Commit Graph

5 Commits

Author SHA1 Message Date
comfyanonymous
26bce56c3b pop clip vision keys after loading them. 2023-06-18 21:21:17 -04:00
comfyanonymous
16c535a309 Properly disable weight initialization in clip models. 2023-06-14 20:13:08 -04:00
comfyanonymous
54c3f45d58 Don't initialize CLIPVision weights to default values. 2023-06-14 12:57:02 -04:00
comfyanonymous
9c2869e012 Fix for new transformers version. 2023-04-09 15:55:21 -04:00
comfyanonymous
b55667284c Add support for unCLIP SD2.x models.
See _for_testing/unclip in the UI for the new nodes.

unCLIPCheckpointLoader is used to load them.

unCLIPConditioning is used to add the image cond and takes as input a
CLIPVisionEncode output which has been moved to the conditioning section.
2023-04-01 23:19:15 -04:00