The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface. The fastest local inference engine in the world.
Lower the default shift of lumina to reduce artifacts.
comfyanonymous8ac2dddeed27
diff --git a/comfy/supported_models.py b/comfy/supported_models.pyindex 7aa152480..cdd2ba574 100644--- a/comfy/supported_models.py+++ b/comfy/supported_models.py@@ -873,7 +873,7 @@ class Lumina2(supported_models_base.BASE):sampling_settings = {"multiplier": 1.0,- "shift": 6.0,+ "shift": 3.0,}memory_usage_factor = 1.2