andreas/ComfyUI
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Support the new hunyuan vae. (#10150)

Browse Source
This commit is contained in:
comfyanonymous
2025-10-01 14:19:13 -07:00
committed by GitHub
parent e4f99b479a
commit a6f83a4a1a
2 changed files with 116 additions and 66 deletions
Download Patch File Download Diff File Expand all files Collapse all files

70
comfy/sd.py
View File

@@ -332,35 +332,51 @@ class VAE:
self.first_stage_model = StageC_coder()
self.downscale_ratio = 32
self.latent_channels = 16
elif "decoder.conv_in.weight" in sd and sd['decoder.conv_in.weight'].shape[1] == 64:
ddconfig = {"block_out_channels": [128, 256, 512, 512, 1024, 1024], "in_channels": 3, "out_channels": 3, "num_res_blocks": 2, "ffactor_spatial": 32, "downsample_match_channel": True, "upsample_match_channel": True}
self.latent_channels = ddconfig['z_channels'] = sd["decoder.conv_in.weight"].shape[1]
self.downscale_ratio = 32
self.upscale_ratio = 32
self.working_dtypes = [torch.float16, torch.bfloat16, torch.float32]
self.first_stage_model = AutoencodingEngine(regularizer_config={'target': "comfy.ldm.models.autoencoder.DiagonalGaussianRegularizer"},
encoder_config={'target': "comfy.ldm.hunyuan_video.vae.Encoder", 'params': ddconfig},
decoder_config={'target': "comfy.ldm.hunyuan_video.vae.Decoder", 'params': ddconfig})
self.memory_used_encode = lambda shape, dtype: (700 * shape[2] * shape[3]) * model_management.dtype_size(dtype)
self.memory_used_decode = lambda shape, dtype: (700 * shape[2] * shape[3] * 32 * 32) * model_management.dtype_size(dtype)
elif "decoder.conv_in.weight" in sd:
#default SD1.x/SD2.x VAE parameters
ddconfig = {'double_z': True, 'z_channels': 4, 'resolution': 256, 'in_channels': 3, 'out_ch': 3, 'ch': 128, 'ch_mult': [1, 2, 4, 4], 'num_res_blocks': 2, 'attn_resolutions': [], 'dropout': 0.0}
if 'encoder.down.2.downsample.conv.weight' not in sd and 'decoder.up.3.upsample.conv.weight' not in sd: #Stable diffusion x4 upscaler VAE
ddconfig['ch_mult'] = [1, 2, 4]
self.downscale_ratio = 4
self.upscale_ratio = 4
self.latent_channels = ddconfig['z_channels'] = sd["decoder.conv_in.weight"].shape[1]
if 'post_quant_conv.weight' in sd:
self.first_stage_model = AutoencoderKL(ddconfig=ddconfig, embed_dim=sd['post_quant_conv.weight'].shape[1])
else:
if sd['decoder.conv_in.weight'].shape[1] == 64:
ddconfig = {"block_out_channels": [128, 256, 512, 512, 1024, 1024], "in_channels": 3, "out_channels": 3, "num_res_blocks": 2, "ffactor_spatial": 32, "downsample_match_channel": True, "upsample_match_channel": True}
self.latent_channels = ddconfig['z_channels'] = sd["decoder.conv_in.weight"].shape[1]
self.downscale_ratio = 32
self.upscale_ratio = 32
self.working_dtypes = [torch.float16, torch.bfloat16, torch.float32]
self.first_stage_model = AutoencodingEngine(regularizer_config={'target': "comfy.ldm.models.autoencoder.DiagonalGaussianRegularizer"},
encoder_config={'target': "comfy.ldm.modules.diffusionmodules.model.Encoder", 'params': ddconfig},
decoder_config={'target': "comfy.ldm.modules.diffusionmodules.model.Decoder", 'params': ddconfig})
encoder_config={'target': "comfy.ldm.hunyuan_video.vae.Encoder", 'params': ddconfig},
decoder_config={'target': "comfy.ldm.hunyuan_video.vae.Decoder", 'params': ddconfig})
self.memory_used_encode = lambda shape, dtype: (700 * shape[2] * shape[3]) * model_management.dtype_size(dtype)
self.memory_used_decode = lambda shape, dtype: (700 * shape[2] * shape[3] * 32 * 32) * model_management.dtype_size(dtype)
elif sd['decoder.conv_in.weight'].shape[1] == 32:
ddconfig = {"block_out_channels": [128, 256, 512, 1024, 1024], "in_channels": 3, "out_channels": 3, "num_res_blocks": 2, "ffactor_spatial": 16, "ffactor_temporal": 4, "downsample_match_channel": True, "upsample_match_channel": True, "refiner_vae": False}
self.latent_channels = ddconfig['z_channels'] = sd["decoder.conv_in.weight"].shape[1]
self.working_dtypes = [torch.float16, torch.bfloat16, torch.float32]
self.upscale_ratio = (lambda a: max(0, a * 4 - 3), 16, 16)
self.upscale_index_formula = (4, 16, 16)
self.downscale_ratio = (lambda a: max(0, math.floor((a + 3) / 4)), 16, 16)
self.downscale_index_formula = (4, 16, 16)
self.latent_dim = 3
self.not_video = True
self.first_stage_model = AutoencodingEngine(regularizer_config={'target': "comfy.ldm.models.autoencoder.DiagonalGaussianRegularizer"},
encoder_config={'target': "comfy.ldm.hunyuan_video.vae_refiner.Encoder", 'params': ddconfig},
decoder_config={'target': "comfy.ldm.hunyuan_video.vae_refiner.Decoder", 'params': ddconfig})
self.memory_used_encode = lambda shape, dtype: (2800 * shape[-2] * shape[-1]) * model_management.dtype_size(dtype)
self.memory_used_decode = lambda shape, dtype: (2800 * shape[-3] * shape[-2] * shape[-1] * 16 * 16) * model_management.dtype_size(dtype)
else:
#default SD1.x/SD2.x VAE parameters
ddconfig = {'double_z': True, 'z_channels': 4, 'resolution': 256, 'in_channels': 3, 'out_ch': 3, 'ch': 128, 'ch_mult': [1, 2, 4, 4], 'num_res_blocks': 2, 'attn_resolutions': [], 'dropout': 0.0}
if 'encoder.down.2.downsample.conv.weight' not in sd and 'decoder.up.3.upsample.conv.weight' not in sd: #Stable diffusion x4 upscaler VAE
ddconfig['ch_mult'] = [1, 2, 4]
self.downscale_ratio = 4
self.upscale_ratio = 4
self.latent_channels = ddconfig['z_channels'] = sd["decoder.conv_in.weight"].shape[1]
if 'post_quant_conv.weight' in sd:
self.first_stage_model = AutoencoderKL(ddconfig=ddconfig, embed_dim=sd['post_quant_conv.weight'].shape[1])
else:
self.first_stage_model = AutoencodingEngine(regularizer_config={'target': "comfy.ldm.models.autoencoder.DiagonalGaussianRegularizer"},
encoder_config={'target': "comfy.ldm.modules.diffusionmodules.model.Encoder", 'params': ddconfig},
decoder_config={'target': "comfy.ldm.modules.diffusionmodules.model.Decoder", 'params': ddconfig})
elif "decoder.layers.1.layers.0.beta" in sd:
self.first_stage_model = AudioOobleckVAE()
self.memory_used_encode = lambda shape, dtype: (1000 * shape[2]) * model_management.dtype_size(dtype)