Joe Sandusky

[Feature Request] - Presets (or cycle button?) to snap to the 9 resolutions SDXL was trained on

5

Hello! Per the Stability AI, SDXL was trained on images with the resolutions listed below (1024x1024 , 1152x96, 896x1152, 1216x832, 832x1216, 1344x768, 768x1344, 1536x640, 640x1536). I was wondering if there...

Extension "Frame 2 Frame"

4

I am in no way associated w/ this extension but I've enjoyed using it so submitting it in the event someone here wants to reach out or add it. Same...

Saved models out of Forge gives "'NoneType' object is not iterable" when used to generate in both A1111 and Comfy

5

Not sure when this started happening but noticed an issue w/ models saved out using Forge giving me the following error. I get this when trying to use the saved...

Error when attempting to merge SDXL Inpaint .1 Beta model - Perhaps impossible? (RuntimeError: The size of tensor a (9) must match the size of tensor b (4) at non-singleton dimension 1)

2

The developer branch of A1111 allows for use of SDXL inpaint models. SAI quietly released a very early beta inpaint model for SDXL months ago in diffuser format, and I...

SDXL models trained w/ "One Trainer" are rejected w/ warning, "Warning model_a is SDNone but model_b is SDXL"

3

Hey, I think this is a issue/quirk on the [OneTrainer](https://github.com/Nerogar/OneTrainer) side, but due to some difference in the way the header(maybe?) is formatted some applications read SDXL models trained w/...

Issue where model in merged but not save leads to "Cannot copy out of meta tensor; no data!" - persists through restart - had to disable app to continue

15

Hey, first off congratulations on your extension. Having the option to merge up 5 models and also to have the option right on the TXT2IMG page is pretty cool. I...

Fix loras having a weak effect when applied on fp8. - [Comfy Pushed fix for thsi - Can we get in Forge]

7

Please see this commit that Comfy pushed earlier today that fixes the issue where some Flux LoRA are very weak when using along w/ fp8. It would be great if...

Forge was updated today - Errors on inference when Model Mixer isn't enabled

7

Hey! Forge lllyasviel was very kind and provided a much needed update to Forge today (including upgrading GRadio to 4.0). I installed MMixer from the installer and w/o even enabling...

Error after update

2

Hello, I updated today for the first time in a week or two and have gotten this type error twice now after running a few successful merge generations. Unfortunately I...

Hi! At the moment Flux LoRA made w/ Ostris' AI-Toolkit are not properly merged when using the merge to base option. AI-Toolkit LoRA have slightly varied key namings which cause...