The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface. The fastest local inference engine in the world.
Basic tiled decoding for audio VAE.
comfyanonymousa45df695706e
diff --git a/comfy/sd.py b/comfy/sd.pyindex 58a858aa0..cfbf8fa4d 100644--- a/comfy/sd.py+++ b/comfy/sd.py@@ -298,6 +298,17 @@ class VAE:/ 3.0)return output+ def decode_tiled_1d(self, samples, tile_x=128, overlap=64):+ output = torch.empty((samples.shape[0], self.output_channels) + tuple(map(lambda a: a * self.upscale_ratio, samples.shape[2:])), device=self.output_device)++ for j in range(samples.shape[0]):+ for i in range(0, samples.shape[-1], tile_x - overlap):+ f = i+ t = i + tile_x+ output[j:j+1,:,f * self.upscale_ratio:t * self.upscale_ratio] = self.first_stage_model.decode(samples[j:j+1,:,f:t].to(self.vae_dtype).to(self.device)).float()++ return output+def encode_tiled_(self, pixel_samples, tile_x=512, tile_y=512, overlap = 64):steps = pixel_samples.shape[0] * comfy.utils.get_tiled_scale_steps(pixel_samples.shape[3], pixel_samples.shape[2], tile_x, tile_y, overlap)steps += pixel_samples.shape[0] * comfy.utils.get_tiled_scale_steps(pixel_samples.shape[3], pixel_samples.shape[2], tile_x // 2, tile_y * 2, overlap)@@ -325,7 +336,10 @@ class VAE:pixel_samples[x:x+batch_number] = self.process_output(self.first_stage_model.decode(samples).to(self.output_device).float())except model_management.OOM_EXCEPTION as e:logging.warning("Warning: Ran out of memory when regular VAE decoding, retrying with tiled VAE decoding.")- pixel_samples = self.decode_tiled_(samples_in)+ if len(samples_in.shape) == 3:+ pixel_samples = self.decode_tiled_1d(samples_in)+ else:+ pixel_samples = self.decode_tiled_(samples_in)pixel_samples = pixel_samples.to(self.output_device).movedim(1,-1)return pixel_samples