Sign In

Anime from HaDeS XL

105
1.4k
46
Verified:
SafeTensor
Type
Checkpoint Trained
Stats
266
Reviews
Published
Jul 29, 2024
Base Model
SDXL 1.0
Hash
AutoV2
B69DBD0B53

If you like what I do, leave me a ❤️ to receive notifications of future updates and follow me here on Civitai. Remember that it is a hobby for me and it costs a lot of time and everything is shared entirely for free, I appreciate that you make a review and share your creations on this wall.


Anime From HaDeS XL v2.1

Width/Height: 1024x1408

Sampler: DPM++ 3M SDE, DPM++ 3M SDE Karras, DPM++ 2M SDE Karras

Steps: Around 20

CFG: 3-7

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

Anime From HaDeS XL Lightning v2

  • Improved image quality

  • Improved Speed

  • Added Artistic image Enhancer XL v1.1 Lite

  • Added Fashionizer XL Lite

  • Added R.O.A.R. Better Hands XL Lite (unreleased)

Width/Height: 1024x1408

Sampler: DPM++ 3M SDE (This is one of my favorites, but you can try others and they will also give you excellent results).

Steps: 4-12 (8-10 best values)

CFG: 1-4

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 steps used to generate the main image and 0.15 Denoise + Upscale: 2

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.

Width/Height: 1024x1408

Sampler: DPM++ 3M SDE

Steps: 8-10

CFG: 1-4

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 + Upscale: 2

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.