Hyper SD

import torch
from diffusers import FluxPipeline
from huggingface_hub import hf_hub_download
base_model_id = "black-forest-labs/FLUX.1-dev"
repo_name = "ByteDance/Hyper-SD"
# Take 8-steps lora as an example
ckpt_name = "Hyper-FLUX.1-dev-8steps-lora.safetensors"
# Load model, please fill in your access tokens since FLUX.1-dev repo is a gated model.
pipe = FluxPipeline.from_pretrained(base_model_id, token="xxx")
pipe.load_lora_weights(hf_hub_download(repo_name, ckpt_name))
pipe.fuse_lora(lora_scale=0.125)
pipe.to("cuda", dtype=torch.float16)
image=pipe(prompt="a photo of a cat", num_inference_steps=8, guidance_scale=3.5).images[0]
image.save("output.png")

import torch
from diffusers import StableDiffusion3Pipeline
from huggingface_hub import hf_hub_download
base_model_id = "stabilityai/stable-diffusion-3-medium-diffusers"
repo_name = "ByteDance/Hyper-SD"
# Take 8-steps lora as an example
ckpt_name = "Hyper-SD3-8steps-CFG-lora.safetensors"
# Load model, please fill in your access tokens since SD3 repo is a gated model.
pipe = StableDiffusion3Pipeline.from_pretrained(base_model_id, token="xxx")
pipe.load_lora_weights(hf_hub_download(repo_name, ckpt_name))
pipe.fuse_lora(lora_scale=0.125)
pipe.to("cuda", dtype=torch.float16)
image=pipe(prompt="a photo of a cat", num_inference_steps=8, guidance_scale=5.0).images[0]
image.save("output.png")

import torch
from diffusers import DiffusionPipeline, DDIMScheduler
from huggingface_hub import hf_hub_download
base_model_id = "stabilityai/stable-diffusion-xl-base-1.0"
repo_name = "ByteDance/Hyper-SD"
# Take 2-steps lora as an example
ckpt_name = "Hyper-SDXL-2steps-lora.safetensors"
# Load model.
pipe = DiffusionPipeline.from_pretrained(base_model_id, torch_dtype=torch.float16, variant="fp16").to("cuda")
pipe.load_lora_weights(hf_hub_download(repo_name, ckpt_name))
pipe.fuse_lora()
# Ensure ddim scheduler timestep spacing set as trailing !!!
pipe.scheduler = DDIMScheduler.from_config(pipe.scheduler.config, timestep_spacing="trailing")
# lower eta results in more detail
prompt="a photo of a cat"
image=pipe(prompt=prompt, num_inference_steps=2, guidance_scale=0).images[0]

import torch
from diffusers import DiffusionPipeline, TCDScheduler
from huggingface_hub import hf_hub_download
base_model_id = "stabilityai/stable-diffusion-xl-base-1.0"
repo_name = "ByteDance/Hyper-SD"
ckpt_name = "Hyper-SDXL-1step-lora.safetensors"
# Load model.
pipe = DiffusionPipeline.from_pretrained(base_model_id, torch_dtype=torch.float16, variant="fp16").to("cuda")
pipe.load_lora_weights(hf_hub_download(repo_name, ckpt_name))
pipe.fuse_lora()
# Use TCD scheduler to achieve better image quality
pipe.scheduler = TCDScheduler.from_config(pipe.scheduler.config)
# Lower eta results in more detail for multi-steps inference
eta=1.0
prompt="a photo of a cat"
image=pipe(prompt=prompt, num_inference_steps=1, guidance_scale=0, eta=eta).images[0]

import torch
from diffusers import DiffusionPipeline, UNet2DConditionModel, LCMScheduler
from huggingface_hub import hf_hub_download
from safetensors.torch import load_file
base_model_id = "stabilityai/stable-diffusion-xl-base-1.0"
repo_name = "ByteDance/Hyper-SD"
ckpt_name = "Hyper-SDXL-1step-Unet.safetensors"
# Load model.
unet = UNet2DConditionModel.from_config(base_model_id, subfolder="unet").to("cuda", torch.float16)
unet.load_state_dict(load_file(hf_hub_download(repo_name, ckpt_name), device="cuda"))
pipe = DiffusionPipeline.from_pretrained(base_model_id, unet=unet, torch_dtype=torch.float16, variant="fp16").to("cuda")
# Use LCM scheduler instead of ddim scheduler to support specific timestep number inputs
pipe.scheduler = LCMScheduler.from_config(pipe.scheduler.config)
# Set start timesteps to 800 in the one-step inference to get better results
prompt="a photo of a cat"
image=pipe(prompt=prompt, num_inference_steps=1, guidance_scale=0, timesteps=[800]).images[0]

import torch
from diffusers import DiffusionPipeline, DDIMScheduler
from huggingface_hub import hf_hub_download
base_model_id = "runwayml/stable-diffusion-v1-5"
repo_name = "ByteDance/Hyper-SD"
# Take 2-steps lora as an example
ckpt_name = "Hyper-SD15-2steps-lora.safetensors"
# Load model.
pipe = DiffusionPipeline.from_pretrained(base_model_id, torch_dtype=torch.float16, variant="fp16").to("cuda")
pipe.load_lora_weights(hf_hub_download(repo_name, ckpt_name))
pipe.fuse_lora()
# Ensure ddim scheduler timestep spacing set as trailing !!!
pipe.scheduler = DDIMScheduler.from_config(pipe.scheduler.config, timestep_spacing="trailing")
prompt="a photo of a cat"
image=pipe(prompt=prompt, num_inference_steps=2, guidance_scale=0).images[0]

import torch
from diffusers import DiffusionPipeline, TCDScheduler
from huggingface_hub import hf_hub_download
base_model_id = "runwayml/stable-diffusion-v1-5"
repo_name = "ByteDance/Hyper-SD"
ckpt_name = "Hyper-SD15-1step-lora.safetensors"
# Load model.
pipe = DiffusionPipeline.from_pretrained(base_model_id, torch_dtype=torch.float16, variant="fp16").to("cuda")
pipe.load_lora_weights(hf_hub_download(repo_name, ckpt_name))
pipe.fuse_lora()
# Use TCD scheduler to achieve better image quality
pipe.scheduler = TCDScheduler.from_config(pipe.scheduler.config)
# Lower eta results in more detail for multi-steps inference
eta=1.0
prompt="a photo of a cat"
image=pipe(prompt=prompt, num_inference_steps=1, guidance_scale=0, eta=eta).images[0]

import torch
from diffusers.utils import load_image
import numpy as np
import cv2
from PIL import Image
from diffusers import ControlNetModel, StableDiffusionXLControlNetPipeline, AutoencoderKL, DDIMScheduler
from huggingface_hub import hf_hub_download

# Load original image
image = load_image("https://huggingface.co/datasets/hf-internal-testing/diffusers-images/resolve/main/sd_controlnet/hf-logo.png")
image = np.array(image)
# Prepare Canny Control Image
low_threshold = 100
high_threshold = 200
image = cv2.Canny(image, low_threshold, high_threshold)
image = image[:, :, None]
image = np.concatenate([image, image, image], axis=2)
control_image = Image.fromarray(image)
control_image.save("control.png")
control_weight = 0.5  # recommended for good generalization

# Initialize pipeline
controlnet = ControlNetModel.from_pretrained(
    "diffusers/controlnet-canny-sdxl-1.0",
    torch_dtype=torch.float16
)
vae = AutoencoderKL.from_pretrained("madebyollin/sdxl-vae-fp16-fix", torch_dtype=torch.float16)
pipe = StableDiffusionXLControlNetPipeline.from_pretrained("stabilityai/stable-diffusion-xl-base-1.0", controlnet=controlnet, vae=vae, torch_dtype=torch.float16).to("cuda")

pipe.load_lora_weights(hf_hub_download("ByteDance/Hyper-SD", "Hyper-SDXL-2steps-lora.safetensors"))
# Ensure ddim scheduler timestep spacing set as trailing !!!
pipe.scheduler = DDIMScheduler.from_config(pipe.scheduler.config, timestep_spacing="trailing")
pipe.fuse_lora()
image = pipe("A chocolate cookie", num_inference_steps=2, image=control_image, guidance_scale=0, controlnet_conditioning_scale=control_weight).images[0]
image.save('image_out.png')

import torch
from diffusers.utils import load_image
import numpy as np
import cv2
from PIL import Image
from diffusers import ControlNetModel, StableDiffusionXLControlNetPipeline, AutoencoderKL, TCDScheduler
from huggingface_hub import hf_hub_download

# Load original image
image = load_image("https://huggingface.co/datasets/hf-internal-testing/diffusers-images/resolve/main/sd_controlnet/hf-logo.png")
image = np.array(image)
# Prepare Canny Control Image
low_threshold = 100
high_threshold = 200
image = cv2.Canny(image, low_threshold, high_threshold)
image = image[:, :, None]
image = np.concatenate([image, image, image], axis=2)
control_image = Image.fromarray(image)
control_image.save("control.png")
control_weight = 0.5  # recommended for good generalization

# Initialize pipeline
controlnet = ControlNetModel.from_pretrained(
    "diffusers/controlnet-canny-sdxl-1.0",
    torch_dtype=torch.float16
)
vae = AutoencoderKL.from_pretrained("madebyollin/sdxl-vae-fp16-fix", torch_dtype=torch.float16)
pipe = StableDiffusionXLControlNetPipeline.from_pretrained(
    "stabilityai/stable-diffusion-xl-base-1.0",
    controlnet=controlnet, vae=vae, torch_dtype=torch.float16).to("cuda")

# Load Hyper-SD15-1step lora
pipe.load_lora_weights(hf_hub_download("ByteDance/Hyper-SD", "Hyper-SDXL-1step-lora.safetensors"))
pipe.fuse_lora()
# Use TCD scheduler to achieve better image quality
pipe.scheduler = TCDScheduler.from_config(pipe.scheduler.config)
# Lower eta results in more detail for multi-steps inference
eta=1.0
image = pipe("A chocolate cookie", num_inference_steps=4, image=control_image, guidance_scale=0, controlnet_conditioning_scale=control_weight, eta=eta).images[0]
image.save('image_out.png')

import torch
from diffusers.utils import load_image
import numpy as np
import cv2
from PIL import Image
from diffusers import ControlNetModel, StableDiffusionControlNetPipeline, DDIMScheduler

from huggingface_hub import hf_hub_download

controlnet_checkpoint = "lllyasviel/control_v11p_sd15_canny"

# Load original image
image = load_image("https://huggingface.co/lllyasviel/control_v11p_sd15_canny/resolve/main/images/input.png")
image = np.array(image)
# Prepare Canny Control Image
low_threshold = 100
high_threshold = 200
image = cv2.Canny(image, low_threshold, high_threshold)
image = image[:, :, None]
image = np.concatenate([image, image, image], axis=2)
control_image = Image.fromarray(image)
control_image.save("control.png")

# Initialize pipeline
controlnet = ControlNetModel.from_pretrained(controlnet_checkpoint, torch_dtype=torch.float16)
pipe = StableDiffusionControlNetPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", controlnet=controlnet, torch_dtype=torch.float16).to("cuda")
pipe.load_lora_weights(hf_hub_download("ByteDance/Hyper-SD", "Hyper-SD15-2steps-lora.safetensors"))
pipe.fuse_lora()
# Ensure ddim scheduler timestep spacing set as trailing !!!
pipe.scheduler = DDIMScheduler.from_config(pipe.scheduler.config, timestep_spacing="trailing")
image = pipe("a blue paradise bird in the jungle", num_inference_steps=2, image=control_image, guidance_scale=0).images[0]
image.save('image_out.png')

import torch
from diffusers.utils import load_image
import numpy as np
import cv2
from PIL import Image
from diffusers import ControlNetModel, StableDiffusionControlNetPipeline, TCDScheduler
from huggingface_hub import hf_hub_download

controlnet_checkpoint = "lllyasviel/control_v11p_sd15_canny"

# Load original image
image = load_image("https://huggingface.co/lllyasviel/control_v11p_sd15_canny/resolve/main/images/input.png")
image = np.array(image)
# Prepare Canny Control Image
low_threshold = 100
high_threshold = 200
image = cv2.Canny(image, low_threshold, high_threshold)
image = image[:, :, None]
image = np.concatenate([image, image, image], axis=2)
control_image = Image.fromarray(image)
control_image.save("control.png")

# Initialize pipeline
controlnet = ControlNetModel.from_pretrained(controlnet_checkpoint, torch_dtype=torch.float16)
pipe = StableDiffusionControlNetPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", controlnet=controlnet, torch_dtype=torch.float16).to("cuda")
# Load Hyper-SD15-1step lora
pipe.load_lora_weights(hf_hub_download("ByteDance/Hyper-SD", "Hyper-SD15-1step-lora.safetensors"))
pipe.fuse_lora()
# Use TCD scheduler to achieve better image quality
pipe.scheduler = TCDScheduler.from_config(pipe.scheduler.config)
# Lower eta results in more detail for multi-steps inference
eta=1.0
image = pipe("a blue paradise bird in the jungle", num_inference_steps=1, image=control_image, guidance_scale=0, eta=eta).images[0]
image.save('image_out.png')

@misc{ren2024hypersd,
      title={Hyper-SD: Trajectory Segmented Consistency Model for Efficient Image Synthesis}, 
      author={Yuxi Ren and Xin Xia and Yanzuo Lu and Jiacheng Zhang and Jie Wu and Pan Xie and Xing Wang and Xuefeng Xiao},
      year={2024},
      eprint={2404.13686},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}