Topaz Astra: Video Creative Upscale

Enhance videos with Topaz AI. Supports resolution upscaling using Starlight (Astra) Fast model and frame interpolation with apo-8 model.

Download Workflow Try in Cloud

Output

00:00

Example

Call this model from your code

The request below uses the same prepared graph and settings as the Playground. Each submission can start a paid run; do not automatically retry a submission whose outcome is unknown.

Get API key

What you need

Runs on: Comfy Cloud
Key: COMFY_API_KEY
Your files: Uploaded by the code from their urls

Needs a paid Cloud plan and credits.

Download API JSON

# Python 3.10+: pip install comfy-sdk==0.4.0
import os

from comfy_sdk import Comfy

api_key = os.environ.get("COMFY_API_KEY", "").strip()
if not api_key: raise RuntimeError("Set COMFY_API_KEY")
os.environ.setdefault("COMFY_BASE_URL", "https://cloud.comfy.org")
client = Comfy(api_key=api_key)
workflow = client.workflows.from_json({
    "7": {
        "class_type": "TopazVideoEnhance",
        "inputs": {
            "dynamic_compression_level": "Low",
            "interpolation_duplicate": False,
            "interpolation_duplicate_threshold": 0.01,
            "interpolation_enabled": False,
            "interpolation_frame_rate": 60,
            "interpolation_model": "apo-8",
            "interpolation_slowmo": 1,
            "upscaler_creativity": "low",
            "upscaler_enabled": True,
            "upscaler_model": "Starlight (Astra) Fast",
            "upscaler_resolution": "FullHD (1080p)",
            "video": [
                "8",
                0
            ]
        },
        "_meta": {
            "title": "Topaz Video Enhance (Legacy)"
        }
    },
    "8": {
        "class_type": "LoadVideo",
        "inputs": {
            "file": "UPLOADED_video_FILENAME"
        },
        "_meta": {
            "title": "Load Video"
        }
    },
    "9": {
        "class_type": "SaveVideo",
        "inputs": {
            "filename_prefix": "video/Topaz",
            "format": "auto",
            "format.codec": "h264",
            "video": [
                "7",
                0
            ]
        },
        "_meta": {
            "title": "Save Video"
        }
    }
})
workflow.set_input("8", "file", client.assets.from_url("https://comfy.org/catalog-media/f431e5db-800f-4067-ac4e-a6104cdfed2c/a55015d8-b301-4be6-890f-e00bc02f0f3e"))

# run() also passes api_key to the partner nodes in this workflow.
job = client.run(workflow, api_key=api_key)
for output in job.get_outputs("9"):
    output.to_file(output.name)

API documentation

Try an example

About this workflow

The 'Topaz Astra: Video Creative Upscale' workflow is designed to enhance video quality using advanced AI techniques. At its core, this workflow leverages the Topaz AI models, specifically the Starlight (Astra) Fast model for resolution upscaling and the apo-8 model for frame interpolation. The workflow begins by loading a video file using the LoadVideo node, which serves as the input for the enhancement process. The TopazVideoEnhance node then applies the selected AI models to upscale the video resolution and smooth out motion through frame interpolation.

Finally, the enhanced video is saved using the SaveVideo node, ensuring that the output retains the improvements made during processing.

This workflow is particularly useful for creators looking to improve the visual quality of their video content without the need for expensive hardware or extensive manual editing. By automating the upscaling and interpolation processes, users can achieve professional-looking results with minimal effort. The integration of Topaz AI's advanced models ensures that the enhancements are both efficient and effective, making this workflow a valuable tool for video editors and content creators alike.

Topaz Astra: Video Creative Upscale

Input

Inside the workflow

Call this model from your code

What you need

Try an example

About this workflow

Questions & answers

Input

Inside the workflow

Call this model from your code

What you need

Try an example

About this workflow

Questions & answers

What file formats are supported by the LoadVideo node?

Can I use this workflow to process multiple videos at once?

How long does it take to process a video using this workflow?

Is there a way to adjust the level of enhancement applied by the AI models?