Finally, just comment that I still recommend the entire version of Anime from HaDeS XL v1.0 in terms of quality. For the rest, I hope you like the model and I can't wait to see your creations on this wall. Thumbs up if you like it and reviews are highly appreciated. Anime From HaDeS v1.0 Anime from HaDeS comes to SDXL with a very balanced first version. After months trying to achieve results similar to the SD 1.5 version, I can finally publish a v1.0. Anime from HaDeS XL was born in the same way as its namesake from SD 1.5, thanks to a merge with realism from HaDes XL and several LoRas. (And many hours testing and starting over, especially because of wanting to include a custom VAE, which in the end this version will not include due to compatibility problems and various bugs). Ultimately, this is the beginning of a model that I hope to take further and that also unfortunately means that Anime from HaDeS SD 1.5 will not receive any more updates. (I don't have the life to work on so many models at once, I will focus only on SDXL from now on). I hope you like it, receive a lot of positive feedback and comments that help me evolve this model and take it to the highest levels of quality. Enjoy creating!! Recommendations? None, the model is quite flexible, accepting a multitude of configurations. There are some sample images above, surprise me.