dc-ae-f64c128-in-1.0-diffusers

Name: dc-ae-f64c128-in-1.0-diffusers
Author: mit-han-lab

2.7K

—

mit-han-lab

Other

OTHER

New

3K downloads

Early-stage

Try on Hugging Face Add to Compare

Edge AI:

Mobile

Laptop

Server

Unknown

Mobile

Laptop

Server

Quick Summary

Deep Compression Autoencoder for Efficient High-Resolution Diffusion Models Figure 1: We address the reconstruction accuracy drop of high spatial-compression autoencoders.

Code Examples

decodepythonpytorch

# build DC-AE-Diffusion models
# full DC-AE-Diffusion model list: https://huggingface.co/collections/mit-han-lab/dc-ae-diffusion-670dbb8d6b6914cf24c1a49d
from efficientvit.diffusion_model_zoo import DCAE_Diffusion_HF

dc_ae_diffusion = DCAE_Diffusion_HF.from_pretrained(f"mit-han-lab/dc-ae-f64c128-in-1.0-uvit-h-in-512px-train2000k")

# denoising on the latent space
import torch
import numpy as np
from torchvision.utils import save_image

torch.set_grad_enabled(False)
device = torch.device("cuda")
dc_ae_diffusion = dc_ae_diffusion.to(device).eval()

seed = 0
torch.manual_seed(seed)
torch.cuda.manual_seed_all(seed)
eval_generator = torch.Generator(device=device)
eval_generator.manual_seed(seed)

prompts = torch.tensor(
    [279, 333, 979, 936, 933, 145, 497, 1, 248, 360, 793, 12, 387, 437, 938, 978], dtype=torch.int, device=device
)
num_samples = prompts.shape[0]
prompts_null = 1000 * torch.ones((num_samples,), dtype=torch.int, device=device)
latent_samples = dc_ae_diffusion.diffusion_model.generate(prompts, prompts_null, 6.0, eval_generator)
latent_samples = latent_samples / dc_ae_diffusion.scaling_factor

# decode
image_samples = dc_ae_diffusion.autoencoder.decode(latent_samples)
save_image(image_samples * 0.5 + 0.5, "demo_dc_ae_diffusion.png", nrow=int(np.sqrt(num_samples)))

decodepythonpytorch

# build DC-AE-Diffusion models
# full DC-AE-Diffusion model list: https://huggingface.co/collections/mit-han-lab/dc-ae-diffusion-670dbb8d6b6914cf24c1a49d
from efficientvit.diffusion_model_zoo import DCAE_Diffusion_HF

dc_ae_diffusion = DCAE_Diffusion_HF.from_pretrained(f"mit-han-lab/dc-ae-f64c128-in-1.0-uvit-h-in-512px-train2000k")

# denoising on the latent space
import torch
import numpy as np
from torchvision.utils import save_image

torch.set_grad_enabled(False)
device = torch.device("cuda")
dc_ae_diffusion = dc_ae_diffusion.to(device).eval()

seed = 0
torch.manual_seed(seed)
torch.cuda.manual_seed_all(seed)
eval_generator = torch.Generator(device=device)
eval_generator.manual_seed(seed)

prompts = torch.tensor(
    [279, 333, 979, 936, 933, 145, 497, 1, 248, 360, 793, 12, 387, 437, 938, 978], dtype=torch.int, device=device
)
num_samples = prompts.shape[0]
prompts_null = 1000 * torch.ones((num_samples,), dtype=torch.int, device=device)
latent_samples = dc_ae_diffusion.diffusion_model.generate(prompts, prompts_null, 6.0, eval_generator)
latent_samples = latent_samples / dc_ae_diffusion.scaling_factor

# decode
image_samples = dc_ae_diffusion.autoencoder.decode(latent_samples)
save_image(image_samples * 0.5 + 0.5, "demo_dc_ae_diffusion.png", nrow=int(np.sqrt(num_samples)))

decodepythonpytorch

# build DC-AE-Diffusion models
# full DC-AE-Diffusion model list: https://huggingface.co/collections/mit-han-lab/dc-ae-diffusion-670dbb8d6b6914cf24c1a49d
from efficientvit.diffusion_model_zoo import DCAE_Diffusion_HF

dc_ae_diffusion = DCAE_Diffusion_HF.from_pretrained(f"mit-han-lab/dc-ae-f64c128-in-1.0-uvit-h-in-512px-train2000k")

# denoising on the latent space
import torch
import numpy as np
from torchvision.utils import save_image

torch.set_grad_enabled(False)
device = torch.device("cuda")
dc_ae_diffusion = dc_ae_diffusion.to(device).eval()

seed = 0
torch.manual_seed(seed)
torch.cuda.manual_seed_all(seed)
eval_generator = torch.Generator(device=device)
eval_generator.manual_seed(seed)

prompts = torch.tensor(
    [279, 333, 979, 936, 933, 145, 497, 1, 248, 360, 793, 12, 387, 437, 938, 978], dtype=torch.int, device=device
)
num_samples = prompts.shape[0]
prompts_null = 1000 * torch.ones((num_samples,), dtype=torch.int, device=device)
latent_samples = dc_ae_diffusion.diffusion_model.generate(prompts, prompts_null, 6.0, eval_generator)
latent_samples = latent_samples / dc_ae_diffusion.scaling_factor

# decode
image_samples = dc_ae_diffusion.autoencoder.decode(latent_samples)
save_image(image_samples * 0.5 + 0.5, "demo_dc_ae_diffusion.png", nrow=int(np.sqrt(num_samples)))

decodepythonpytorch

# build DC-AE-Diffusion models
# full DC-AE-Diffusion model list: https://huggingface.co/collections/mit-han-lab/dc-ae-diffusion-670dbb8d6b6914cf24c1a49d
from efficientvit.diffusion_model_zoo import DCAE_Diffusion_HF

dc_ae_diffusion = DCAE_Diffusion_HF.from_pretrained(f"mit-han-lab/dc-ae-f64c128-in-1.0-uvit-h-in-512px-train2000k")

# denoising on the latent space
import torch
import numpy as np
from torchvision.utils import save_image

torch.set_grad_enabled(False)
device = torch.device("cuda")
dc_ae_diffusion = dc_ae_diffusion.to(device).eval()

seed = 0
torch.manual_seed(seed)
torch.cuda.manual_seed_all(seed)
eval_generator = torch.Generator(device=device)
eval_generator.manual_seed(seed)

prompts = torch.tensor(
    [279, 333, 979, 936, 933, 145, 497, 1, 248, 360, 793, 12, 387, 437, 938, 978], dtype=torch.int, device=device
)
num_samples = prompts.shape[0]
prompts_null = 1000 * torch.ones((num_samples,), dtype=torch.int, device=device)
latent_samples = dc_ae_diffusion.diffusion_model.generate(prompts, prompts_null, 6.0, eval_generator)
latent_samples = latent_samples / dc_ae_diffusion.scaling_factor

# decode
image_samples = dc_ae_diffusion.autoencoder.decode(latent_samples)
save_image(image_samples * 0.5 + 0.5, "demo_dc_ae_diffusion.png", nrow=int(np.sqrt(num_samples)))

decodepythonpytorch

# build DC-AE-Diffusion models
# full DC-AE-Diffusion model list: https://huggingface.co/collections/mit-han-lab/dc-ae-diffusion-670dbb8d6b6914cf24c1a49d
from efficientvit.diffusion_model_zoo import DCAE_Diffusion_HF

dc_ae_diffusion = DCAE_Diffusion_HF.from_pretrained(f"mit-han-lab/dc-ae-f64c128-in-1.0-uvit-h-in-512px-train2000k")

# denoising on the latent space
import torch
import numpy as np
from torchvision.utils import save_image

torch.set_grad_enabled(False)
device = torch.device("cuda")
dc_ae_diffusion = dc_ae_diffusion.to(device).eval()

seed = 0
torch.manual_seed(seed)
torch.cuda.manual_seed_all(seed)
eval_generator = torch.Generator(device=device)
eval_generator.manual_seed(seed)

prompts = torch.tensor(
    [279, 333, 979, 936, 933, 145, 497, 1, 248, 360, 793, 12, 387, 437, 938, 978], dtype=torch.int, device=device
)
num_samples = prompts.shape[0]
prompts_null = 1000 * torch.ones((num_samples,), dtype=torch.int, device=device)
latent_samples = dc_ae_diffusion.diffusion_model.generate(prompts, prompts_null, 6.0, eval_generator)
latent_samples = latent_samples / dc_ae_diffusion.scaling_factor

# decode
image_samples = dc_ae_diffusion.autoencoder.decode(latent_samples)
save_image(image_samples * 0.5 + 0.5, "demo_dc_ae_diffusion.png", nrow=int(np.sqrt(num_samples)))

decodepythonpytorch

# build DC-AE-Diffusion models
# full DC-AE-Diffusion model list: https://huggingface.co/collections/mit-han-lab/dc-ae-diffusion-670dbb8d6b6914cf24c1a49d
from efficientvit.diffusion_model_zoo import DCAE_Diffusion_HF

dc_ae_diffusion = DCAE_Diffusion_HF.from_pretrained(f"mit-han-lab/dc-ae-f64c128-in-1.0-uvit-h-in-512px-train2000k")

# denoising on the latent space
import torch
import numpy as np
from torchvision.utils import save_image

torch.set_grad_enabled(False)
device = torch.device("cuda")
dc_ae_diffusion = dc_ae_diffusion.to(device).eval()

seed = 0
torch.manual_seed(seed)
torch.cuda.manual_seed_all(seed)
eval_generator = torch.Generator(device=device)
eval_generator.manual_seed(seed)

prompts = torch.tensor(
    [279, 333, 979, 936, 933, 145, 497, 1, 248, 360, 793, 12, 387, 437, 938, 978], dtype=torch.int, device=device
)
num_samples = prompts.shape[0]
prompts_null = 1000 * torch.ones((num_samples,), dtype=torch.int, device=device)
latent_samples = dc_ae_diffusion.diffusion_model.generate(prompts, prompts_null, 6.0, eval_generator)
latent_samples = latent_samples / dc_ae_diffusion.scaling_factor

# decode
image_samples = dc_ae_diffusion.autoencoder.decode(latent_samples)
save_image(image_samples * 0.5 + 0.5, "demo_dc_ae_diffusion.png", nrow=int(np.sqrt(num_samples)))

decodepythonpytorch

# build DC-AE-Diffusion models
# full DC-AE-Diffusion model list: https://huggingface.co/collections/mit-han-lab/dc-ae-diffusion-670dbb8d6b6914cf24c1a49d
from efficientvit.diffusion_model_zoo import DCAE_Diffusion_HF

dc_ae_diffusion = DCAE_Diffusion_HF.from_pretrained(f"mit-han-lab/dc-ae-f64c128-in-1.0-uvit-h-in-512px-train2000k")

# denoising on the latent space
import torch
import numpy as np
from torchvision.utils import save_image

torch.set_grad_enabled(False)
device = torch.device("cuda")
dc_ae_diffusion = dc_ae_diffusion.to(device).eval()

seed = 0
torch.manual_seed(seed)
torch.cuda.manual_seed_all(seed)
eval_generator = torch.Generator(device=device)
eval_generator.manual_seed(seed)

prompts = torch.tensor(
    [279, 333, 979, 936, 933, 145, 497, 1, 248, 360, 793, 12, 387, 437, 938, 978], dtype=torch.int, device=device
)
num_samples = prompts.shape[0]
prompts_null = 1000 * torch.ones((num_samples,), dtype=torch.int, device=device)
latent_samples = dc_ae_diffusion.diffusion_model.generate(prompts, prompts_null, 6.0, eval_generator)
latent_samples = latent_samples / dc_ae_diffusion.scaling_factor

# decode
image_samples = dc_ae_diffusion.autoencoder.decode(latent_samples)
save_image(image_samples * 0.5 + 0.5, "demo_dc_ae_diffusion.png", nrow=int(np.sqrt(num_samples)))

decodepythonpytorch

# build DC-AE-Diffusion models
# full DC-AE-Diffusion model list: https://huggingface.co/collections/mit-han-lab/dc-ae-diffusion-670dbb8d6b6914cf24c1a49d
from efficientvit.diffusion_model_zoo import DCAE_Diffusion_HF

dc_ae_diffusion = DCAE_Diffusion_HF.from_pretrained(f"mit-han-lab/dc-ae-f64c128-in-1.0-uvit-h-in-512px-train2000k")

# denoising on the latent space
import torch
import numpy as np
from torchvision.utils import save_image

torch.set_grad_enabled(False)
device = torch.device("cuda")
dc_ae_diffusion = dc_ae_diffusion.to(device).eval()

seed = 0
torch.manual_seed(seed)
torch.cuda.manual_seed_all(seed)
eval_generator = torch.Generator(device=device)
eval_generator.manual_seed(seed)

prompts = torch.tensor(
    [279, 333, 979, 936, 933, 145, 497, 1, 248, 360, 793, 12, 387, 437, 938, 978], dtype=torch.int, device=device
)
num_samples = prompts.shape[0]
prompts_null = 1000 * torch.ones((num_samples,), dtype=torch.int, device=device)
latent_samples = dc_ae_diffusion.diffusion_model.generate(prompts, prompts_null, 6.0, eval_generator)
latent_samples = latent_samples / dc_ae_diffusion.scaling_factor

# decode
image_samples = dc_ae_diffusion.autoencoder.decode(latent_samples)
save_image(image_samples * 0.5 + 0.5, "demo_dc_ae_diffusion.png", nrow=int(np.sqrt(num_samples)))

decodepythonpytorch

# build DC-AE-Diffusion models
# full DC-AE-Diffusion model list: https://huggingface.co/collections/mit-han-lab/dc-ae-diffusion-670dbb8d6b6914cf24c1a49d
from efficientvit.diffusion_model_zoo import DCAE_Diffusion_HF

dc_ae_diffusion = DCAE_Diffusion_HF.from_pretrained(f"mit-han-lab/dc-ae-f64c128-in-1.0-uvit-h-in-512px-train2000k")

# denoising on the latent space
import torch
import numpy as np
from torchvision.utils import save_image

torch.set_grad_enabled(False)
device = torch.device("cuda")
dc_ae_diffusion = dc_ae_diffusion.to(device).eval()

seed = 0
torch.manual_seed(seed)
torch.cuda.manual_seed_all(seed)
eval_generator = torch.Generator(device=device)
eval_generator.manual_seed(seed)

prompts = torch.tensor(
    [279, 333, 979, 936, 933, 145, 497, 1, 248, 360, 793, 12, 387, 437, 938, 978], dtype=torch.int, device=device
)
num_samples = prompts.shape[0]
prompts_null = 1000 * torch.ones((num_samples,), dtype=torch.int, device=device)
latent_samples = dc_ae_diffusion.diffusion_model.generate(prompts, prompts_null, 6.0, eval_generator)
latent_samples = latent_samples / dc_ae_diffusion.scaling_factor

# decode
image_samples = dc_ae_diffusion.autoencoder.decode(latent_samples)
save_image(image_samples * 0.5 + 0.5, "demo_dc_ae_diffusion.png", nrow=int(np.sqrt(num_samples)))

decodepythonpytorch

# build DC-AE-Diffusion models
# full DC-AE-Diffusion model list: https://huggingface.co/collections/mit-han-lab/dc-ae-diffusion-670dbb8d6b6914cf24c1a49d
from efficientvit.diffusion_model_zoo import DCAE_Diffusion_HF

dc_ae_diffusion = DCAE_Diffusion_HF.from_pretrained(f"mit-han-lab/dc-ae-f64c128-in-1.0-uvit-h-in-512px-train2000k")

# denoising on the latent space
import torch
import numpy as np
from torchvision.utils import save_image

torch.set_grad_enabled(False)
device = torch.device("cuda")
dc_ae_diffusion = dc_ae_diffusion.to(device).eval()

seed = 0
torch.manual_seed(seed)
torch.cuda.manual_seed_all(seed)
eval_generator = torch.Generator(device=device)
eval_generator.manual_seed(seed)

prompts = torch.tensor(
    [279, 333, 979, 936, 933, 145, 497, 1, 248, 360, 793, 12, 387, 437, 938, 978], dtype=torch.int, device=device
)
num_samples = prompts.shape[0]
prompts_null = 1000 * torch.ones((num_samples,), dtype=torch.int, device=device)
latent_samples = dc_ae_diffusion.diffusion_model.generate(prompts, prompts_null, 6.0, eval_generator)
latent_samples = latent_samples / dc_ae_diffusion.scaling_factor

# decode
image_samples = dc_ae_diffusion.autoencoder.decode(latent_samples)
save_image(image_samples * 0.5 + 0.5, "demo_dc_ae_diffusion.png", nrow=int(np.sqrt(num_samples)))

decodepythonpytorch

# build DC-AE-Diffusion models
# full DC-AE-Diffusion model list: https://huggingface.co/collections/mit-han-lab/dc-ae-diffusion-670dbb8d6b6914cf24c1a49d
from efficientvit.diffusion_model_zoo import DCAE_Diffusion_HF

dc_ae_diffusion = DCAE_Diffusion_HF.from_pretrained(f"mit-han-lab/dc-ae-f64c128-in-1.0-uvit-h-in-512px-train2000k")

# denoising on the latent space
import torch
import numpy as np
from torchvision.utils import save_image

torch.set_grad_enabled(False)
device = torch.device("cuda")
dc_ae_diffusion = dc_ae_diffusion.to(device).eval()

seed = 0
torch.manual_seed(seed)
torch.cuda.manual_seed_all(seed)
eval_generator = torch.Generator(device=device)
eval_generator.manual_seed(seed)

prompts = torch.tensor(
    [279, 333, 979, 936, 933, 145, 497, 1, 248, 360, 793, 12, 387, 437, 938, 978], dtype=torch.int, device=device
)
num_samples = prompts.shape[0]
prompts_null = 1000 * torch.ones((num_samples,), dtype=torch.int, device=device)
latent_samples = dc_ae_diffusion.diffusion_model.generate(prompts, prompts_null, 6.0, eval_generator)
latent_samples = latent_samples / dc_ae_diffusion.scaling_factor

# decode
image_samples = dc_ae_diffusion.autoencoder.decode(latent_samples)
save_image(image_samples * 0.5 + 0.5, "demo_dc_ae_diffusion.png", nrow=int(np.sqrt(num_samples)))

decodepythonpytorch

# build DC-AE-Diffusion models
# full DC-AE-Diffusion model list: https://huggingface.co/collections/mit-han-lab/dc-ae-diffusion-670dbb8d6b6914cf24c1a49d
from efficientvit.diffusion_model_zoo import DCAE_Diffusion_HF

dc_ae_diffusion = DCAE_Diffusion_HF.from_pretrained(f"mit-han-lab/dc-ae-f64c128-in-1.0-uvit-h-in-512px-train2000k")

# denoising on the latent space
import torch
import numpy as np
from torchvision.utils import save_image

torch.set_grad_enabled(False)
device = torch.device("cuda")
dc_ae_diffusion = dc_ae_diffusion.to(device).eval()

seed = 0
torch.manual_seed(seed)
torch.cuda.manual_seed_all(seed)
eval_generator = torch.Generator(device=device)
eval_generator.manual_seed(seed)

prompts = torch.tensor(
    [279, 333, 979, 936, 933, 145, 497, 1, 248, 360, 793, 12, 387, 437, 938, 978], dtype=torch.int, device=device
)
num_samples = prompts.shape[0]
prompts_null = 1000 * torch.ones((num_samples,), dtype=torch.int, device=device)
latent_samples = dc_ae_diffusion.diffusion_model.generate(prompts, prompts_null, 6.0, eval_generator)
latent_samples = latent_samples / dc_ae_diffusion.scaling_factor

# decode
image_samples = dc_ae_diffusion.autoencoder.decode(latent_samples)
save_image(image_samples * 0.5 + 0.5, "demo_dc_ae_diffusion.png", nrow=int(np.sqrt(num_samples)))

decodepythonpytorch

# build DC-AE-Diffusion models
# full DC-AE-Diffusion model list: https://huggingface.co/collections/mit-han-lab/dc-ae-diffusion-670dbb8d6b6914cf24c1a49d
from efficientvit.diffusion_model_zoo import DCAE_Diffusion_HF

dc_ae_diffusion = DCAE_Diffusion_HF.from_pretrained(f"mit-han-lab/dc-ae-f64c128-in-1.0-uvit-h-in-512px-train2000k")

# denoising on the latent space
import torch
import numpy as np
from torchvision.utils import save_image

torch.set_grad_enabled(False)
device = torch.device("cuda")
dc_ae_diffusion = dc_ae_diffusion.to(device).eval()

seed = 0
torch.manual_seed(seed)
torch.cuda.manual_seed_all(seed)
eval_generator = torch.Generator(device=device)
eval_generator.manual_seed(seed)

prompts = torch.tensor(
    [279, 333, 979, 936, 933, 145, 497, 1, 248, 360, 793, 12, 387, 437, 938, 978], dtype=torch.int, device=device
)
num_samples = prompts.shape[0]
prompts_null = 1000 * torch.ones((num_samples,), dtype=torch.int, device=device)
latent_samples = dc_ae_diffusion.diffusion_model.generate(prompts, prompts_null, 6.0, eval_generator)
latent_samples = latent_samples / dc_ae_diffusion.scaling_factor

# decode
image_samples = dc_ae_diffusion.autoencoder.decode(latent_samples)
save_image(image_samples * 0.5 + 0.5, "demo_dc_ae_diffusion.png", nrow=int(np.sqrt(num_samples)))

decodepythonpytorch

# build DC-AE-Diffusion models
# full DC-AE-Diffusion model list: https://huggingface.co/collections/mit-han-lab/dc-ae-diffusion-670dbb8d6b6914cf24c1a49d
from efficientvit.diffusion_model_zoo import DCAE_Diffusion_HF

dc_ae_diffusion = DCAE_Diffusion_HF.from_pretrained(f"mit-han-lab/dc-ae-f64c128-in-1.0-uvit-h-in-512px-train2000k")

# denoising on the latent space
import torch
import numpy as np
from torchvision.utils import save_image

torch.set_grad_enabled(False)
device = torch.device("cuda")
dc_ae_diffusion = dc_ae_diffusion.to(device).eval()

seed = 0
torch.manual_seed(seed)
torch.cuda.manual_seed_all(seed)
eval_generator = torch.Generator(device=device)
eval_generator.manual_seed(seed)

prompts = torch.tensor(
    [279, 333, 979, 936, 933, 145, 497, 1, 248, 360, 793, 12, 387, 437, 938, 978], dtype=torch.int, device=device
)
num_samples = prompts.shape[0]
prompts_null = 1000 * torch.ones((num_samples,), dtype=torch.int, device=device)
latent_samples = dc_ae_diffusion.diffusion_model.generate(prompts, prompts_null, 6.0, eval_generator)
latent_samples = latent_samples / dc_ae_diffusion.scaling_factor

# decode
image_samples = dc_ae_diffusion.autoencoder.decode(latent_samples)
save_image(image_samples * 0.5 + 0.5, "demo_dc_ae_diffusion.png", nrow=int(np.sqrt(num_samples)))

decodepythonpytorch

# build DC-AE-Diffusion models
# full DC-AE-Diffusion model list: https://huggingface.co/collections/mit-han-lab/dc-ae-diffusion-670dbb8d6b6914cf24c1a49d
from efficientvit.diffusion_model_zoo import DCAE_Diffusion_HF

dc_ae_diffusion = DCAE_Diffusion_HF.from_pretrained(f"mit-han-lab/dc-ae-f64c128-in-1.0-uvit-h-in-512px-train2000k")

# denoising on the latent space
import torch
import numpy as np
from torchvision.utils import save_image

torch.set_grad_enabled(False)
device = torch.device("cuda")
dc_ae_diffusion = dc_ae_diffusion.to(device).eval()

seed = 0
torch.manual_seed(seed)
torch.cuda.manual_seed_all(seed)
eval_generator = torch.Generator(device=device)
eval_generator.manual_seed(seed)

prompts = torch.tensor(
    [279, 333, 979, 936, 933, 145, 497, 1, 248, 360, 793, 12, 387, 437, 938, 978], dtype=torch.int, device=device
)
num_samples = prompts.shape[0]
prompts_null = 1000 * torch.ones((num_samples,), dtype=torch.int, device=device)
latent_samples = dc_ae_diffusion.diffusion_model.generate(prompts, prompts_null, 6.0, eval_generator)
latent_samples = latent_samples / dc_ae_diffusion.scaling_factor

# decode
image_samples = dc_ae_diffusion.autoencoder.decode(latent_samples)
save_image(image_samples * 0.5 + 0.5, "demo_dc_ae_diffusion.png", nrow=int(np.sqrt(num_samples)))

decodepythonpytorch

# build DC-AE-Diffusion models
# full DC-AE-Diffusion model list: https://huggingface.co/collections/mit-han-lab/dc-ae-diffusion-670dbb8d6b6914cf24c1a49d
from efficientvit.diffusion_model_zoo import DCAE_Diffusion_HF

dc_ae_diffusion = DCAE_Diffusion_HF.from_pretrained(f"mit-han-lab/dc-ae-f64c128-in-1.0-uvit-h-in-512px-train2000k")

# denoising on the latent space
import torch
import numpy as np
from torchvision.utils import save_image

torch.set_grad_enabled(False)
device = torch.device("cuda")
dc_ae_diffusion = dc_ae_diffusion.to(device).eval()

seed = 0
torch.manual_seed(seed)
torch.cuda.manual_seed_all(seed)
eval_generator = torch.Generator(device=device)
eval_generator.manual_seed(seed)

prompts = torch.tensor(
    [279, 333, 979, 936, 933, 145, 497, 1, 248, 360, 793, 12, 387, 437, 938, 978], dtype=torch.int, device=device
)
num_samples = prompts.shape[0]
prompts_null = 1000 * torch.ones((num_samples,), dtype=torch.int, device=device)
latent_samples = dc_ae_diffusion.diffusion_model.generate(prompts, prompts_null, 6.0, eval_generator)
latent_samples = latent_samples / dc_ae_diffusion.scaling_factor

# decode
image_samples = dc_ae_diffusion.autoencoder.decode(latent_samples)
save_image(image_samples * 0.5 + 0.5, "demo_dc_ae_diffusion.png", nrow=int(np.sqrt(num_samples)))

decodepythonpytorch

# build DC-AE-Diffusion models
# full DC-AE-Diffusion model list: https://huggingface.co/collections/mit-han-lab/dc-ae-diffusion-670dbb8d6b6914cf24c1a49d
from efficientvit.diffusion_model_zoo import DCAE_Diffusion_HF

dc_ae_diffusion = DCAE_Diffusion_HF.from_pretrained(f"mit-han-lab/dc-ae-f64c128-in-1.0-uvit-h-in-512px-train2000k")

# denoising on the latent space
import torch
import numpy as np
from torchvision.utils import save_image

torch.set_grad_enabled(False)
device = torch.device("cuda")
dc_ae_diffusion = dc_ae_diffusion.to(device).eval()

seed = 0
torch.manual_seed(seed)
torch.cuda.manual_seed_all(seed)
eval_generator = torch.Generator(device=device)
eval_generator.manual_seed(seed)

prompts = torch.tensor(
    [279, 333, 979, 936, 933, 145, 497, 1, 248, 360, 793, 12, 387, 437, 938, 978], dtype=torch.int, device=device
)
num_samples = prompts.shape[0]
prompts_null = 1000 * torch.ones((num_samples,), dtype=torch.int, device=device)
latent_samples = dc_ae_diffusion.diffusion_model.generate(prompts, prompts_null, 6.0, eval_generator)
latent_samples = latent_samples / dc_ae_diffusion.scaling_factor

# decode
image_samples = dc_ae_diffusion.autoencoder.decode(latent_samples)
save_image(image_samples * 0.5 + 0.5, "demo_dc_ae_diffusion.png", nrow=int(np.sqrt(num_samples)))

decodepythonpytorch

# build DC-AE-Diffusion models
# full DC-AE-Diffusion model list: https://huggingface.co/collections/mit-han-lab/dc-ae-diffusion-670dbb8d6b6914cf24c1a49d
from efficientvit.diffusion_model_zoo import DCAE_Diffusion_HF

dc_ae_diffusion = DCAE_Diffusion_HF.from_pretrained(f"mit-han-lab/dc-ae-f64c128-in-1.0-uvit-h-in-512px-train2000k")

# denoising on the latent space
import torch
import numpy as np
from torchvision.utils import save_image

torch.set_grad_enabled(False)
device = torch.device("cuda")
dc_ae_diffusion = dc_ae_diffusion.to(device).eval()

seed = 0
torch.manual_seed(seed)
torch.cuda.manual_seed_all(seed)
eval_generator = torch.Generator(device=device)
eval_generator.manual_seed(seed)

prompts = torch.tensor(
    [279, 333, 979, 936, 933, 145, 497, 1, 248, 360, 793, 12, 387, 437, 938, 978], dtype=torch.int, device=device
)
num_samples = prompts.shape[0]
prompts_null = 1000 * torch.ones((num_samples,), dtype=torch.int, device=device)
latent_samples = dc_ae_diffusion.diffusion_model.generate(prompts, prompts_null, 6.0, eval_generator)
latent_samples = latent_samples / dc_ae_diffusion.scaling_factor

# decode
image_samples = dc_ae_diffusion.autoencoder.decode(latent_samples)
save_image(image_samples * 0.5 + 0.5, "demo_dc_ae_diffusion.png", nrow=int(np.sqrt(num_samples)))

decodepythonpytorch

# build DC-AE-Diffusion models
# full DC-AE-Diffusion model list: https://huggingface.co/collections/mit-han-lab/dc-ae-diffusion-670dbb8d6b6914cf24c1a49d
from efficientvit.diffusion_model_zoo import DCAE_Diffusion_HF

dc_ae_diffusion = DCAE_Diffusion_HF.from_pretrained(f"mit-han-lab/dc-ae-f64c128-in-1.0-uvit-h-in-512px-train2000k")

# denoising on the latent space
import torch
import numpy as np
from torchvision.utils import save_image

torch.set_grad_enabled(False)
device = torch.device("cuda")
dc_ae_diffusion = dc_ae_diffusion.to(device).eval()

seed = 0
torch.manual_seed(seed)
torch.cuda.manual_seed_all(seed)
eval_generator = torch.Generator(device=device)
eval_generator.manual_seed(seed)

prompts = torch.tensor(
    [279, 333, 979, 936, 933, 145, 497, 1, 248, 360, 793, 12, 387, 437, 938, 978], dtype=torch.int, device=device
)
num_samples = prompts.shape[0]
prompts_null = 1000 * torch.ones((num_samples,), dtype=torch.int, device=device)
latent_samples = dc_ae_diffusion.diffusion_model.generate(prompts, prompts_null, 6.0, eval_generator)
latent_samples = latent_samples / dc_ae_diffusion.scaling_factor

# decode
image_samples = dc_ae_diffusion.autoencoder.decode(latent_samples)
save_image(image_samples * 0.5 + 0.5, "demo_dc_ae_diffusion.png", nrow=int(np.sqrt(num_samples)))

decodepythonpytorch

# build DC-AE-Diffusion models
# full DC-AE-Diffusion model list: https://huggingface.co/collections/mit-han-lab/dc-ae-diffusion-670dbb8d6b6914cf24c1a49d
from efficientvit.diffusion_model_zoo import DCAE_Diffusion_HF

dc_ae_diffusion = DCAE_Diffusion_HF.from_pretrained(f"mit-han-lab/dc-ae-f64c128-in-1.0-uvit-h-in-512px-train2000k")

# denoising on the latent space
import torch
import numpy as np
from torchvision.utils import save_image

torch.set_grad_enabled(False)
device = torch.device("cuda")
dc_ae_diffusion = dc_ae_diffusion.to(device).eval()

seed = 0
torch.manual_seed(seed)
torch.cuda.manual_seed_all(seed)
eval_generator = torch.Generator(device=device)
eval_generator.manual_seed(seed)

prompts = torch.tensor(
    [279, 333, 979, 936, 933, 145, 497, 1, 248, 360, 793, 12, 387, 437, 938, 978], dtype=torch.int, device=device
)
num_samples = prompts.shape[0]
prompts_null = 1000 * torch.ones((num_samples,), dtype=torch.int, device=device)
latent_samples = dc_ae_diffusion.diffusion_model.generate(prompts, prompts_null, 6.0, eval_generator)
latent_samples = latent_samples / dc_ae_diffusion.scaling_factor

# decode
image_samples = dc_ae_diffusion.autoencoder.decode(latent_samples)
save_image(image_samples * 0.5 + 0.5, "demo_dc_ae_diffusion.png", nrow=int(np.sqrt(num_samples)))

decodepythonpytorch

# build DC-AE-Diffusion models
# full DC-AE-Diffusion model list: https://huggingface.co/collections/mit-han-lab/dc-ae-diffusion-670dbb8d6b6914cf24c1a49d
from efficientvit.diffusion_model_zoo import DCAE_Diffusion_HF

dc_ae_diffusion = DCAE_Diffusion_HF.from_pretrained(f"mit-han-lab/dc-ae-f64c128-in-1.0-uvit-h-in-512px-train2000k")

# denoising on the latent space
import torch
import numpy as np
from torchvision.utils import save_image

torch.set_grad_enabled(False)
device = torch.device("cuda")
dc_ae_diffusion = dc_ae_diffusion.to(device).eval()

seed = 0
torch.manual_seed(seed)
torch.cuda.manual_seed_all(seed)
eval_generator = torch.Generator(device=device)
eval_generator.manual_seed(seed)

prompts = torch.tensor(
    [279, 333, 979, 936, 933, 145, 497, 1, 248, 360, 793, 12, 387, 437, 938, 978], dtype=torch.int, device=device
)
num_samples = prompts.shape[0]
prompts_null = 1000 * torch.ones((num_samples,), dtype=torch.int, device=device)
latent_samples = dc_ae_diffusion.diffusion_model.generate(prompts, prompts_null, 6.0, eval_generator)
latent_samples = latent_samples / dc_ae_diffusion.scaling_factor

# decode
image_samples = dc_ae_diffusion.autoencoder.decode(latent_samples)
save_image(image_samples * 0.5 + 0.5, "demo_dc_ae_diffusion.png", nrow=int(np.sqrt(num_samples)))

decodepythonpytorch

# build DC-AE-Diffusion models
# full DC-AE-Diffusion model list: https://huggingface.co/collections/mit-han-lab/dc-ae-diffusion-670dbb8d6b6914cf24c1a49d
from efficientvit.diffusion_model_zoo import DCAE_Diffusion_HF

dc_ae_diffusion = DCAE_Diffusion_HF.from_pretrained(f"mit-han-lab/dc-ae-f64c128-in-1.0-uvit-h-in-512px-train2000k")

# denoising on the latent space
import torch
import numpy as np
from torchvision.utils import save_image

torch.set_grad_enabled(False)
device = torch.device("cuda")
dc_ae_diffusion = dc_ae_diffusion.to(device).eval()

seed = 0
torch.manual_seed(seed)
torch.cuda.manual_seed_all(seed)
eval_generator = torch.Generator(device=device)
eval_generator.manual_seed(seed)

prompts = torch.tensor(
    [279, 333, 979, 936, 933, 145, 497, 1, 248, 360, 793, 12, 387, 437, 938, 978], dtype=torch.int, device=device
)
num_samples = prompts.shape[0]
prompts_null = 1000 * torch.ones((num_samples,), dtype=torch.int, device=device)
latent_samples = dc_ae_diffusion.diffusion_model.generate(prompts, prompts_null, 6.0, eval_generator)
latent_samples = latent_samples / dc_ae_diffusion.scaling_factor

# decode
image_samples = dc_ae_diffusion.autoencoder.decode(latent_samples)
save_image(image_samples * 0.5 + 0.5, "demo_dc_ae_diffusion.png", nrow=int(np.sqrt(num_samples)))

decodepythonpytorch

# build DC-AE-Diffusion models
# full DC-AE-Diffusion model list: https://huggingface.co/collections/mit-han-lab/dc-ae-diffusion-670dbb8d6b6914cf24c1a49d
from efficientvit.diffusion_model_zoo import DCAE_Diffusion_HF

dc_ae_diffusion = DCAE_Diffusion_HF.from_pretrained(f"mit-han-lab/dc-ae-f64c128-in-1.0-uvit-h-in-512px-train2000k")

# denoising on the latent space
import torch
import numpy as np
from torchvision.utils import save_image

torch.set_grad_enabled(False)
device = torch.device("cuda")
dc_ae_diffusion = dc_ae_diffusion.to(device).eval()

seed = 0
torch.manual_seed(seed)
torch.cuda.manual_seed_all(seed)
eval_generator = torch.Generator(device=device)
eval_generator.manual_seed(seed)

prompts = torch.tensor(
    [279, 333, 979, 936, 933, 145, 497, 1, 248, 360, 793, 12, 387, 437, 938, 978], dtype=torch.int, device=device
)
num_samples = prompts.shape[0]
prompts_null = 1000 * torch.ones((num_samples,), dtype=torch.int, device=device)
latent_samples = dc_ae_diffusion.diffusion_model.generate(prompts, prompts_null, 6.0, eval_generator)
latent_samples = latent_samples / dc_ae_diffusion.scaling_factor

# decode
image_samples = dc_ae_diffusion.autoencoder.decode(latent_samples)
save_image(image_samples * 0.5 + 0.5, "demo_dc_ae_diffusion.png", nrow=int(np.sqrt(num_samples)))

decodepythonpytorch

# build DC-AE-Diffusion models
# full DC-AE-Diffusion model list: https://huggingface.co/collections/mit-han-lab/dc-ae-diffusion-670dbb8d6b6914cf24c1a49d
from efficientvit.diffusion_model_zoo import DCAE_Diffusion_HF

dc_ae_diffusion = DCAE_Diffusion_HF.from_pretrained(f"mit-han-lab/dc-ae-f64c128-in-1.0-uvit-h-in-512px-train2000k")

# denoising on the latent space
import torch
import numpy as np
from torchvision.utils import save_image

torch.set_grad_enabled(False)
device = torch.device("cuda")
dc_ae_diffusion = dc_ae_diffusion.to(device).eval()

seed = 0
torch.manual_seed(seed)
torch.cuda.manual_seed_all(seed)
eval_generator = torch.Generator(device=device)
eval_generator.manual_seed(seed)

prompts = torch.tensor(
    [279, 333, 979, 936, 933, 145, 497, 1, 248, 360, 793, 12, 387, 437, 938, 978], dtype=torch.int, device=device
)
num_samples = prompts.shape[0]
prompts_null = 1000 * torch.ones((num_samples,), dtype=torch.int, device=device)
latent_samples = dc_ae_diffusion.diffusion_model.generate(prompts, prompts_null, 6.0, eval_generator)
latent_samples = latent_samples / dc_ae_diffusion.scaling_factor

# decode
image_samples = dc_ae_diffusion.autoencoder.decode(latent_samples)
save_image(image_samples * 0.5 + 0.5, "demo_dc_ae_diffusion.png", nrow=int(np.sqrt(num_samples)))

decodepythonpytorch

# build DC-AE-Diffusion models
# full DC-AE-Diffusion model list: https://huggingface.co/collections/mit-han-lab/dc-ae-diffusion-670dbb8d6b6914cf24c1a49d
from efficientvit.diffusion_model_zoo import DCAE_Diffusion_HF

dc_ae_diffusion = DCAE_Diffusion_HF.from_pretrained(f"mit-han-lab/dc-ae-f64c128-in-1.0-uvit-h-in-512px-train2000k")

# denoising on the latent space
import torch
import numpy as np
from torchvision.utils import save_image

torch.set_grad_enabled(False)
device = torch.device("cuda")
dc_ae_diffusion = dc_ae_diffusion.to(device).eval()

seed = 0
torch.manual_seed(seed)
torch.cuda.manual_seed_all(seed)
eval_generator = torch.Generator(device=device)
eval_generator.manual_seed(seed)

prompts = torch.tensor(
    [279, 333, 979, 936, 933, 145, 497, 1, 248, 360, 793, 12, 387, 437, 938, 978], dtype=torch.int, device=device
)
num_samples = prompts.shape[0]
prompts_null = 1000 * torch.ones((num_samples,), dtype=torch.int, device=device)
latent_samples = dc_ae_diffusion.diffusion_model.generate(prompts, prompts_null, 6.0, eval_generator)
latent_samples = latent_samples / dc_ae_diffusion.scaling_factor

# decode
image_samples = dc_ae_diffusion.autoencoder.decode(latent_samples)
save_image(image_samples * 0.5 + 0.5, "demo_dc_ae_diffusion.png", nrow=int(np.sqrt(num_samples)))

decodepythonpytorch

# build DC-AE-Diffusion models
# full DC-AE-Diffusion model list: https://huggingface.co/collections/mit-han-lab/dc-ae-diffusion-670dbb8d6b6914cf24c1a49d
from efficientvit.diffusion_model_zoo import DCAE_Diffusion_HF

dc_ae_diffusion = DCAE_Diffusion_HF.from_pretrained(f"mit-han-lab/dc-ae-f64c128-in-1.0-uvit-h-in-512px-train2000k")

# denoising on the latent space
import torch
import numpy as np
from torchvision.utils import save_image

torch.set_grad_enabled(False)
device = torch.device("cuda")
dc_ae_diffusion = dc_ae_diffusion.to(device).eval()

seed = 0
torch.manual_seed(seed)
torch.cuda.manual_seed_all(seed)
eval_generator = torch.Generator(device=device)
eval_generator.manual_seed(seed)

prompts = torch.tensor(
    [279, 333, 979, 936, 933, 145, 497, 1, 248, 360, 793, 12, 387, 437, 938, 978], dtype=torch.int, device=device
)
num_samples = prompts.shape[0]
prompts_null = 1000 * torch.ones((num_samples,), dtype=torch.int, device=device)
latent_samples = dc_ae_diffusion.diffusion_model.generate(prompts, prompts_null, 6.0, eval_generator)
latent_samples = latent_samples / dc_ae_diffusion.scaling_factor

# decode
image_samples = dc_ae_diffusion.autoencoder.decode(latent_samples)
save_image(image_samples * 0.5 + 0.5, "demo_dc_ae_diffusion.png", nrow=int(np.sqrt(num_samples)))

decodepythonpytorch

# build DC-AE-Diffusion models
# full DC-AE-Diffusion model list: https://huggingface.co/collections/mit-han-lab/dc-ae-diffusion-670dbb8d6b6914cf24c1a49d
from efficientvit.diffusion_model_zoo import DCAE_Diffusion_HF

dc_ae_diffusion = DCAE_Diffusion_HF.from_pretrained(f"mit-han-lab/dc-ae-f64c128-in-1.0-uvit-h-in-512px-train2000k")

# denoising on the latent space
import torch
import numpy as np
from torchvision.utils import save_image

torch.set_grad_enabled(False)
device = torch.device("cuda")
dc_ae_diffusion = dc_ae_diffusion.to(device).eval()

seed = 0
torch.manual_seed(seed)
torch.cuda.manual_seed_all(seed)
eval_generator = torch.Generator(device=device)
eval_generator.manual_seed(seed)

prompts = torch.tensor(
    [279, 333, 979, 936, 933, 145, 497, 1, 248, 360, 793, 12, 387, 437, 938, 978], dtype=torch.int, device=device
)
num_samples = prompts.shape[0]
prompts_null = 1000 * torch.ones((num_samples,), dtype=torch.int, device=device)
latent_samples = dc_ae_diffusion.diffusion_model.generate(prompts, prompts_null, 6.0, eval_generator)
latent_samples = latent_samples / dc_ae_diffusion.scaling_factor

# decode
image_samples = dc_ae_diffusion.autoencoder.decode(latent_samples)
save_image(image_samples * 0.5 + 0.5, "demo_dc_ae_diffusion.png", nrow=int(np.sqrt(num_samples)))

decodepythonpytorch

# build DC-AE-Diffusion models
# full DC-AE-Diffusion model list: https://huggingface.co/collections/mit-han-lab/dc-ae-diffusion-670dbb8d6b6914cf24c1a49d
from efficientvit.diffusion_model_zoo import DCAE_Diffusion_HF

dc_ae_diffusion = DCAE_Diffusion_HF.from_pretrained(f"mit-han-lab/dc-ae-f64c128-in-1.0-uvit-h-in-512px-train2000k")

# denoising on the latent space
import torch
import numpy as np
from torchvision.utils import save_image

torch.set_grad_enabled(False)
device = torch.device("cuda")
dc_ae_diffusion = dc_ae_diffusion.to(device).eval()

seed = 0
torch.manual_seed(seed)
torch.cuda.manual_seed_all(seed)
eval_generator = torch.Generator(device=device)
eval_generator.manual_seed(seed)

prompts = torch.tensor(
    [279, 333, 979, 936, 933, 145, 497, 1, 248, 360, 793, 12, 387, 437, 938, 978], dtype=torch.int, device=device
)
num_samples = prompts.shape[0]
prompts_null = 1000 * torch.ones((num_samples,), dtype=torch.int, device=device)
latent_samples = dc_ae_diffusion.diffusion_model.generate(prompts, prompts_null, 6.0, eval_generator)
latent_samples = latent_samples / dc_ae_diffusion.scaling_factor

# decode
image_samples = dc_ae_diffusion.autoencoder.decode(latent_samples)
save_image(image_samples * 0.5 + 0.5, "demo_dc_ae_diffusion.png", nrow=int(np.sqrt(num_samples)))

decodepythonpytorch

# build DC-AE-Diffusion models
# full DC-AE-Diffusion model list: https://huggingface.co/collections/mit-han-lab/dc-ae-diffusion-670dbb8d6b6914cf24c1a49d
from efficientvit.diffusion_model_zoo import DCAE_Diffusion_HF

dc_ae_diffusion = DCAE_Diffusion_HF.from_pretrained(f"mit-han-lab/dc-ae-f64c128-in-1.0-uvit-h-in-512px-train2000k")

# denoising on the latent space
import torch
import numpy as np
from torchvision.utils import save_image

torch.set_grad_enabled(False)
device = torch.device("cuda")
dc_ae_diffusion = dc_ae_diffusion.to(device).eval()

seed = 0
torch.manual_seed(seed)
torch.cuda.manual_seed_all(seed)
eval_generator = torch.Generator(device=device)
eval_generator.manual_seed(seed)

prompts = torch.tensor(
    [279, 333, 979, 936, 933, 145, 497, 1, 248, 360, 793, 12, 387, 437, 938, 978], dtype=torch.int, device=device
)
num_samples = prompts.shape[0]
prompts_null = 1000 * torch.ones((num_samples,), dtype=torch.int, device=device)
latent_samples = dc_ae_diffusion.diffusion_model.generate(prompts, prompts_null, 6.0, eval_generator)
latent_samples = latent_samples / dc_ae_diffusion.scaling_factor

# decode
image_samples = dc_ae_diffusion.autoencoder.decode(latent_samples)
save_image(image_samples * 0.5 + 0.5, "demo_dc_ae_diffusion.png", nrow=int(np.sqrt(num_samples)))

decodepythonpytorch

# build DC-AE-Diffusion models
# full DC-AE-Diffusion model list: https://huggingface.co/collections/mit-han-lab/dc-ae-diffusion-670dbb8d6b6914cf24c1a49d
from efficientvit.diffusion_model_zoo import DCAE_Diffusion_HF

dc_ae_diffusion = DCAE_Diffusion_HF.from_pretrained(f"mit-han-lab/dc-ae-f64c128-in-1.0-uvit-h-in-512px-train2000k")

# denoising on the latent space
import torch
import numpy as np
from torchvision.utils import save_image

torch.set_grad_enabled(False)
device = torch.device("cuda")
dc_ae_diffusion = dc_ae_diffusion.to(device).eval()

seed = 0
torch.manual_seed(seed)
torch.cuda.manual_seed_all(seed)
eval_generator = torch.Generator(device=device)
eval_generator.manual_seed(seed)

prompts = torch.tensor(
    [279, 333, 979, 936, 933, 145, 497, 1, 248, 360, 793, 12, 387, 437, 938, 978], dtype=torch.int, device=device
)
num_samples = prompts.shape[0]
prompts_null = 1000 * torch.ones((num_samples,), dtype=torch.int, device=device)
latent_samples = dc_ae_diffusion.diffusion_model.generate(prompts, prompts_null, 6.0, eval_generator)
latent_samples = latent_samples / dc_ae_diffusion.scaling_factor

# decode
image_samples = dc_ae_diffusion.autoencoder.decode(latent_samples)
save_image(image_samples * 0.5 + 0.5, "demo_dc_ae_diffusion.png", nrow=int(np.sqrt(num_samples)))

decodepythonpytorch

# build DC-AE-Diffusion models
# full DC-AE-Diffusion model list: https://huggingface.co/collections/mit-han-lab/dc-ae-diffusion-670dbb8d6b6914cf24c1a49d
from efficientvit.diffusion_model_zoo import DCAE_Diffusion_HF

dc_ae_diffusion = DCAE_Diffusion_HF.from_pretrained(f"mit-han-lab/dc-ae-f64c128-in-1.0-uvit-h-in-512px-train2000k")

# denoising on the latent space
import torch
import numpy as np
from torchvision.utils import save_image

torch.set_grad_enabled(False)
device = torch.device("cuda")
dc_ae_diffusion = dc_ae_diffusion.to(device).eval()

seed = 0
torch.manual_seed(seed)
torch.cuda.manual_seed_all(seed)
eval_generator = torch.Generator(device=device)
eval_generator.manual_seed(seed)

prompts = torch.tensor(
    [279, 333, 979, 936, 933, 145, 497, 1, 248, 360, 793, 12, 387, 437, 938, 978], dtype=torch.int, device=device
)
num_samples = prompts.shape[0]
prompts_null = 1000 * torch.ones((num_samples,), dtype=torch.int, device=device)
latent_samples = dc_ae_diffusion.diffusion_model.generate(prompts, prompts_null, 6.0, eval_generator)
latent_samples = latent_samples / dc_ae_diffusion.scaling_factor

# decode
image_samples = dc_ae_diffusion.autoencoder.decode(latent_samples)
save_image(image_samples * 0.5 + 0.5, "demo_dc_ae_diffusion.png", nrow=int(np.sqrt(num_samples)))

decodepythonpytorch

# build DC-AE-Diffusion models
# full DC-AE-Diffusion model list: https://huggingface.co/collections/mit-han-lab/dc-ae-diffusion-670dbb8d6b6914cf24c1a49d
from efficientvit.diffusion_model_zoo import DCAE_Diffusion_HF

dc_ae_diffusion = DCAE_Diffusion_HF.from_pretrained(f"mit-han-lab/dc-ae-f64c128-in-1.0-uvit-h-in-512px-train2000k")

# denoising on the latent space
import torch
import numpy as np
from torchvision.utils import save_image

torch.set_grad_enabled(False)
device = torch.device("cuda")
dc_ae_diffusion = dc_ae_diffusion.to(device).eval()

seed = 0
torch.manual_seed(seed)
torch.cuda.manual_seed_all(seed)
eval_generator = torch.Generator(device=device)
eval_generator.manual_seed(seed)

prompts = torch.tensor(
    [279, 333, 979, 936, 933, 145, 497, 1, 248, 360, 793, 12, 387, 437, 938, 978], dtype=torch.int, device=device
)
num_samples = prompts.shape[0]
prompts_null = 1000 * torch.ones((num_samples,), dtype=torch.int, device=device)
latent_samples = dc_ae_diffusion.diffusion_model.generate(prompts, prompts_null, 6.0, eval_generator)
latent_samples = latent_samples / dc_ae_diffusion.scaling_factor

# decode
image_samples = dc_ae_diffusion.autoencoder.decode(latent_samples)
save_image(image_samples * 0.5 + 0.5, "demo_dc_ae_diffusion.png", nrow=int(np.sqrt(num_samples)))

decodepythonpytorch

# build DC-AE-Diffusion models
# full DC-AE-Diffusion model list: https://huggingface.co/collections/mit-han-lab/dc-ae-diffusion-670dbb8d6b6914cf24c1a49d
from efficientvit.diffusion_model_zoo import DCAE_Diffusion_HF

dc_ae_diffusion = DCAE_Diffusion_HF.from_pretrained(f"mit-han-lab/dc-ae-f64c128-in-1.0-uvit-h-in-512px-train2000k")

# denoising on the latent space
import torch
import numpy as np
from torchvision.utils import save_image

torch.set_grad_enabled(False)
device = torch.device("cuda")
dc_ae_diffusion = dc_ae_diffusion.to(device).eval()

seed = 0
torch.manual_seed(seed)
torch.cuda.manual_seed_all(seed)
eval_generator = torch.Generator(device=device)
eval_generator.manual_seed(seed)

prompts = torch.tensor(
    [279, 333, 979, 936, 933, 145, 497, 1, 248, 360, 793, 12, 387, 437, 938, 978], dtype=torch.int, device=device
)
num_samples = prompts.shape[0]
prompts_null = 1000 * torch.ones((num_samples,), dtype=torch.int, device=device)
latent_samples = dc_ae_diffusion.diffusion_model.generate(prompts, prompts_null, 6.0, eval_generator)
latent_samples = latent_samples / dc_ae_diffusion.scaling_factor

# decode
image_samples = dc_ae_diffusion.autoencoder.decode(latent_samples)
save_image(image_samples * 0.5 + 0.5, "demo_dc_ae_diffusion.png", nrow=int(np.sqrt(num_samples)))

decodepythonpytorch

# build DC-AE-Diffusion models
# full DC-AE-Diffusion model list: https://huggingface.co/collections/mit-han-lab/dc-ae-diffusion-670dbb8d6b6914cf24c1a49d
from efficientvit.diffusion_model_zoo import DCAE_Diffusion_HF

dc_ae_diffusion = DCAE_Diffusion_HF.from_pretrained(f"mit-han-lab/dc-ae-f64c128-in-1.0-uvit-h-in-512px-train2000k")

# denoising on the latent space
import torch
import numpy as np
from torchvision.utils import save_image

torch.set_grad_enabled(False)
device = torch.device("cuda")
dc_ae_diffusion = dc_ae_diffusion.to(device).eval()

seed = 0
torch.manual_seed(seed)
torch.cuda.manual_seed_all(seed)
eval_generator = torch.Generator(device=device)
eval_generator.manual_seed(seed)

prompts = torch.tensor(
    [279, 333, 979, 936, 933, 145, 497, 1, 248, 360, 793, 12, 387, 437, 938, 978], dtype=torch.int, device=device
)
num_samples = prompts.shape[0]
prompts_null = 1000 * torch.ones((num_samples,), dtype=torch.int, device=device)
latent_samples = dc_ae_diffusion.diffusion_model.generate(prompts, prompts_null, 6.0, eval_generator)
latent_samples = latent_samples / dc_ae_diffusion.scaling_factor

# decode
image_samples = dc_ae_diffusion.autoencoder.decode(latent_samples)
save_image(image_samples * 0.5 + 0.5, "demo_dc_ae_diffusion.png", nrow=int(np.sqrt(num_samples)))

decodepythonpytorch

# build DC-AE-Diffusion models
# full DC-AE-Diffusion model list: https://huggingface.co/collections/mit-han-lab/dc-ae-diffusion-670dbb8d6b6914cf24c1a49d
from efficientvit.diffusion_model_zoo import DCAE_Diffusion_HF

dc_ae_diffusion = DCAE_Diffusion_HF.from_pretrained(f"mit-han-lab/dc-ae-f64c128-in-1.0-uvit-h-in-512px-train2000k")

# denoising on the latent space
import torch
import numpy as np
from torchvision.utils import save_image

torch.set_grad_enabled(False)
device = torch.device("cuda")
dc_ae_diffusion = dc_ae_diffusion.to(device).eval()

seed = 0
torch.manual_seed(seed)
torch.cuda.manual_seed_all(seed)
eval_generator = torch.Generator(device=device)
eval_generator.manual_seed(seed)

prompts = torch.tensor(
    [279, 333, 979, 936, 933, 145, 497, 1, 248, 360, 793, 12, 387, 437, 938, 978], dtype=torch.int, device=device
)
num_samples = prompts.shape[0]
prompts_null = 1000 * torch.ones((num_samples,), dtype=torch.int, device=device)
latent_samples = dc_ae_diffusion.diffusion_model.generate(prompts, prompts_null, 6.0, eval_generator)
latent_samples = latent_samples / dc_ae_diffusion.scaling_factor

# decode
image_samples = dc_ae_diffusion.autoencoder.decode(latent_samples)
save_image(image_samples * 0.5 + 0.5, "demo_dc_ae_diffusion.png", nrow=int(np.sqrt(num_samples)))

decodepythonpytorch

# build DC-AE-Diffusion models
# full DC-AE-Diffusion model list: https://huggingface.co/collections/mit-han-lab/dc-ae-diffusion-670dbb8d6b6914cf24c1a49d
from efficientvit.diffusion_model_zoo import DCAE_Diffusion_HF

dc_ae_diffusion = DCAE_Diffusion_HF.from_pretrained(f"mit-han-lab/dc-ae-f64c128-in-1.0-uvit-h-in-512px-train2000k")

# denoising on the latent space
import torch
import numpy as np
from torchvision.utils import save_image

torch.set_grad_enabled(False)
device = torch.device("cuda")
dc_ae_diffusion = dc_ae_diffusion.to(device).eval()

seed = 0
torch.manual_seed(seed)
torch.cuda.manual_seed_all(seed)
eval_generator = torch.Generator(device=device)
eval_generator.manual_seed(seed)

prompts = torch.tensor(
    [279, 333, 979, 936, 933, 145, 497, 1, 248, 360, 793, 12, 387, 437, 938, 978], dtype=torch.int, device=device
)
num_samples = prompts.shape[0]
prompts_null = 1000 * torch.ones((num_samples,), dtype=torch.int, device=device)
latent_samples = dc_ae_diffusion.diffusion_model.generate(prompts, prompts_null, 6.0, eval_generator)
latent_samples = latent_samples / dc_ae_diffusion.scaling_factor

# decode
image_samples = dc_ae_diffusion.autoencoder.decode(latent_samples)
save_image(image_samples * 0.5 + 0.5, "demo_dc_ae_diffusion.png", nrow=int(np.sqrt(num_samples)))

Deploy This Model

Production-ready deployment in minutes

Together.ai

Instant API access to this model

Fastest API

Production-ready inference API. Start free, scale to millions.

Try Free API

Replicate

One-click model deployment

Easiest Setup

Run models in the cloud with simple API. No DevOps required.

Deploy Now

Disclosure: We may earn a commission from these partners. This helps keep LLMYourWay free.