|
I'm extremely pleased to introduce my newest hand-crafted Model 2.1 embedding! Meet Bliss, a beautiful hand painted style that creates stunning, highly detailed scenes with simple prompts, delivering easy flexibility and fantastic coherence, anchored in the real world with just a hint of fantasy and wonder! ??I hope you enjoy using these embeddings in your art as much as I enjoy creating them for the Stable Diffusion community. ????If you do like them, can you pretty please click the heart at the top and leave a review? Many thanks! ?? As with my other high quality embeddings, Bliss is very flexible and can be used to create a variety of subjects from science fiction to fantasy to wildlife and more! Even better, Bliss excels at inpainting and latent upscaling! See the 4 box example of a latent upscaled txt2img output, along with the inpainted final sample. Leave a comment and let me know if you have questions on how I achieve my results, or hit me up on Discord, I'm happy to chat! As usual, all of the sample images on this page use my special Fix yo' ugly face! Magic facelift embedding. I highly recommend it, along with all of my other high quality embeddings you can find on my profile page. Follow me to be notified when I release new embeddings! (Side note, I wanted to make comparing Bliss with Euphoria as easy as possible, so I used the same simple prompts to create the demo images) --------- A note on the creation of this embedding Bliss is a hybrid embedding. It was created through multiple methods including training, pure textual inversion through token crafting, and merging and mixing multiple released and unreleased embeddings of my own making. Bliss is a large embedding due to the nature of its creation, but shouldn't cause any issues in AUTOMATIC1111's Web UI. -------- To use this embedding in AUTOMATIC1111, copy it to your embeddings folder in your stable-diffusion-webui directory. No need to restart, just invoke the embedding from your prompt. Make sure you are using a compatible model or you will get errors! -------- | 
发表于 2023-6-7 22:44:45