Runway
Runway Gen4 Image generates cinematic-quality stills at 720p or 1080p with reference image support and element tagging. Designed for storyboard-to-production workflows where generated frames feed into Runway video models.
Runway Gen4 Image extends Runway's video-focused AI capabilities into still image generation. It produces images with a cinematic, film-grade aesthetic — natural depth of field, filmic color grading, and dramatic lighting that pairs naturally with Runway's Gen4 Turbo video model. The model offers 720p and 1080p resolution output across 6 aspect ratios (1:1, 16:9, 7:3, 4:3, 3:4, 9:16), making it suitable for both widescreen cinematic frames and vertical mobile content. Reference image support lets you maintain character, wardrobe, and set consistency across a scene sequence. Element tagging provides spatial control over composition — tag specific objects or regions for the model to emphasize. It's positioned as a premium tool for production-quality key frames rather than rapid iteration.
Connect Runway Gen4 Image with other AI models on Martini's infinite canvas. No GPU required — start free.
Get Started FreeRunway Gen4 Image supports 720p and 1080p resolution output. Use 720p for fast storyboard drafts and 1080p for final frames. For 4K output, chain with an upscale tool like Recraft Crisp or Topaz.
Yes — this is its primary use case. Generate cinematic key frames with Gen4 Image, then feed them directly into Runway Gen4 Turbo video nodes. The cinematic aesthetic carries through consistently from still to motion.
Gen4 Image supports 6 aspect ratios: 1:1 (square), 16:9 (widescreen), 7:3 (ultrawide cinematic), 4:3 (standard), 3:4 (portrait), and 9:16 (vertical/mobile).
Midjourney
Midjourney v7 is the most recognizable AI image generator, with the strongest aesthetic signature in the category. On Martini you get V7 for photoreal and painterly work, Niji 7 for anime, Omni Reference for character lock-in, and Stylization, Variety, and Weirdness sliders for fine control — all from the canvas, no Discord required.
View detailsBlack Forest Labs
FLUX by Black Forest Labs is a fast, high-quality image generation family known for photorealistic output and excellent prompt adherence. Variants span free-tier dev models to ultra-resolution Pro outputs.
View detailsBlack Forest Labs
FLUX Kontext is a context-aware image generation and editing model that uses reference images to maintain character and style consistency across outputs. Available in Pro and Max tiers.
View details