git clone https://github.com/NVIDIA/cosmos-framework.git packages/cosmos-framework
pip install -e packages/cosmos-framework

export PROMPT_UPSAMPLER_ENDPOINT_URL="https://api.anthropic.com/v1/"
export PROMPT_UPSAMPLER_MODEL_NAME="claude-opus-4-6"
export PROMPT_UPSAMPLER_API_TOKEN="<you_token>"

python -m cosmos_framework.inference.prompt_upsampling \
    --input assets/example_t2v_prompt_short.txt \
    --output /tmp/upsampled_t2v_opus/ \
    --mode text2video \
    --endpoint-url "${PROMPT_UPSAMPLER_ENDPOINT_URL}" \
    --model "${PROMPT_UPSAMPLER_MODEL_NAME}" \
    --api-token "${PROMPT_UPSAMPLER_API_TOKEN}" \
    --resolution 720 \
    --aspect-ratio "16,9"

docker pull vllm/vllm-omni:cosmos3

vllm serve nvidia/Cosmos3-Nano \
  --omni \
  --host 0.0.0.0 \
  --port 8000 \
  --init-timeout 1800

pip install -U "huggingface_hub[cli]"
hf download nvidia/Cosmos3-Nano assets/ --local-dir Cosmos3-Nano
cd Cosmos3-Nano

import json
import mimetypes
from pathlib import Path

import requests

# 1. Read JSON-upsampled prompt and negative prompt
json_prompt = json.load(open("assets/example_i2v_prompt.json"))
negative_prompt = json.load(open("assets/negative_prompt.json"))

# 2. Build and send the multipart API request
url = "http://localhost:8000/v1/videos/sync"
image_path = Path("assets/example_i2v_input.jpg")
mime_type = mimetypes.guess_type(image_path)[0] or "image/png"
data = {
    "prompt": json.dumps(json_prompt),
    "negative_prompt": json.dumps(negative_prompt),
    "size": "1280x720",
    "num_frames": "189",
    "fps": "24",
    "num_inference_steps": "35",
    "guidance_scale": "6.0",
    "max_sequence_length": "4096",
    "flow_shift": "10.0",
    "extra_params": json.dumps(
        {
          "use_resolution_template": False,
          "use_duration_template": False,
          "guardrails": True,
        }
    ),
    "seed": "1111",
}

with image_path.open("rb") as image_file:
    files = {
        "input_reference": (image_path.name, image_file, mime_type),
    }
    print("Sending request to server...")
    response = requests.post(
        url,
        data=data,
        files=files,
        headers={"Accept": "video/mp4"},
    )
    response.raise_for_status()

# 3. Save the generated video
output_path = Path("/tmp/cosmos3_nano_i2v.mp4")
output_path.write_bytes(response.content)
print(f"Saved video to {output_path}")

import json
from pathlib import Path

import requests

# 1. Read JSON-upsampled prompt and negative prompt
json_prompt = json.load(open("assets/example_t2v_prompt.json"))
negative_prompt = json.load(open("assets/negative_prompt.json"))

# 2. Build your API payload
data = {
    "prompt": json.dumps(json_prompt),
    "negative_prompt": json.dumps(negative_prompt),
    "size": "1280x720",
    "num_frames": "189",
    "fps": "24",
    "num_inference_steps": "35",
    "guidance_scale": "6.0",
    "max_sequence_length": "4096",
    "flow_shift": "10.0",
    "extra_params": json.dumps(
        {
          "use_resolution_template": False,
          "use_duration_template": False,
          "guardrails": True,
        }
    ),
    "seed": "123",
}

# 3. Send the POST request
url = "http://localhost:8000/v1/videos/sync"
print("Sending request to server...")
response = requests.post(
    url,
    data=data,
    headers={"Accept": "video/mp4"},
)
response.raise_for_status()

# 4. Save the generated video
output_path = Path("/tmp/cosmos3_nano_t2v.mp4")
output_path.write_bytes(response.content)
print(f"Saved video to {output_path}")

import json
import mimetypes
from pathlib import Path

import requests

# 1. Read JSON-upsampled prompt and negative prompt
json_prompt = json.load(open("assets/example_i2v_prompt.json"))
negative_prompt = json.load(open("assets/negative_prompt.json"))

# 2. Build and send the multipart API request
url = "http://localhost:8000/v1/videos/sync"
image_path = Path("assets/example_i2v_input.jpg")
mime_type = mimetypes.guess_type(image_path)[0] or "image/png"
data = {
    "prompt": json.dumps(json_prompt),
    "negative_prompt": json.dumps(negative_prompt),
    "size": "1280x720",
    "num_frames": "189",
    "fps": "24",
    "num_inference_steps": "35",
    "guidance_scale": "6.0",
    "max_sequence_length": "4096",
    "generate_sound": "true",
    "sound_duration": "7.875",
    "flow_shift": "10.0",
    "extra_params": json.dumps(
        {
          "use_resolution_template": False,
          "use_duration_template": False,
          "guardrails": True,
        }
    ),
    "seed": "0",
}

with image_path.open("rb") as image_file:
    files = {
        "input_reference": (image_path.name, image_file, mime_type),
    }
    print("Sending request to server...")
    response = requests.post(
        url,
        data=data,
        files=files,
        headers={"Accept": "video/mp4"},
    )
    response.raise_for_status()

# 3. Save the generated video
output_path = Path("/tmp/cosmos3_nano_i2vs.mp4")
output_path.write_bytes(response.content)
print(f"Saved video to {output_path}")

import json
from pathlib import Path

import requests

# 1. Read JSON-upsampled prompt and negative prompt
json_prompt = json.load(open("assets/example_t2vs_prompt.json"))
negative_prompt = json.load(open("assets/negative_prompt.json"))

# 2. Build your API payload
data = {
    "prompt": json.dumps(json_prompt),
    "negative_prompt": json.dumps(negative_prompt),
    "size": "1280x720",
    "num_frames": "189",
    "fps": "24",
    "num_inference_steps": "35",
    "guidance_scale": "6.0",
    "max_sequence_length": "4096",
    "generate_sound": "true",
    "sound_duration": "7.875",
    "flow_shift": "10.0",
    "extra_params": json.dumps(
        {
          "use_resolution_template": False,
          "use_duration_template": False,
          "guardrails": True,
        }
    ),
    "seed": "0",
}

# 3. Send the POST request
url = "http://localhost:8000/v1/videos/sync"
print("Sending request to server...")
response = requests.post(
    url,
    data=data,
    headers={"Accept": "video/mp4"},
)
response.raise_for_status()

# 4. Save the generated video
output_path = Path("/tmp/cosmos3_nano_t2vs.mp4")
output_path.write_bytes(response.content)
print(f"Saved video to {output_path}")

import json
import mimetypes
from pathlib import Path

import imageio.v3 as iio
import numpy as np
import requests
from PIL import Image

url = "http://localhost:8000/v1/videos/sync"
first_frame_path = Path("assets/example_action_fd_agibotworld_first_frame.png")
action_spec = json.loads(Path("assets/example_action_fd_agibotworld_action_chunks.json").read_text())
action_chunks = action_spec["action_chunks"]

prompt = action_spec.get("prompt", "Pickup items in the supermarket")
fps = int(action_spec.get("fps", 10))
action_chunk_size = int(action_spec.get("action_chunk_size", 16))
current_frame_path = first_frame_path
input_width, input_height = Image.open(first_frame_path).size
chunk_video_paths = []
stitch_frames = []

for chunk_idx, action_chunk in enumerate(action_chunks):
    mime_type = mimetypes.guess_type(current_frame_path)[0] or "image/png"
    extra_params = {
        "action_mode": "forward_dynamics",
        "domain_name": action_spec.get("domain_name", "agibotworld"),
        "action_chunk_size": action_chunk_size,
        "image_size": action_spec.get("image_size", 480),
        "view_point": action_spec.get("view_point", "concat_view"),
        "action": action_chunk,
        "guardrails": True,
    }
    data = {
        "prompt": prompt,
        "num_frames": str(action_chunk_size + 1),  # conditioning frame + generated frames
        "fps": str(fps),
        "size": f"{input_width}x{input_height}",  # return chunks at input resolution
        "num_inference_steps": "30",
        "guidance_scale": "1.0",
        "flow_shift": "10.0",
        "seed": "0",
        "extra_params": json.dumps(extra_params),
    }

    with current_frame_path.open("rb") as image_file:
        files = {"input_reference": (current_frame_path.name, image_file, mime_type)}
        print(f"Sending action FD chunk {chunk_idx} to vLLM-Omni...")
        response = requests.post(
            url,
            data=data,
            files=files,
            headers={"Accept": "video/mp4"},
            timeout=600,
        )
        response.raise_for_status()

    chunk_video_path = Path(f"/tmp/cosmos3_nano_action_fd_chunk_{chunk_idx:02d}.mp4")
    chunk_video_path.write_bytes(response.content)
    chunk_video_paths.append(chunk_video_path)

    # The returned chunk contains the conditioning frame followed by generated frames.
    # Drop the conditioning frame when stitching the generated-only rollout.
    frames = iio.imread(chunk_video_path)
    stitch_frames.extend(frames[1:])

    # Autoregressive conditioning: use the final generated frame from this chunk
    # as the input image for the next vLLM-Omni request.
    if chunk_idx + 1 < len(action_chunks):
        current_frame_path = Path(f"/tmp/cosmos3_nano_action_fd_ar_frame_{chunk_idx + 1:02d}.png")
        iio.imwrite(current_frame_path, frames[-1])

stitched_path = Path("/tmp/cosmos3_nano_action_fd_agibotworld_4chunk.mp4")
iio.imwrite(stitched_path, np.asarray(stitch_frames), fps=fps)
print("Generated chunk videos:", chunk_video_paths)
print("Saved stitched rollout:", stitched_path)
print("stitched resolution:", f"{input_width}x{input_height}")

import json
import time
from pathlib import Path

import requests

base_url = "http://localhost:8000"
input_videos = {
    "av_inverse_0": Path("assets/example_action_id_av_0_input.mp4"),
    "av_inverse_1": Path("assets/example_action_id_av_1_input.mp4"),
}

for name, video_path in input_videos.items():
    extra_params = {
        "action_mode": "inverse_dynamics",
        "domain_name": "av",
        "action_chunk_size": 60,
        "image_size": 480,
        "view_point": "ego_view",
        "raw_action_dim": 9,
        "guardrails": True,
    }
    data = {
        "prompt": "You are an autonomous vehicle planning system.",
        "num_frames": "61",
        "fps": "10",
        "num_inference_steps": "30",
        "guidance_scale": "1.0",
        "flow_shift": "10.0",
        "seed": "0",
        "extra_params": json.dumps(extra_params),
    }

    with video_path.open("rb") as video_file:
        files = {
            "input_reference": (video_path.name, video_file, "video/mp4"),
        }
        print(f"Submitting {name} request to server...")
        response = requests.post(f"{base_url}/v1/videos", data=data, files=files)
        response.raise_for_status()
    initial = response.json()

    while True:
        response = requests.get(f"{base_url}/v1/videos/{initial['id']}", timeout=30)
        response.raise_for_status()
        final = response.json()
        print(initial["id"], final.get("status"), f"{final.get('progress', 0)}%")
        if final.get("status") == "completed":
            break
        if final.get("status") in {"failed", "cancelled"}:
            raise RuntimeError(json.dumps(final, indent=2))
        time.sleep(2)

    action = final.get("action")
    if not action or "data" not in action:
        raise RuntimeError(f"Response did not include action data: {json.dumps(final, indent=2)}")

    output_path = Path(f"/tmp/cosmos3_nano_action_id_{name}.json")
    output_path.write_text(json.dumps(action, indent=2))
    print(f"Saved predicted action to {output_path}")
    print("action shape:", action.get("shape"), "dtype:", action.get("dtype"))

uv venv --python 3.13 --seed --managed-python
source .venv/bin/activate
uv pip install --torch-backend=cu130 "vllm==0.21.0" \
  "vllm-cosmos3 @ git+https://github.com/NVIDIA/cosmos-framework.git#subdirectory=packages/vllm-cosmos3" \
  openai

CUDA_VISIBLE_DEVICES=0 \
vllm serve nvidia/Cosmos3-Nano \
  --hf-overrides '{"architectures": ["Cosmos3ReasonerForConditionalGeneration"]}' \
  --tensor-parallel-size 1 \
  --mm-encoder-tp-mode data \
  --async-scheduling \
  --allowed-local-media-path / \
  --media-io-kwargs '{"video": {"num_frames": -1}}' \
  --port 8000

import json
from pathlib import Path

import openai

# 1. Read the image reasoning prompt
example = json.load(open("assets/example_reasoning_prompt.json"))
image_path = Path("assets/example_reasoning_input.png").resolve()
image_url = image_path.as_uri()

# 2. Query the OpenAI-compatible vLLM server
client = openai.OpenAI(
    api_key="EMPTY",
    base_url="http://localhost:8000/v1",
)

response = client.chat.completions.create(
    model=client.models.list().data[0].id,
    messages=[
        {
            "role": "user",
            "content": [
                {"type": "image_url", "image_url": {"url": image_url}},
                {"type": "text", "text": example["prompt"]},
            ],
        },
    ],
    max_tokens=example["max_tokens"],
    seed=0,
)

# 3. Print the generated reasoning output
print(response.choices[0].message.content)

The task is to put flower into the red bottle. Generate a plan consisting of subtasks for accomplish the task.

Move your arm to the flower. Grasp the flower. Move your arm to the red bottle. Place the flower in the red bottle.

uv venv --python 3.13 --seed --managed-python
source .venv/bin/activate
uv pip install \
  "diffusers @ git+https://github.com/huggingface/diffusers.git" \
  accelerate \
  av \
  cosmos_guardrail \
  huggingface_hub \
  imageio \
  imageio-ffmpeg \
  torch \
  torchvision \
  transformers

import json
import torch
from diffusers import Cosmos3OmniPipeline
from diffusers.schedulers.scheduling_unipc_multistep import UniPCMultistepScheduler
from diffusers.utils import export_to_video

# Read JSON-upsampled prompt and negative prompt
json_prompt = json.load(open("assets/example_t2v_prompt.json"))
negative_prompt = json.load(open("assets/negative_prompt.json"))

pipe = Cosmos3OmniPipeline.from_pretrained(
    "nvidia/Cosmos3-Nano",
    torch_dtype=torch.bfloat16,
    device_map="cuda",
    enable_safety_checker=True,
)
pipe.scheduler = UniPCMultistepScheduler.from_config(pipe.scheduler.config, flow_shift=10.0)

result = pipe(
    prompt=json.dumps(json_prompt),
    negative_prompt=json.dumps(negative_prompt),
    num_frames=189,
    height=720,
    width=1280,
    num_inference_steps=35,
    guidance_scale=6.0,
    generator=torch.Generator(device="cuda").manual_seed(123),
)

export_to_video(result.video, "/tmp/cosmos3_nano_t2v_diffusers.mp4", fps=24)
print("Saved video to /tmp/cosmos3_nano_t2v_diffusers.mp4")