Sketch input in the DeepFillV2 model #1219
-
|
Hey guys thanks so much for opening up and implementing so many models for opensource community. I wanted to ask if the DeepFillV2 model in mmediting also supports user-sketch input, like in the original paper:
|
Beta Was this translation helpful? Give feedback.
Replies: 1 comment 1 reply
-
|
Hi @ankuPRK Yes. The DeepFillv2 model in MMEditing supports deals with input images with sketch input. Unfortunately, now, MMEditing only provides the pre-trained DeepFillv2 model that deals with input images without sketch input. Don't hesitate to contribute this new feature/model to MMEditing! |
Beta Was this translation helpful? Give feedback.
-
|
Hi @zengyh1900 , thanks for the clarification. |
Beta Was this translation helpful? Give feedback.
Hi @ankuPRK
Yes. The DeepFillv2 model in MMEditing supports deals with input images with sketch input.
You can check the source code here: https://github.com/open-mmlab/mmediting/blob/master/mmedit/models/backbones/encoder_decoders/encoders/deepfill_encoder.py#L10
Unfortunately, now, MMEditing only provides the pre-trained DeepFillv2 model that deals with input images without sketch input.
Don't hesitate to contribute this new feature/model to MMEditing!