anindya
/
Hacklahoma-AI-Image-Workshop
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity
Browse Source

Update 'README.md'

main
Anindya Maiti 1 year ago
parent
81b2d91b4d
commit
dd85401a90
1 changed files with 5 additions and 5 deletions
Whitespace
Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL
Unified View
Diff Options
Show Stats Download Patch File Download Diff File
  1. 10
      README.md

10
README.md
View File

@ -39,17 +39,18 @@ LoRA Models: [CivitAI](https://civitai.com/models/)
Place downloaded models in the `stable-diffusion-webui/models`. Place downloaded models in the `stable-diffusion-webui/models`.
Some technical background on the latent space of an image model:
![](images/sd-latent-space.jpg)
## Start Generating ## Start Generating
### Image Dimensions (Resolution) ### Image Dimensions (Resolution)
As different models are trained on different image resolutions, it is best to use the training image resolution for generations. For `SD1.5` use 512x512 and for `SDXL1.0` use 1024x1024. You can slightly vary one of the dimensions without significant issues. As different models are trained on different image resolutions, it is best to use the training image resolution for generations. For SD1.5 use 512x512 and for SDXL1.0 use 1024x1024. You can slightly vary one of the dimensions without significant issues.
### text2img generation ### text2img generation
`text2img` can be thought of as generating visual content based on textual descriptions. Popular models include [DALL-E](https://openai.com/dall-e-2), [Midjourney](https://www.midjourney.com/home), and [Stable Diffusion](https://stability.ai/blog/stable-diffusion-public-release). `text2img` can be thought of as generating visual content based on textual descriptions. Popular models include [DALL-E](https://openai.com/dall-e-2), [Midjourney](https://www.midjourney.com/home), and [Stable Diffusion](https://stability.ai/blog/stable-diffusion-public-release). Stable Diffusion (such as SD1.5 and SDXL1.0) are open and gives us the more control on the image generation process.
![](images/sd-latent-space.jpg)
### img2img generation ### img2img generation
@ -59,5 +60,4 @@ As different models are trained on different image resolutions, it is best to us
![](images/cn-sd.png) ![](images/cn-sd.png)
Install extension for A1111: [`sd-webui-controlnet`](https://github.com/Mikubill/sd-webui-controlnet) Install extension for A1111: [`sd-webui-controlnet`](https://github.com/Mikubill/sd-webui-controlnet)
Write Preview
Loading…
Cancel
Save