Compare the AI models that power generated images and video in Descript.
The AI model you pick shapes how your generated images and video turn out: some are faster, some more polished, some better at following a complex prompt. Compare them below to choose the right one.
Availability & usageModel availability depends on your plan. Some premium models use more AI Credits than others. You can switch models anytime; choosing a new model only affects generations made after the switch.
Choose a model for each type of generative media in your App Settings, under the AI models tab.Clicking this link will take you directly to your App Settings in DescriptIf you only need to change the model for a single image or video generation and don’t want to modify your overall account settings, select a model for the specific generation you are performing while using the associated AI tool.Changing the model in this menu does not change your App Settings.
The below model descriptions are our best-faith effort to characterize each model’s strengths based on provider documentation and community feedback. Think of these descriptions as general guidance rather than precise specifications.
Versatile all-purpose model for complex prompts and precise editing. Balances speed and quality across various tasks.
Google Deepmind
November 2025
Flux [dev]
Fast, budget-friendly model for quick generation. Excels at creative, fantasy-style imagery and concept work. Uses fewer credits for rapid iteration.
Black Forest Labs (BFL)
August 2024
Flux Kontext
Maintains visual consistency across edits and generations. Balances quality and cost for projects requiring visual coherence.
Black Forest Labs (BFL)
May 2025
FLUX.2 Pro
Balances speed and quality with enhanced text rendering and image restyling capabilities. Suitable for most image generation needs.
Black Forest Labs (BFL)
November 2025
GPT Image 2
Designed for complex editing with nuanced instructions. Especially strong at creating infographics and text-dense images.
OpenAI
April 2026
Nano Banana 2
Combines Pro-level quality with Flash speed. Features advanced world knowledge, subject consistency for up to five characters, precise instruction following, and production-ready output up to 4K resolution.
Google Deepmind
February 2026
Nano Banana Pro
Renders lighting and textures with greater detail for both artistic and photorealistic prompts.
Google Deepmind
November 2025
Qwen
Works well for readable text over artistic imagery. Supports Chinese, Japanese, and English with accurate multi-line layouts.
Well-balanced for most video generation needs. Offers smooth motion, stable camera work, and good lighting with balanced speed, quality, and cost.
PixVerse AI
August 2025
Hailuo 02
Physics-focused model for realistic movement and character consistency. Handles complex actions with high fidelity.
Alibaba
June 2025
Kling v01
Generates video up to 10 seconds long. Strong for visual quality and production value.
Kling AI (Kuaishou)
December 2025
Kling O3
Smooth transitions and text-driven scene guidance. Efficient option for quick iteration.
Kling AI (Kuaishou)
February 2026
Kling O3 Pro
Enhanced frame-to-frame coherence and text-driven scene guidance.
Kling AI (Kuaishou)
February 2026
Kling v3.0
Strong with fluid motion and native audio. Good balance of quality and speed for most video creation needs.
Kling AI (Kuaishou)
February 2026
Kling v3.0 Pro
Does well with fluid motion and native audio.
Kling AI (Kuaishou)
February 2026
Seedance 2.0
Strong at motion stability and reallism. Adheres to prompt directions well. Note: Cannot accept image inputs with human faces, but can generate humans from scratch.
Kling AI (Kuaishou)
February 2026
Veo 3.1
High-end model with integrated audio. Features enhanced realism, synchronized dialogue and sound effects, and cinematic output.
Google Deepmind
October 2025
Veo 3.1 [fast]
Faster version of Veo 3.1 with similar visual quality. Cost-effective for iteration.
Google Deepmind
October 2025
Wan v2.2 [turbo]
Speed-optimized for rapid experimentation and concept validation. Efficient resource usage ideal for early-stage work.
Balanced 720p avatar model for everyday use. Good mix of realism, motion, and stability for most production work. Supports additional attitude prompting.
Kling AI (Kuaishou)
December 2025
Kling Avatar v2 Pro
High-fidelity 1080p avatar model. Strong model for photorealism and expressive motion. Supports additional attitude prompting.
It depends! The table above can help match your goal (speed vs polish vs complexity) to an available model. You can always choose a different model in your App settings and re-create your content to see what works best for you.
Often, yes. Higher-end models and longer videos usually consume more credits. If you’re exploring or drafting, try a “fast/lean” model first; switch to a premium model when you’re ready to finalize. Learn more about how to track and understand your Media Minutes and AI Credits.
