rabidcopy

Xenoblade Chronicles 3 [010074F013262000]: Vulkan backend crashes before title screen on AMD

3

## Bug Report ### What's the issue you encountered? Game fails to reach the title screen when using the Vulkan backend. Have tried 1x resolution, 2x resolution, clearing caches, clearing...

Xenoblade Chronicles 3 [010074F013262000]: Flickering/missing graphics on OpenGL/Linux/AMD

3

## Bug Report ### What's the issue you encountered? Experiencing extreme flickering graphics during gameplay. Some graphical effects do not render correctly. Requires AMD_DEBUG=nohyperz to render most models correctly. ###...

**Describe the bug** Use of the 3 way checkpoint merge with add difference selected results in an unusable checkpoint. (with model hash 925997e9 as the tertiary???) **To Reproduce** Steps to...

Implement Training-Free Structured Diffusion Guidance for Compositional Text-to-Image Synthesis

6

**Is your feature request related to a problem? Please describe.** Don't think this is a duplicate of anything else and shouldn't be confused with #1325. This is related to the...

Question regarding embeddings trained with multiple placeholders_strings/initializer_words.

3

This is a bit of an odd case but I was wondering if there is any means to take an embeddings.pt with multiple placeholders and merge or otherwise consolidate them...

Replace EOS with newline to prevent context/memory being flushed by EOS in interactive mode

41

Edit: Most of the below is now outdated. This PR aims to do two things. -Replace EOS with newline to prevent context/memory being flushed by EOS in interactive mode -Better...

Can't pinpoint which commit did it but it was working as of 2f9d6a97ec7e3cb25beb13a320da8ec4573355d3. `python main.py --novram --disable-smart-memory --deterministic --extra-model-paths-config extra_model_paths.yaml --dont-upcast-attention --preview-method latent2rgb` ``` ERROR:root:!!! Exception during processing !!! ERROR:root:Traceback...

SDXL CLIPTextEncode: User specified autocast device_type must be 'cuda' or 'cpu'

8

`python main.py --normalvram --use-quad-cross-attention --auto-launch --disable-smart-memory --preview-method latent2rgb --dont-upcast-attention` (model is automatically loaded in lowvram mode due to 4GB of VRAM.) ``` Total VRAM 4096 MB, total RAM 15943 MB...

Currently when using `Read parameters (prompt, etc...) from txt2img tab when making previews`, the sampler selected is ignored and instead the default ("Euler a") sampler is used. This is due...