import torch
import numpy as np
from diffusers import AutoencoderKLWan, ChronoEditTransformer3DModel, ChronoEditPipeline
from diffusers.utils import export_to_video, load_image
from transformers import CLIPVisionModel
from PIL import Image

model_id = "nvidia/ChronoEdit-14B-Diffusers"
image_encoder = CLIPVisionModel.from_pretrained(model_id, subfolder="image_encoder", dtype=torch.float32)
vae = AutoencoderKLWan.from_pretrained(model_id, subfolder="vae", dtype=torch.float32)
transformer = ChronoEditTransformer3DModel.from_pretrained(model_id, subfolder="transformer", dtype=torch.bfloat16)
pipe = ChronoEditPipeline.from_pretrained(model_id, image_encoder=image_encoder, transformer=transformer, vae=vae, dtype=torch.bfloat16)
pipe.to("cuda")  # or "mps", "xpu", "cpu"

image = load_image(
    "https://huggingface.co/spaces/nvidia/ChronoEdit/resolve/main/examples/3.png"
)
max_area = 720 * 1280
aspect_ratio = image.height / image.width
mod_value = pipe.vae_scale_factor_spatial * pipe.transformer.config.patch_size[1]
height = round(np.sqrt(max_area * aspect_ratio)) // mod_value * mod_value
width = round(np.sqrt(max_area / aspect_ratio)) // mod_value * mod_value
print("width", width, "height", height)
image = image.resize((width, height))
prompt = (
    "The user wants to transform the image by adding a small, cute mouse sitting inside the floral teacup, enjoying a spa bath. The mouse should appear relaxed and cheerful, with a tiny white bath towel draped over its head like a turban. It should be positioned comfortably in the cup’s liquid, with gentle steam rising around it to blend with the cozy atmosphere. "
    "The mouse’s pose should be natural—perhaps sitting upright with paws resting lightly on the rim or submerged in the tea. The teacup’s floral design, gold trim, and warm lighting must remain unchanged to preserve the original aesthetic. The steam should softly swirl around the mouse, enhancing the spa-like, whimsical mood."
)

output = pipe(
    image=image,
    prompt=prompt,
    height=height,
    width=width,
    num_frames=5,
    num_inference_steps=50,
    guidance_scale=5.0,
    enable_temporal_reasoning=False,
    num_temporal_reasoning_steps=0,
).frames[0]
Image.fromarray((output[-1] * 255).clip(0, 255).astype("uint8")).save("output.png")

output = pipe(
    image=image,
    prompt=prompt,
    height=height,
    width=width,
    num_frames=29,
    num_inference_steps=50,
    guidance_scale=5.0,
    enable_temporal_reasoning=True,
    num_temporal_reasoning_steps=50,
).frames[0]
export_to_video(output, "output.mp4", fps=16)
Image.fromarray((output[-1] * 255).clip(0, 255).astype("uint8")).save("output.png")

import torch
import numpy as np
from diffusers import AutoencoderKLWan, ChronoEditTransformer3DModel, ChronoEditPipeline
from diffusers.schedulers import UniPCMultistepScheduler
from diffusers.utils import export_to_video, load_image
from transformers import CLIPVisionModel
from PIL import Image

model_id = "nvidia/ChronoEdit-14B-Diffusers"
image_encoder = CLIPVisionModel.from_pretrained(model_id, subfolder="image_encoder", dtype=torch.float32)
vae = AutoencoderKLWan.from_pretrained(model_id, subfolder="vae", dtype=torch.float32)
transformer = ChronoEditTransformer3DModel.from_pretrained(model_id, subfolder="transformer", dtype=torch.bfloat16)
pipe = ChronoEditPipeline.from_pretrained(model_id, image_encoder=image_encoder, transformer=transformer, vae=vae, dtype=torch.bfloat16)
pipe.load_lora_weights("nvidia/ChronoEdit-14B-Diffusers", weight_name="lora/chronoedit_distill_lora.safetensors", adapter_name="distill")
pipe.fuse_lora(adapter_names=["distill"], lora_scale=1.0)
pipe.scheduler = UniPCMultistepScheduler.from_config(pipe.scheduler.config, flow_shift=2.0)
pipe.to("cuda")  # or "mps", "xpu", "cpu"

image = load_image(
    "https://huggingface.co/spaces/nvidia/ChronoEdit/resolve/main/examples/3.png"
)
max_area = 720 * 1280
aspect_ratio = image.height / image.width
mod_value = pipe.vae_scale_factor_spatial * pipe.transformer.config.patch_size[1]
height = round(np.sqrt(max_area * aspect_ratio)) // mod_value * mod_value
width = round(np.sqrt(max_area / aspect_ratio)) // mod_value * mod_value
print("width", width, "height", height)
image = image.resize((width, height))
prompt = (
    "The user wants to transform the image by adding a small, cute mouse sitting inside the floral teacup, enjoying a spa bath. The mouse should appear relaxed and cheerful, with a tiny white bath towel draped over its head like a turban. It should be positioned comfortably in the cup’s liquid, with gentle steam rising around it to blend with the cozy atmosphere. "
    "The mouse’s pose should be natural—perhaps sitting upright with paws resting lightly on the rim or submerged in the tea. The teacup’s floral design, gold trim, and warm lighting must remain unchanged to preserve the original aesthetic. The steam should softly swirl around the mouse, enhancing the spa-like, whimsical mood."
)

output = pipe(
    image=image,
    prompt=prompt,
    height=height,
    width=width,
    num_frames=5,
    num_inference_steps=8,
    guidance_scale=1.0,
    enable_temporal_reasoning=False,
    num_temporal_reasoning_steps=0,
).frames[0]
export_to_video(output, "output.mp4", fps=16)
Image.fromarray((output[-1] * 255).clip(0, 255).astype("uint8")).save("output.png")

import torch
import numpy as np
from diffusers import AutoencoderKLWan, ChronoEditTransformer3DModel, ChronoEditPipeline
from diffusers.schedulers import UniPCMultistepScheduler
from diffusers.utils import export_to_video, load_image
from transformers import CLIPVisionModel
from PIL import Image

model_id = "nvidia/ChronoEdit-14B-Diffusers"
image_encoder = CLIPVisionModel.from_pretrained(model_id, subfolder="image_encoder", dtype=torch.float32)
vae = AutoencoderKLWan.from_pretrained(model_id, subfolder="vae", dtype=torch.float32)
transformer = ChronoEditTransformer3DModel.from_pretrained(model_id, subfolder="transformer", dtype=torch.bfloat16)
pipe = ChronoEditPipeline.from_pretrained(model_id, image_encoder=image_encoder, transformer=transformer, vae=vae, dtype=torch.bfloat16)
pipe.load_lora_weights("nvidia/ChronoEdit-14B-Diffusers-Paint-Brush-Lora", weight_name="paintbrush_lora_diffusers.safetensors", adapter_name="paintbrush")
pipe.load_lora_weights("nvidia/ChronoEdit-14B-Diffusers", weight_name="lora/chronoedit_distill_lora.safetensors", adapter_name="distill")
pipe.fuse_lora(adapter_names=["paintbrush", "distill"], lora_scale=1.0)
pipe.scheduler = UniPCMultistepScheduler.from_config(pipe.scheduler.config, flow_shift=2.0)
pipe.to("cuda")  # or "mps", "xpu", "cpu"

image = load_image(
    "https://raw.githubusercontent.com/nv-tlabs/ChronoEdit/refs/heads/main/assets/images/input_paintbrush.png"
)
max_area = 720 * 1280
aspect_ratio = image.height / image.width
mod_value = pipe.vae_scale_factor_spatial * pipe.transformer.config.patch_size[1]
height = round(np.sqrt(max_area * aspect_ratio)) // mod_value * mod_value
width = round(np.sqrt(max_area / aspect_ratio)) // mod_value * mod_value
print("width", width, "height", height)
image = image.resize((width, height))
prompt = (
    "Turn the pencil sketch in the image into an actual object that is consistent with the image’s content. The user wants to change the sketch to a crown and a hat."
)

output = pipe(
    image=image,
    prompt=prompt,
    height=height,
    width=width,
    num_frames=5,
    num_inference_steps=8,
    guidance_scale=1.0,
    enable_temporal_reasoning=False,
    num_temporal_reasoning_steps=0,
).frames[0]
export_to_video(output, "output.mp4", fps=16)
Image.fromarray((output[-1] * 255).clip(0, 255).astype("uint8")).save("output_1.png")