Marcophono

Displaying Harman launch screen although having license file (Android, AIR SDK 33.0.2.338)

10

Hello! For certain reasons I am using an elder AIR SDK because I only want to use Android

Fast generation of smaller images with the option to generate the large 512x512 version later

4

Hello! I am afraid that there could be two technical reasons that my request could not be solved. But may be I am wrong. As everybody knows not every generated...

Is there kind of a "quality value" available?

2

Hello! As SD starts from a fully noised image to improve the quality value (reduce the error) I think that there should be a value available at the end of...

Where to save the model locally?

1

I cannot believe that I really ask this but after two hours of research I didn't find a working way. I did it very often a few months ago but...

Performance Issue with RTX 4090 and all SD/Diffusers versions

37

### Describe the bug Hello! Since 10 days, nearly round the clock, I try to bring my brand new and proudly owned Geforce RTX 4090 graphic cards to work appropriate...

Strange behaviour and issues with SD 2.1 on multi-gpu (4090) and xformers attention

4

### Describe the bug Hello! Today I tried to setup SD 2.1 but have some trouble with more than one issue. ``` pipe = StableDiffusionPipeline.from_pretrained( "stabilityai/stable-diffusion-2-1", torch_dtype=torch.float16, ).to("cuda") # or...

Possible to reduce the VRAM usage just by 10%?

1

Hello! I was a big fan already of BLIP (1) and very impressed by the improvement of BLIP 2. I have a RTX 4090 but unfortunatelly its VRAM is just...

Add Lora layer on the fly?

1

Hello! Great work, thank you very much! But I have a general question and was not able to google the answer for this. From my understanding Lora has the big...

training Lora with 2.1 able on a 24 GB GPU?

2

Hello! I really would like to train Lora on my 24 GB GPU but I always get OOM. Is there any parameter or setting which I missed and which could...

Blip2ForConditionalGeneration.from_pretrained is limited by 100% CPU usability (on one single core)

9

### System Info - `transformers` version: 4.27.0.dev0 - Platform: Linux-5.19.0-31-generic-x86_64-with-glibc2.36 - Python version: 3.10.6 - Huggingface_hub version: 0.12.0 - PyTorch version (GPU?): 2.0.0.dev20230209+cu118 (True) - Tensorflow version (GPU?): not installed...