Speedway1

Trying different models, only RealVision runs, others all give similar errors to above. However, RealVision crashes with "RuntimeError: The size of tensor a (576) must match the size of tensor...

> Hi, @Speedway1 , I have modified the code, but do not know whether solving your problem. could you git pull and run again? Thank you, we're actually going to...

> Hi, @Speedway1 , I have modified the code, but do not know whether solving your problem. could you git pull and run again? Unfortunately still only "RealVision" option works....

Correction, "Unstable" is now working too. Here is the list of working: Unstable RealVision SDXL: Started download, will report back when finished but looks like will now work. These not...

Cannot run onRTX4090 with 24GB. Keep getting CUDA out of memory error.

OK we just found a way to run it on a RTX4090 , you need to drop the "number of sample steps" to 35 and the image dimensions should be...

> I have been succesful with a RTX 4090 by enabling VAE slicing and CPU offloading. > > Add at line 545 of gradio_app_sdxl_specific_id.py: [TAB]pipe.enable_vae_slicing() [TAB]pipe.enable_model_cpu_offload() > > You may...

Comic strip technology is very good though, shows how to get character consistency.

> > Comic strip technology is very good though, shows how to get character consistency. > > any result examples ? This was meant to be a spy thing with...

> Possible fix, but not yet tested carefully > > In def process_mulline_text > > width = draw.textlength(test_line, font=font) > > no more , _ > > `def add_caption(image, text,...