icon-logo
Stable difusion 2 impainting
Checkpoint
coll-num9
look-num220

2

share
selectCommunity
Model Permissions:
prompt-imgEveryone Can See The Model
prompt-imgAnyone Can Use The Model
prompt-imgCommercial Use Prohibited
1
12DOTZE
uploader
Details
Category
OBJECTS
Type
Checkpoint-Trained
Base Model
SD 2.0
Support
Fill
Uploaded
May 13.2024
Added
9
Runs
220
Security
Verified
Version Info
Better training and acuracy than v1.5

This model card focuses on the model associated with the Stable Diffusion v2, available here.

This stable-diffusion-2-inpainting model is resumed from stable-diffusion-2-base (512-base-ema.ckpt) and trained for another 200k steps. Follows the mask-generation strategy presented in LAMA which, in combination with the latent VAE representations of the masked image, are used as an additional conditioning.

Show More
Gallery
share