Google DeepMind's Veo video model, now presented as Veo 3.1: cinematic video with native audio, plus 1080p and 4K output on the official model page.

AI avatar video platform. Official plans: Free 3 videos/month, Creator $29, Pro $49 with 4K. Avatar V is the current consistency model.

Text/image-to-3D on hyper3d.ai. Free credits plus Rodin Basic $16, Pro $32, Studio $80, API $400 per month when billed yearly.

MiniMax's open-weight music generation model with studio-grade sound, natural vocal synthesis, and full-song generation from prompts and lyrics, with official ComfyUI support.

Google Gemini image model.

Previous OpenAI DALL-E 2 snapshot. DALL-E 3 is already removed from the API.

Midjourney V6 snapshot from Dec 2023. Not the current default; no invented seat table.

Models, datasets, and inference. Extra private storage $18/TB. Not a 100k-model slogan.

Deprecated OpenAI image model from November 2023. Removed from the API; OpenAI now points new work to GPT Image 2.

Stability 2024 stills family. Homepage also leads with audio and Brand Studio.

Ideogram Aug 2024 snapshot. No invented later-version or seat table.

2024 BFL open-weight stills. Not fully MIT, not the flagship.

Previous BFL image SKU. Not a 2024 Midjourney/DALL-E 3 crown.

Previous OpenAI Shap-E snapshot. Live stills path is GPT Image 2.

Tencent coding assistant. No public dollar table;

Image generation and editing skill built on the OpenRouter Image API, reaching Gemini, FLUX, Seedream, Recraft, and GPT-Image from one script.

Diagram skill that generates scientific figures with Nano Banana 2 and regenerates only when a Gemini 3.6 Flash review scores below your document type's bar.

Research talk skill that plans a deck, generates each slide as an AI image through OpenRouter, and combines them into a PDF, with a PowerPoint path.

Black Forest Labs multimodal model for video, audio, upcoming images, and action-prediction, with up to 20-second clips, native audio, and draft mode.

Google Gemini Nano Banana 2 Lite: leftover cheaper Nano Banana 2 sibling on the live Gemini image page.

OpenAI's latest image generation model for fast, high-quality create and edit jobs, with flexible sizes up to 4K and token-based API pricing.

Qwen-Image-2.1 is Alibaba's 7B open-weights model that both generates and edits images, including native transparent PNGs and edits from up to ten references.

Supra2-IMG is an Apache-2.0, 104M-parameter text-to-image DiT trained from scratch in nine hours on one H100, producing 256x256 images.