Skip to content

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 estimation for memory usage during audio VAE encoding/decoding.

comfyanonymousca9d300a804f
diff --git a/comfy/sd.py b/comfy/sd.py
index 82f9aeab8..e16cd8e53 100644
--- a/comfy/sd.py
+++ b/comfy/sd.py
@@ -237,8 +237,8 @@ class VAE:
decoder_config={'target': "comfy.ldm.modules.diffusionmodules.model.Decoder", 'params': ddconfig})
elif "decoder.layers.0.weight_v" in sd:
self.first_stage_model = AudioOobleckVAE()
- self.memory_used_encode = lambda shape, dtype: (1767 * shape[2]) * model_management.dtype_size(dtype) #TODO: tweak for the audio VAE
- self.memory_used_decode = lambda shape, dtype: (2178 * shape[2] * 64) * model_management.dtype_size(dtype)
+ self.memory_used_encode = lambda shape, dtype: (1000 * shape[2]) * model_management.dtype_size(dtype)
+ self.memory_used_decode = lambda shape, dtype: (1000 * shape[2] * 2048) * model_management.dtype_size(dtype)
self.latent_channels = 64
self.output_channels = 2
self.upscale_ratio = 2048