The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface. The fastest local inference engine in the world.
Update AGENTS.md (#14738)
comfyanonymousde1b8f3e8d54
diff --git a/AGENTS.md b/AGENTS.mdindex 5236a00cf..a8bacbd5e 100644--- a/AGENTS.md+++ b/AGENTS.md@@ -171,6 +171,9 @@- Reuse existing model classes, blocks, ops, and helper modules when appropriate.Before implementing a new version of a model component, search the existingmodel code for a class or helper that already provides the behavior.+- Model detection code that inspects linear weight shapes should only use the+ first dimension. The second dimension may be half the original size for+ NVFP4 or other 4-bit quantized models.- Avoid adding `einops` usage in core inference code. Use native torch tensorops such as `reshape`, `view`, `permute`, `transpose`, `flatten`, `unflatten`,`unsqueeze`, and `squeeze` instead.