chore(stablediffusion-ncn): drop in favor of ggml implementation #4652
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Description
This PR drops the
stablediffusion-ncn
backend (onnx and opencv based) in favor of the ggml implementation. The ggml implementation is superior (in terms of supported architectures) and also support GPU(CUDA). It also seems to be maintained and offering more models to pick from. When tests passing and the sd3.5 model is working I will change the model gallery entries to redirect to this backend rather than the old one.This will ease out development of LocalAI even more, we were depending on onnx and opencv in build time specifically for this backend.
Notes for Reviewers
Signed commits