Commit 9b5250c
committed
| Original file line number | Diff line number | Diff line change | |
|---|---|---|---|
@@ -260,6 +260,18 @@ Note that in the guess mode, you will still be able to input prompts. The only d | |||
| 260 | 260 | ||
| 261 | 261 | Besides, if you write some scripts (like BLIP) to generate image captions from the "guess mode" images, and then use the generated captions as prompts to diffuse again, you will get a SOTA pipeline for fully automatic conditional image generating. | |
| 262 | 262 | ||
| 263 | + # Combining Multiple ControlNets | ||
| 264 | + | ||
| 265 | + ControlNets are composable: more than one ControlNet can be easily composed to multi-condition control. | ||
| 266 | + | ||
| 267 | + Right now this feature is in experimental stage in the [Mikubill' A1111 Webui Plugin](https://github.com/Mikubill/sd-webui-controlnet): | ||
| 268 | + | ||
| 269 | +  | ||
| 270 | + | ||
| 271 | +  | ||
| 272 | + | ||
| 273 | + **Keep in mind that as long as the models are controlling the same SD, the "boundary" between research projects does not even exist: ControlNets can work together with [T2I-Adapter](https://github.com/TencentARC/T2I-Adapter) in this plugin.** | ||
| 274 | + | ||
| 263 | 275 | # Use ControlNet in Any Community Model (SD1.X) | |
| 264 | 276 | ||
| 265 | 277 | This is an experimental feature. | |
LoadingViewer requires iframe.
LoadingViewer requires iframe.
0 commit comments