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.
Midjourney v7 became the default model on midjourney.com in mid-2025 and remains the workhorse used by most professional Midjourney users in 2026 — it shipped major upgrades to hand and face rendering, in-image text, and prompt adherence over v6.1. Niji 7, the dedicated anime variant, launched January 9, 2026 with sharper eye and reflection rendering, an upgraded --sref style reference, and tighter prompt literalism. Martini exposes both as a single Midjourney v7 node through the Youchuan API — every call returns a 2x2 grid of 4 images. Omni Reference — Midjourney v7's identity-lock system that replaces the old --cref character reference — works for characters, products, vehicles, or logos. Three sliders shape every generation: Stylization (0–1000, default 100) controls how much aesthetic license the model takes, Variety (0–100, default 0) spreads the four grid images further apart, and Weirdness (0–3000, default 0) pushes outputs away from the average Midjourney generation. On Martini, chain Midjourney into Runway Gen4 or Kling for image-to-video, into Suno for soundtrack, and into FLUX Kontext when you need pixel-level edits — Midjourney itself does not expose inpainting here, so use Kontext or GPT Image 1.5 downstream for surgical fixes. Because access is API-driven, you avoid the account-ban risk that comes with Selenium-based "Midjourney API" wrappers that scrape Discord.
Connect Midjourney v7 with other AI models on Martini's infinite canvas. No GPU required — start free.
Get Started FreeYes. Martini calls Midjourney v7 through an official-grade API and surfaces it as a normal node on the canvas — no Discord server, no slash commands, no moderation queue. This also avoids the account-ban risk that comes with Selenium-based "Midjourney API" wrappers that scrape the Discord client.
Every Midjourney generation returns a 2x2 grid of 4 images. You can pick V7 or Niji 7, use image prompts, add style references with --sref, or use Omni Reference to lock a character, product, or logo identity from one image.
V7 is the default photoreal/painterly model and supports Omni Reference for identity lock — drop in a reference image and the character or object is preserved across new scenes. Niji 7, released January 9, 2026, is the dedicated anime model with sharper eye and reflection rendering and an upgraded style reference, but it does not support Omni Reference. Pick V7 for character-consistent series work and Niji 7 for one-off anime stills or moodboard-driven anime aesthetics.
Black 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 detailsGoogle Imagen 4 is the lightweight entry point to Google's photorealistic image stack on Martini. Use it for fast drafts and steady photorealistic output before upgrading winning prompts to the dedicated Nano Banana 2 lineup.
View details