Alyndiar
Note: This is not my model, but it was not present on CivitAI, so I thought it might be nice to bring it here.
Update : Bob (hesw23168) from HuggingFace - SD-Elysium Model is present on CivitAI as Sinomakoi. He has converted V2 of the Elesium Anime model to safetensors format and posted it here. As this is his model, and without any request from him, I will be removing this version of the model, as well as any of the other versions he decides to bring over to CivitAI. Please visit his page and get the model from him directly. And don't forget to thanks him for his great work.
Original model can be found on HuggingFace at : HuggingFace - SD-Elysium Model and is the creation of Bob (hesw23168). Please give credit to him and go thank him over there if you like this model. Should he come over to CivitAI, I will gladly relinquish any hold I have on this model into his own hands.
Elysium - high quality general model with realistic style
Elysium Anime - anime version of Elysium, detailed versatile anime style
Recommended settings:
Negative prompt: lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry
(General model): Clip skip 1, VAE: 'vae-ft-mse-840000' from StabilityAI (https://huggingface.co/stabilityai/sd-vae-ft-mse-original/tree/main). Sampler: DPM++ 2M Karras
(Anime model): Clip skip 1 or 2, VAE: 'kl-f8-anime2.ckpt' from Waifu Diffusion (https://huggingface.co/hakurei/waifu-diffusion-v1-4/tree/main/vae). Sampler: DPM++ 2M Karras
Both should work well with booru tags.
Can produce softcore NSFW images but needs a little coaxing to get there.
What is Elysium?
Elysium is a highly specialized Image generation AI Model of type Safetensors / Checkpoint AI Model created by AI community user Alyndiar. Derived from the powerful Stable Diffusion (SD 1.5) model, Elysium has undergone an extensive fine-tuning process, leveraging the power of a dataset consisting of images generated by other AI models or user-contributed data. This fine-tuning process ensures that Elysium is capable of generating images that are highly relevant to the specific use-cases it was designed for, such as anime, general purpose, realistic.
With a rating of 5 and over 2 ratings, Elysium is a popular choice among users for generating high-quality images from text prompts.
Can I download Elysium?
Yes! You can download the latest version of Elysium from here.
How to use Elysium?
To use Elysium, download the model checkpoint file and set up an UI for running Stable Diffusion models (for example, AUTOMATIC1111). Then, provide the model with a detailed text prompt to generate an image. Experiment with different prompts and settings to achieve the desired results. If this sounds a bit complicated, check out our initial guide to Stable Diffusion – it might be of help. And if you really want to dive deep into AI image generation and understand how set up AUTOMATIC1111 to use Safetensors / Checkpoint AI Models like Elysium, check out our crash course in AI image generation.
Popularity
Info
Latest version (Elysium Anime V1): 1 File
About this version: Elysium Anime V1
First anime trained version. Gives rather nice images.
