>>> import cv2
>>> import numpy as np
>>> from PIL import Image
>>> import torch
>>> from diffusers import Cosmos2_5_TransferPipeline, AutoModel
>>> from diffusers.utils import export_to_video, load_video

>>> model_id = "nvidia/Cosmos-Transfer2.5-2B"
>>> # Load a Transfer2.5 controlnet variant (edge, depth, seg, or blur)
>>> controlnet = AutoModel.from_pretrained(
...     model_id, revision="diffusers/controlnet/general/edge", torch_dtype=torch.bfloat16
... )
>>> pipe = Cosmos2_5_TransferPipeline.from_pretrained(
...     model_id, controlnet=controlnet, revision="diffusers/general", torch_dtype=torch.bfloat16
... )
>>> pipe = pipe.to("cuda")

>>> # Video2World with edge control: Generate video guided by edge maps extracted from input video.
>>> prompt = (
...     "The video is a demonstration of robotic manipulation, likely in a laboratory or testing environment. It"
...     "features two robotic arms interacting with a piece of blue fabric. The setting is a room with a beige"
...     "couch in the background, providing a neutral backdrop for the robotic activity. The robotic arms are"
...     "positioned on either side of the fabric, which is placed on a yellow cushion. The left robotic arm is"
...     "white with a black gripper, while the right arm is black with a more complex, articulated gripper. At the"
...     "beginning, the fabric is laid out on the cushion. The left robotic arm approaches the fabric, its gripper"
...     "opening and closing as it positions itself. The right arm remains stationary initially, poised to assist."
...     "As the video progresses, the left arm grips the fabric, lifting it slightly off the cushion. The right arm"
...     "then moves in, its gripper adjusting to grasp the opposite side of the fabric. Both arms work in"
...     "coordination, lifting and holding the fabric between them. The fabric is manipulated with precision,"
...     "showcasing the dexterity and control of the robotic arms. The camera remains static throughout, focusing"
...     "on the interaction between the robotic arms and the fabric, allowing viewers to observe the detailed"
...     "movements and coordination involved in the task."
... )
>>> negative_prompt = (
...     "The video captures a series of frames showing ugly scenes, static with no motion, motion blur, "
...     "over-saturation, shaky footage, low resolution, grainy texture, pixelated images, poorly lit areas, "
...     "underexposed and overexposed scenes, poor color balance, washed out colors, choppy sequences, jerky "
...     "movements, low frame rate, artifacting, color banding, unnatural transitions, outdated special effects, "
...     "fake elements, unconvincing visuals, poorly edited content, jump cuts, visual noise, and flickering. "
...     "Overall, the video is of poor quality."
... )
>>> input_video = load_video(
...     "https://github.com/nvidia-cosmos/cosmos-transfer2.5/raw/refs/heads/main/assets/robot_example/robot_input.mp4"
... )
>>> num_frames = 93

>>> # Extract edge maps from the input video using Canny edge detection
>>> edge_maps = [
...     cv2.Canny(cv2.cvtColor(np.array(frame.convert("RGB")), cv2.COLOR_RGB2BGR), 100, 200)
...     for frame in input_video[:num_frames]
... ]
>>> edge_maps = np.stack(edge_maps)[None]  # (T, H, W) -> (1, T, H, W)
>>> controls = torch.from_numpy(edge_maps).expand(3, -1, -1, -1)  # (1, T, H, W) -> (3, T, H, W)
>>> controls = [Image.fromarray(x.numpy()) for x in controls.permute(1, 2, 3, 0)]
>>> export_to_video(controls, "edge_controlled_video_edge.mp4", fps=30)

>>> # Transfer inference with controls.
>>> video = pipe(
...     controls=controls,
...     controls_conditioning_scale=1.0,
...     prompt=prompt,
...     negative_prompt=negative_prompt,
...     num_frames=num_frames,
... ).frames[0]
>>> export_to_video(video, "edge_controlled_video.mp4", fps=30)

>>> import torch
>>> from diffusers import Cosmos2_5_PredictBasePipeline
>>> from diffusers.utils import export_to_video, load_image, load_video

>>> model_id = "nvidia/Cosmos-Predict2.5-2B"
>>> pipe = Cosmos2_5_PredictBasePipeline.from_pretrained(
...     model_id, revision="diffusers/base/post-trained", torch_dtype=torch.bfloat16
... )
>>> pipe = pipe.to("cuda")

>>> # Common negative prompt reused across modes.
>>> negative_prompt = (
...     "The video captures a series of frames showing ugly scenes, static with no motion, motion blur, "
...     "over-saturation, shaky footage, low resolution, grainy texture, pixelated images, poorly lit areas, "
...     "underexposed and overexposed scenes, poor color balance, washed out colors, choppy sequences, jerky "
...     "movements, low frame rate, artifacting, color banding, unnatural transitions, outdated special effects, "
...     "fake elements, unconvincing visuals, poorly edited content, jump cuts, visual noise, and flickering. "
...     "Overall, the video is of poor quality."
... )

>>> # Text2World: generate a 93-frame world video from text only.
>>> prompt = (
...     "As the red light shifts to green, the red bus at the intersection begins to move forward, its headlights "
...     "cutting through the falling snow. The snowy tire tracks deepen as the vehicle inches ahead, casting fresh "
...     "lines onto the slushy road. Around it, streetlights glow warmer, illuminating the drifting flakes and wet "
...     "reflections on the asphalt. Other cars behind start to edge forward, their beams joining the scene. "
...     "The stillness of the urban street transitions into motion as the quiet snowfall is punctuated by the slow "
...     "advance of traffic through the frosty city corridor."
... )
>>> video = pipe(
...     image=None,
...     video=None,
...     prompt=prompt,
...     negative_prompt=negative_prompt,
...     num_frames=93,
...     generator=torch.Generator().manual_seed(1),
... ).frames[0]
>>> export_to_video(video, "text2world.mp4", fps=16)

>>> # Image2World: condition on a single image and generate a 93-frame world video.
>>> prompt = (
...     "A high-definition video captures the precision of robotic welding in an industrial setting. "
...     "The first frame showcases a robotic arm, equipped with a welding torch, positioned over a large metal structure. "
...     "The welding process is in full swing, with bright sparks and intense light illuminating the scene, creating a vivid "
...     "display of blue and white hues. A significant amount of smoke billows around the welding area, partially obscuring "
...     "the view but emphasizing the heat and activity. The background reveals parts of the workshop environment, including a "
...     "ventilation system and various pieces of machinery, indicating a busy and functional industrial workspace. As the video "
...     "progresses, the robotic arm maintains its steady position, continuing the welding process and moving to its left. "
...     "The welding torch consistently emits sparks and light, and the smoke continues to rise, diffusing slightly as it moves upward. "
...     "The metal surface beneath the torch shows ongoing signs of heating and melting. The scene retains its industrial ambiance, with "
...     "the welding sparks and smoke dominating the visual field, underscoring the ongoing nature of the welding operation."
... )
>>> image = load_image(
...     "https://media.githubusercontent.com/media/nvidia-cosmos/cosmos-predict2.5/refs/heads/main/assets/base/robot_welding.jpg"
... )
>>> video = pipe(
...     image=image,
...     video=None,
...     prompt=prompt,
...     negative_prompt=negative_prompt,
...     num_frames=93,
...     generator=torch.Generator().manual_seed(1),
... ).frames[0]
>>> export_to_video(video, "image2world.mp4", fps=16)

>>> # Video2World: condition on an input clip and predict a 93-frame world video.
>>> prompt = (
...     "The video opens with an aerial view of a large-scale sand mining construction operation, showcasing extensive piles "
...     "of brown sand meticulously arranged in parallel rows. A central water channel, fed by a water pipe, flows through the "
...     "middle of these sand heaps, creating ripples and movement as it cascades down. The surrounding area features dense green "
...     "vegetation on the left, contrasting with the sandy terrain, while a body of water is visible in the background on the right. "
...     "As the video progresses, a piece of heavy machinery, likely a bulldozer, enters the frame from the right, moving slowly along "
...     "the edge of the sand piles. This machinery's presence indicates ongoing construction work in the operation. The final frame "
...     "captures the same scene, with the water continuing its flow and the bulldozer still in motion, maintaining the dynamic yet "
...     "steady pace of the construction activity."
... )
>>> input_video = load_video(
...     "https://github.com/nvidia-cosmos/cosmos-predict2.5/raw/refs/heads/main/assets/base/sand_mining.mp4"
... )
>>> video = pipe(
...     image=None,
...     video=input_video,
...     prompt=prompt,
...     negative_prompt=negative_prompt,
...     num_frames=93,
...     generator=torch.Generator().manual_seed(1),
... ).frames[0]
>>> export_to_video(video, "video2world.mp4", fps=16)

>>> # To produce an image instead of a world (video) clip, set num_frames=1 and
>>> # save the first frame: pipe(..., num_frames=1).frames[0][0].

>>> import torch
>>> from diffusers import CosmosTextToWorldPipeline
>>> from diffusers.utils import export_to_video

>>> model_id = "nvidia/Cosmos-1.0-Diffusion-7B-Text2World"
>>> pipe = CosmosTextToWorldPipeline.from_pretrained(model_id, torch_dtype=torch.bfloat16)
>>> pipe.to("cuda")

>>> prompt = "A sleek, humanoid robot stands in a vast warehouse filled with neatly stacked cardboard boxes on industrial shelves. The robot's metallic body gleams under the bright, even lighting, highlighting its futuristic design and intricate joints. A glowing blue light emanates from its chest, adding a touch of advanced technology. The background is dominated by rows of boxes, suggesting a highly organized storage system. The floor is lined with wooden pallets, enhancing the industrial setting. The camera remains static, capturing the robot's poised stance amidst the orderly environment, with a shallow depth of field that keeps the focus on the robot while subtly blurring the background for a cinematic effect."

>>> output = pipe(prompt=prompt).frames[0]
>>> export_to_video(output, "output.mp4", fps=30)

>>> import torch
>>> from diffusers import CosmosVideoToWorldPipeline
>>> from diffusers.utils import export_to_video, load_image

>>> model_id = "nvidia/Cosmos-1.0-Diffusion-7B-Video2World"
>>> pipe = CosmosVideoToWorldPipeline.from_pretrained(model_id, torch_dtype=torch.bfloat16)
>>> pipe.to("cuda")

>>> prompt = "The video depicts a long, straight highway stretching into the distance, flanked by metal guardrails. The road is divided into multiple lanes, with a few vehicles visible in the far distance. The surrounding landscape features dry, grassy fields on one side and rolling hills on the other. The sky is mostly clear with a few scattered clouds, suggesting a bright, sunny day."
>>> image = load_image(
...     "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/cosmos/cosmos-video2world-input.jpg"
... )

>>> video = pipe(image=image, prompt=prompt).frames[0]
>>> export_to_video(video, "output.mp4", fps=30)

>>> import torch
>>> from diffusers import CosmosVideoToWorldPipeline
>>> from diffusers.utils import export_to_video, load_video

>>> model_id = "nvidia/Cosmos-1.0-Diffusion-7B-Video2World"
>>> pipe = CosmosVideoToWorldPipeline.from_pretrained(model_id, torch_dtype=torch.bfloat16)
>>> pipe.transformer = torch.compile(pipe.transformer)
>>> pipe.to("cuda")

>>> prompt = "The video depicts a winding mountain road covered in snow, with a single vehicle traveling along it. The road is flanked by steep, rocky cliffs and sparse vegetation. The landscape is characterized by rugged terrain and a river visible in the distance. The scene captures the solitude and beauty of a winter drive through a mountainous region."
>>> video = load_video(
...     "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/cosmos/cosmos-video2world-input-vid.mp4"
... )[
...     :21
... ]  # This example uses only the first 21 frames

>>> video = pipe(video=video, prompt=prompt).frames[0]
>>> export_to_video(video, "output.mp4", fps=30)

>>> import torch
>>> from diffusers import Cosmos2TextToImagePipeline

>>> # Available checkpoints: nvidia/Cosmos-Predict2-2B-Text2Image, nvidia/Cosmos-Predict2-14B-Text2Image
>>> model_id = "nvidia/Cosmos-Predict2-2B-Text2Image"
>>> pipe = Cosmos2TextToImagePipeline.from_pretrained(model_id, torch_dtype=torch.bfloat16)
>>> pipe.to("cuda")

>>> prompt = "A close-up shot captures a vibrant yellow scrubber vigorously working on a grimy plate, its bristles moving in circular motions to lift stubborn grease and food residue. The dish, once covered in remnants of a hearty meal, gradually reveals its original glossy surface. Suds form and bubble around the scrubber, creating a satisfying visual of cleanliness in progress. The sound of scrubbing fills the air, accompanied by the gentle clinking of the dish against the sink. As the scrubber continues its task, the dish transforms, gleaming under the bright kitchen lights, symbolizing the triumph of cleanliness over mess."
>>> negative_prompt = "The video captures a series of frames showing ugly scenes, static with no motion, motion blur, over-saturation, shaky footage, low resolution, grainy texture, pixelated images, poorly lit areas, underexposed and overexposed scenes, poor color balance, washed out colors, choppy sequences, jerky movements, low frame rate, artifacting, color banding, unnatural transitions, outdated special effects, fake elements, unconvincing visuals, poorly edited content, jump cuts, visual noise, and flickering. Overall, the video is of poor quality."

>>> output = pipe(
...     prompt=prompt, negative_prompt=negative_prompt, generator=torch.Generator().manual_seed(1)
... ).images[0]
>>> output.save("output.png")

>>> import torch
>>> from diffusers import Cosmos2VideoToWorldPipeline
>>> from diffusers.utils import export_to_video, load_image

>>> # Available checkpoints: nvidia/Cosmos-Predict2-2B-Video2World, nvidia/Cosmos-Predict2-14B-Video2World
>>> model_id = "nvidia/Cosmos-Predict2-2B-Video2World"
>>> pipe = Cosmos2VideoToWorldPipeline.from_pretrained(model_id, torch_dtype=torch.bfloat16)
>>> pipe.to("cuda")

>>> prompt = "A close-up shot captures a vibrant yellow scrubber vigorously working on a grimy plate, its bristles moving in circular motions to lift stubborn grease and food residue. The dish, once covered in remnants of a hearty meal, gradually reveals its original glossy surface. Suds form and bubble around the scrubber, creating a satisfying visual of cleanliness in progress. The sound of scrubbing fills the air, accompanied by the gentle clinking of the dish against the sink. As the scrubber continues its task, the dish transforms, gleaming under the bright kitchen lights, symbolizing the triumph of cleanliness over mess."
>>> negative_prompt = "The video captures a series of frames showing ugly scenes, static with no motion, motion blur, over-saturation, shaky footage, low resolution, grainy texture, pixelated images, poorly lit areas, underexposed and overexposed scenes, poor color balance, washed out colors, choppy sequences, jerky movements, low frame rate, artifacting, color banding, unnatural transitions, outdated special effects, fake elements, unconvincing visuals, poorly edited content, jump cuts, visual noise, and flickering. Overall, the video is of poor quality."
>>> image = load_image(
...     "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/yellow-scrubber.png"
... )

>>> video = pipe(
...     image=image, prompt=prompt, negative_prompt=negative_prompt, generator=torch.Generator().manual_seed(1)
... ).frames[0]
>>> export_to_video(video, "output.mp4", fps=16)