nod-ai / SHARK

SHARK - High Performance Machine Learning Distribution
Apache License 2.0
1.41k stars 168 forks source link

SHARK Stable Release Tracker (12/2023) #2005

Open monorimet opened 9 months ago

monorimet commented 9 months ago

Adding a list of TODOs:

radudiaconu0 commented 9 months ago

can we have sdxl turbo too added?

monorimet commented 9 months ago

can we have sdxl turbo too added?

Done. https://github.com/nod-ai/SHARK/releases/tag/20231205.1064

radudiaconu0 commented 9 months ago
image

i get this on rx 7900xtx on default settings on sd xl turbo

radudiaconu0 commented 9 months ago

@monorimet

one-lithe-rune commented 9 months ago

@monorimet Now I've got my LoRA changes vaguely into shape, I'll take a look the nod-ai logo and the gradio update regressions.

EDIT: /em looks at time, sometime tomorrow if no-one has picked them up.

radudiaconu0 commented 9 months ago

@monorimet it works nevermind

mergmann commented 9 months ago

When switching to sdxl-turbo, it disables the positive prompt, leaving only the negative one. Instead, I have to write the prompt while in sdxl-base mode, then switch to turbo.

mergmann commented 9 months ago

The sdxl-turbo model works mostly fine for me, but trying to run sdxl-base results in SystemExit: SharkifyStableDiffusionModel.get_unet_sdxl.<locals>.UnetModel.forward() missing 2 required positional arguments: 'time_ids' and 'guidance_scale' OS: EndeavourOS/Arch Linux GPU: RX 7900 XT (using amdvlk as mesa/vulkan-radeon is broken) Settings: 512x512 50 steps

monorimet commented 9 months ago

When switching to sdxl-turbo, it disables the positive prompt, leaving only the negative one. Instead, I have to write the prompt while in sdxl-base mode, then switch to turbo.

There's something goofy about the inputs/guidance scale for the SDXL implementation. This is actually intended behavior as a quick'n'dirty workaround but it's not a long term solution. I'll add a task for it.