The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface. The fastest local inference engine in the world.
Better memory estimation for the SD/Flux VAE on AMD. (#10334)
comfyanonymousdfff7e533253
diff --git a/comfy/sd.py b/comfy/sd.pyindex b9c2e995e..28bee248d 100644--- a/comfy/sd.py+++ b/comfy/sd.py@@ -276,8 +276,13 @@ class VAE:if 'decoder.up_blocks.0.resnets.0.norm1.weight' in sd.keys(): #diffusers formatsd = diffusers_convert.convert_vae_state_dict(sd)- self.memory_used_encode = lambda shape, dtype: (1767 * shape[2] * shape[3]) * model_management.dtype_size(dtype) #These are for AutoencoderKL and need tweaking (should be lower)- self.memory_used_decode = lambda shape, dtype: (2178 * shape[2] * shape[3] * 64) * model_management.dtype_size(dtype)+ if model_management.is_amd():+ VAE_KL_MEM_RATIO = 2.73+ else:+ VAE_KL_MEM_RATIO = 1.0++ self.memory_used_encode = lambda shape, dtype: (1767 * shape[2] * shape[3]) * model_management.dtype_size(dtype) * VAE_KL_MEM_RATIO #These are for AutoencoderKL and need tweaking (should be lower)+ self.memory_used_decode = lambda shape, dtype: (2178 * shape[2] * shape[3] * 64) * model_management.dtype_size(dtype) * VAE_KL_MEM_RATIOself.downscale_ratio = 8self.upscale_ratio = 8self.latent_channels = 4