Skip to main content

AI Toolkit: AI Agent

The Artlist AI Toolkit turns your ideas into images and videos using simple text prompts. Describe what you want, and the AI generates visuals you can refine with follow-up prompts or reference files. Adjust motion, style, or settings without switching tools, keeping everything in one workflow. Every creation can be iterated, edited, or expanded, making it easy to explore multiple directions from a single starting point.

Conversation‑based generation turns creative dialogue into visuals. Instead of hunting through menus and settings, you can:

Describe what you want → get an image or video → refine it conversationally

This conversational approach makes it easier and faster to go from idea to usable visual content, all inside the Artlist AI Toolkit.

Accessing AI Agent

  1. From the top panel on the Homepage click AI Toolkit.
  2. Navigate to image or video generation from the bottom left side of the prompt field.
  3. From the prompt area select the “speech bubble” icon. This is the Agent icon.

Getting Started

You can start free-form writing or select one of the session starters.

  • Help me write a prompt
  • Create a video
  • Describe an image
  • Create an image
  • Edit an image 

Generate from Natural Language Prompts

You can describe what you want in plain language, and the Toolkit AI Agent will interpret that text to create fully generated images or cinematic video clips:

  • Write a description, and the system can improve upon the prompt or turn it into a visual output.
    • If you do not want the Agent to process a  generation, specify that you need help improving a prompt.
    • For example: “Help me improve this prompt…”
  • Upload reference images, video, audio files, or start/end frames. The Agent can detect any style.
  • Use built‑in controls like aspect ratio, resolution, and duration to tailor the result
  • Continue refining through follow‑up messages until you get the look you want. 

This conversational workflow removes the need to switch between multiple tools to begin creating.

Important note: Talking to the agent, refining prompts, and visualizing references does not cost any credits. Generating or refining an image or video will automatically use credits. For any generation over 1,000 credits you will be prompted to confirm the generation output. Credit cost is the same as Standard mode. 

Build on Previous Generations

Within a session, once an image or video is generated, you don’t have to stop there:

  • Turn text prompts into original images or full video scenes
    • When generating a video, the optimal flow is to create an image first, then use it to generate a video.
  • Give the context of what you are doing and the Agent will understand that background and create a prompt.
    • "I am building a presentation for my co-workers about the financial crisis, please generate a prompt for an image of an office." 
  • Refine results through iterative conversation (edit the prompt, regenerate, or build on previous outputs)
  • Generate variations or evolve the idea without starting from scratch
  • Upload and edit an existing image or video by describing changes
  • Animate generated images into videos
  • Reuse prompts and settings to create variations
  • Iterate on the same idea without starting over

Note: The agent retains memory for one session. Memory isn’t retained between sessions.

One Flow, Many Formats

Within a single conversational session you can seamlessly move between modals. Such as:

  • Text → Image generation
  • Image → Video animation
  • Audio → Video animation
  • Prompt refinements
  • Adding motion, style details, or other tweaks

This lets you go from a rough idea to a visual concept and animated asset without leaving the Toolkit. The Toolkit AI Agent supports transforming text, images, and video into each other, enabling flexible creative workflows .

Step-by-Step Generation Guides

The Toolkit’s AI Agent provides clear, actionable walkthroughs for each type of AI generation.

Image Generation

Helps users create visuals using text or references:

  • Explain Text-to-Image and Image-to-Image workflows
  • Guide users reference images 
  • Clarify settings such as:
    • Aspect ratio
    • Resolution
    • Number of outputs

Video Generation

Supports users in creating clips:

  • Text-to-video generation (from prompts)
  • Image-to-video animation
  • Video-to-video transformations
  • Advanced controls:
    • Start/end frame
    • Motion control
    • Extend video
    • Multi-reference (image, video, & audio)

Choosing the Right AI Model

When asked, the Agent will select models based on your goals:

For instance:

Images

  • Artlist Original 1.0 → cinematic, production-ready visuals
  • Nano Banana Pro → strong typography and design accuracy

Videos

  • Veo 3.1 → strong audio synchronization
  • Sora 2 Pro → high-end cinematic realism
  • Kling O3 → precise control over complex scenes

Managing Expectations

The AI Toolkit is designed for creating and generating assets quickly, not for final video editing or post-production.

  • The AI Toolkit is not a full video editor like DaVinci Resolve or Premiere Pro
  • It is designed for generation and asset creation, not final editing
  • It cannot generate voiceovers or music

Users will still need tools like:

  • Final Cut Pro
  • DaVinci Resolve
  • Premier Pro

Need some more help? Head back to our Help Center.