mirror of
https://github.com/lllyasviel/ControlNet.git
synced 2026-04-24 03:00:54 -04:00
guess mode
This commit is contained in:
@@ -248,7 +248,7 @@ Without prompt, the HED seems good at generating images look like paintings when
|
||||
|
||||

|
||||
|
||||
As you can see below, because **non-prompted mode is extremely difficult**, even the very deep ControlNet may also generate failure cases. (In the example below, the right-bottom one seems ok while others looks meh.) Because of this, the non-prompted mode seems a nice metric to test the capability of different encoder-based methods to control stable diffusion.
|
||||
As you can see below, because **non-prompted mode is extremely difficult**, even the very deep ControlNet may also generate failure cases. (In the example below, the right-bottom one seems ok while others look meh.) Because of this, the non-prompted mode seems a nice metric to test the capability of different encoder-based methods to control stable diffusion.
|
||||
|
||||

|
||||
|
||||
|
||||
Reference in New Issue
Block a user