The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface. The fastest local inference engine in the world.
Refactor VAE code.
comfyanonymous5eddfdd80caa
diff --git a/comfy/sd.py b/comfy/sd.pyindex 220637a05..10a6715a8 100644--- a/comfy/sd.py+++ b/comfy/sd.py@@ -157,6 +157,8 @@ class VAE: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)+ self.downscale_ratio = 8+ self.latent_channels = 4if config is None:if "decoder.mid.block_1.mix_factor" in sd:@@ -204,9 +206,9 @@ class VAE:decode_fn = lambda a: (self.first_stage_model.decode(a.to(self.vae_dtype).to(self.device)) + 1.0).float()output = torch.clamp((- (comfy.utils.tiled_scale(samples, decode_fn, tile_x // 2, tile_y * 2, overlap, upscale_amount = 8, output_device=self.output_device, pbar = pbar) +- comfy.utils.tiled_scale(samples, decode_fn, tile_x * 2, tile_y // 2, overlap, upscale_amount = 8, output_device=self.output_device, pbar = pbar) +- comfy.utils.tiled_scale(samples, decode_fn, tile_x, tile_y, overlap, upscale_amount = 8, output_device=self.output_device, pbar = pbar))+ (comfy.utils.tiled_scale(samples, decode_fn, tile_x // 2, tile_y * 2, overlap, upscale_amount = self.downscale_ratio, output_device=self.output_device, pbar = pbar) ++ comfy.utils.tiled_scale(samples, decode_fn, tile_x * 2, tile_y // 2, overlap, upscale_amount = self.downscale_ratio, output_device=self.output_device, pbar = pbar) ++ comfy.utils.tiled_scale(samples, decode_fn, tile_x, tile_y, overlap, upscale_amount = self.downscale_ratio, output_device=self.output_device, pbar = pbar))/ 3.0) / 2.0, min=0.0, max=1.0)return output@@ -217,9 +219,9 @@ class VAE:pbar = comfy.utils.ProgressBar(steps)encode_fn = lambda a: self.first_stage_model.encode((2. * a - 1.).to(self.vae_dtype).to(self.device)).float()- samples = comfy.utils.tiled_scale(pixel_samples, encode_fn, tile_x, tile_y, overlap, upscale_amount = (1/8), out_channels=4, output_device=self.output_device, pbar=pbar)- samples += comfy.utils.tiled_scale(pixel_samples, encode_fn, tile_x * 2, tile_y // 2, overlap, upscale_amount = (1/8), out_channels=4, output_device=self.output_device, pbar=pbar)- samples += comfy.utils.tiled_scale(pixel_samples, encode_fn, tile_x // 2, tile_y * 2, overlap, upscale_amount = (1/8), out_channels=4, output_device=self.output_device, pbar=pbar)+ samples = comfy.utils.tiled_scale(pixel_samples, encode_fn, tile_x, tile_y, overlap, upscale_amount = (1/self.downscale_ratio), out_channels=self.latent_channels, output_device=self.output_device, pbar=pbar)+ samples += comfy.utils.tiled_scale(pixel_samples, encode_fn, tile_x * 2, tile_y // 2, overlap, upscale_amount = (1/self.downscale_ratio), out_channels=self.latent_channels, output_device=self.output_device, pbar=pbar)+ samples += comfy.utils.tiled_scale(pixel_samples, encode_fn, tile_x // 2, tile_y * 2, overlap, upscale_amount = (1/self.downscale_ratio), out_channels=self.latent_channels, output_device=self.output_device, pbar=pbar)samples /= 3.0return samples@@ -231,7 +233,7 @@ class VAE:batch_number = int(free_memory / memory_used)batch_number = max(1, batch_number)- pixel_samples = torch.empty((samples_in.shape[0], 3, round(samples_in.shape[2] * 8), round(samples_in.shape[3] * 8)), device=self.output_device)+ pixel_samples = torch.empty((samples_in.shape[0], 3, round(samples_in.shape[2] * self.downscale_ratio), round(samples_in.shape[3] * self.downscale_ratio)), device=self.output_device)for x in range(0, samples_in.shape[0], batch_number):samples = samples_in[x:x+batch_number].to(self.vae_dtype).to(self.device)pixel_samples[x:x+batch_number] = torch.clamp((self.first_stage_model.decode(samples).to(self.output_device).float() + 1.0) / 2.0, min=0.0, max=1.0)@@ -255,7 +257,7 @@ class VAE:free_memory = model_management.get_free_memory(self.device)batch_number = int(free_memory / memory_used)batch_number = max(1, batch_number)- samples = torch.empty((pixel_samples.shape[0], 4, round(pixel_samples.shape[2] // 8), round(pixel_samples.shape[3] // 8)), device=self.output_device)+ samples = torch.empty((pixel_samples.shape[0], self.latent_channels, round(pixel_samples.shape[2] // self.downscale_ratio), round(pixel_samples.shape[3] // self.downscale_ratio)), device=self.output_device)for x in range(0, pixel_samples.shape[0], batch_number):pixels_in = (2. * pixel_samples[x:x+batch_number] - 1.).to(self.vae_dtype).to(self.device)samples[x:x+batch_number] = self.first_stage_model.encode(pixels_in).to(self.output_device).float()