Supported Models
Last updated February 26, 2026
Gemini Pro
LLMAdvanced reasoning and multimodal understanding with 1M token context.
Gemini Flash
LLMFast, cost-efficient model for everyday tasks.
Nano Banana Pro
ImageHigh-quality image generation via Google AI Studio.
Veo 3.1
VideoState-of-the-art video generation with audio. Supports text-to-video and image-to-video.
GPT-5.2
LLMAdvanced LLM with 128K context window.
Sora 2
VideoHigh-quality video generation from text and image inputs.
DeepSeek V3.2
LLMHigh-performance text-only LLM with 128K context.
FLUX.2 Pro
ImageHigh-quality image generation with excellent prompt adherence.
Kling 3.0
VideoHigh-quality video generation with strong motion consistency.
Seedance 1.5 Pro
VideoDance and motion-focused video generation.
Wan 2.2
VideoText-to-video with strong character consistency.
Wan 2.6
VideoLatest Wan model with improved quality and longer durations.
HunyuanVideo
VideoTencent's video generation model via fal.ai.
Voice Cloning
VoiceClone any voice from a short audio sample. Use for character dialogue.
Text-to-Speech
VoiceHigh-quality speech synthesis with cloned or preset voices.
Local Models
Run models on your Mac. No API key needed. Zero per-generation cost.
FLUX.2 klein
ImageLightweight FLUX model for local image generation on Mac (Metal/MPS).
Wan 2.6 T2V
VideoText-to-video on device. Requires 16GB+ RAM.
Qwen3-4B
LLMCompact LLM via Ollama for script writing and AI assistant. Runs locally.
Start creating with these models.
Join the waitlist for early access and founding member pricing.
We'll email you when Skia is ready. No spam. Unsubscribe anytime.