A Stable Diffusion LoRA profile based on Emma Watson
.
Place it in "stable-diffusion-webui\extensions\sd-webui-additional-networks\models\lora" folder in Automatic1111 WebUI root folder.
Made using kohya-ss so make sure to have that extension installed!
In txt2img, under "Additional Networks", select "Enable" and under Model 1 select "Emma Watson" and assign a weight between 0.3-0.7 (feel free to experiment!). In the prompt text window use "Emma Watson" within your prompt to generate images.
Embed has been trained on Stable Diffusion 1.5 model.
I Recommend the model https://civarchive.com/models/4922/grapelikedreamfruit - Gives amazing realistic renders.
Description
FAQ
Comments (4)
Why? She's in every model
Great job ! With the Colorful_v21 mix the realism of the renders is perfect. Keep going with other LORAs.
Off topic but is there a reason why people say stuff like "Made using kohya-ss so make sure to have that extension"? Like will the extension have different results than the base lora compatibility that is in a1111 now?
I AM NOT complaining about the LORA, but I am curious, why would we need a LORA for emma when SD already has a pretty good grasp of her? If you use emma watson as a prompt, you're gonna get a pretty accurate likeness without the need of a TI or LORA. Does this provide some extra flexibility that i'm missing?
Details
Files
Available On (2 platforms)
Same model published on other platforms. May have additional downloads or version variants.