Save 4 hours! We auto-setup your workflow! Free!

Drop your workflow.json — we handle every dependency, custom node, and model. Just open the link and run.

Auto-Setup Workflow Json (Free) Now!
ComfyUI > Nodes > ComfyUI-Olm-SoL-Refiner > SoL Refine Video (Olm)

ComfyUI Node: SoL Refine Video (Olm)

Class Name

OlmSoLRefineVideo

Category
Olm/SoL Refiner
Author
o-l-l-i (Account age: 3312days)
Extension
ComfyUI-Olm-SoL-Refiner
Latest Updated
2026-10-09
Github Stars
0.02K

How to Install ComfyUI-Olm-SoL-Refiner

Install this extension via the ComfyUI Manager by searching for ComfyUI-Olm-SoL-Refiner
  • 1. Click the Manager button in the main menu
  • 2. Select Custom Nodes Manager button
  • 3. Enter ComfyUI-Olm-SoL-Refiner in the search bar
After installation, click the Restart button to restart ComfyUI. Then, manually refresh your browser to clear the cache and access the updated list of nodes.

Visit ComfyUI Online for ready-to-use ComfyUI environment

  • Free trial available
  • 16GB VRAM to 80GB VRAM GPU machines
  • 400+ preloaded models/nodes
  • Freedom to upload custom models/nodes
  • 200+ ready-to-run workflows
  • 100% private workspace with up to 200GB storage
  • Dedicated Support

Run ComfyUI Online

SoL Refine Video (Olm) Description

Enhance video content with AI-driven refinement for artistic control and high-quality output.

SoL Refine Video (Olm):

The OlmSoLRefineVideo node is designed to enhance and refine video content using advanced AI-driven techniques. It leverages the capabilities of the OLM_SOL_REFINER to process a sequence of images, transforming them into a refined video output based on a user-provided prompt. This node is particularly beneficial for AI artists looking to improve the visual quality and coherence of their video projects. By utilizing a combination of image processing and prompt-based refinement, the node allows for creative control over the final video output, making it a powerful tool for generating high-quality, visually appealing videos. The node's functionality is centered around refining video frames to match the desired artistic style or thematic elements specified in the prompt, offering a seamless integration of AI-driven enhancements into video production workflows.

SoL Refine Video (Olm) Input Parameters:

refiner

The refiner parameter specifies the OLM_SOL_REFINER model to be used for refining the video. This model is responsible for applying the AI-driven enhancements to the input images, transforming them into a cohesive video output.

images

The images parameter is a sequence of images that serve as the input frames for the video. These images are processed and refined based on the provided prompt and other parameters to produce the final video output.

prompt

The prompt parameter is a string input that describes the desired style or theme of the video. It guides the refinement process, allowing the AI model to tailor the video output to match the specified artistic direction. This parameter supports multiline input for detailed descriptions.

fps

The fps parameter stands for frames per second and determines the playback speed of the video. It accepts a floating-point value with a default of 24.0, and it can range from 1.0 to 240.0. Adjusting this parameter affects the smoothness and temporal resolution of the video.

width

The width parameter specifies the width of the output video in pixels. It accepts integer values ranging from 224 to 4096, with a default of 1920. This parameter allows you to define the horizontal resolution of the video, impacting its visual clarity and detail.

height

The height parameter defines the height of the output video in pixels. Similar to the width parameter, it accepts integer values between 224 and 4096, with a default of 1080. This parameter sets the vertical resolution of the video, influencing its overall aspect ratio and visual quality.

seed

The seed parameter is an integer used to initialize the random number generator for the refinement process. It allows for reproducibility of results by ensuring that the same input parameters produce the same output. The default value is 0, and it can range up to 0xFFFFFFFFFFFFFFFF.

decoder_seed

The decoder_seed parameter functions similarly to the seed parameter but is specifically used for the decoding process. It ensures consistent results during the video decoding phase, with a default value of 0 and a range up to 0xFFFFFFFFFFFFFFFF.

decoder_tile_size

The decoder_tile_size parameter determines the size of the tiles used during the decoding process. It offers options of 256, 384, 512, and 768, with a default of 384. This parameter affects the granularity of the decoding process, influencing the efficiency and quality of the video output.

decoder_tile_frames

The decoder_tile_frames parameter specifies the number of frames processed per tile during decoding. It provides options of 16, 32, 64, and 128, with a default of 32. This parameter impacts the temporal resolution and processing speed of the video refinement.

SoL Refine Video (Olm) Output Parameters:

images

The images output parameter represents the refined video frames resulting from the node's processing. These frames have been enhanced and adjusted according to the input parameters and prompt, providing a high-quality video output that aligns with the specified artistic vision.

SoL Refine Video (Olm) Usage Tips:

  • Ensure that the prompt parameter is detailed and descriptive to achieve the desired artistic effect in the video output.
  • Adjust the fps parameter to match the intended playback speed and smoothness of your video project.
  • Use the seed and decoder_seed parameters to reproduce consistent results across multiple runs with the same input settings.
  • Experiment with different decoder_tile_size and decoder_tile_frames settings to balance processing speed and video quality.

SoL Refine Video (Olm) Common Errors and Solutions:

"Select a supported decoder tile size"

  • Explanation: This error occurs when an unsupported value is provided for the decoder_tile_size or decoder_tile_frames parameters.
  • Solution: Ensure that the decoder_tile_size is one of the following: 256, 384, 512, or 768, and decoder_tile_frames is one of: 16, 32, 64, or 128.

"FPS must be positive"

  • Explanation: This error indicates that the fps parameter has been set to a non-positive value.
  • Solution: Set the fps parameter to a positive value within the range of 1.0 to 240.0.

"Provide a batch of RGB video frames"

  • Explanation: This error suggests that the input images parameter does not contain a valid batch of RGB video frames.
  • Solution: Ensure that the images input is a 4-dimensional tensor with the last dimension representing the RGB channels.

"Provide a prompt describing the video"

  • Explanation: This error occurs when the prompt parameter is empty or consists only of whitespace.
  • Solution: Provide a meaningful and descriptive prompt to guide the video refinement process.

SoL Refine Video (Olm) Related Nodes

Go back to the extension to check out more related nodes.
ComfyUI-Olm-SoL-Refiner
RunComfy
Copyright 2025 RunComfy. All Rights Reserved.

RunComfy is the premier ComfyUI platform, offering ComfyUI online environment and services, along with ComfyUI workflows featuring stunning visuals. RunComfy also provides AI Models, enabling artists to harness the latest AI tools to create incredible art.

SoL Refine Video (Olm)