Runway/upscale_v1 is Runway’s production-targeted video upscaler model (model id upscale_v1) designed to increase video resolution by 4× up to 4K (capped at 4096 pixels on a side). It’s available through Runway’s API surface and is also packaged on third-party model hosting marketplaces (e.g., CometAPI).
Model Type: Video
Gen-4 Image is Runway’s flagship multimodal image-generation model in the Gen-4 family that supports prompted generation plus visual references (you can “@mention” reference images) to produce highly controllable, stylistically consistent outputs for image and image→video pipelines.
Model Type: Image Generation
Runway Gen-4 Aleph(model id /gen4_aleph) is Runway’s in-context, video-to-video model that extends the Gen-4 family with powerful video editing, shot continuation and view-synthesis capabilities. In plain terms: Aleph can take an input clip and perform complex edits — add/remove/replace objects, relight, restyle, generate novel camera angles, and even generate the “next shot” in a sequence — driven by text prompts and optional reference images. This release is presented as a major step toward coherent, multi-shot video generation and in-context editing.
Model Type: Video
Act-Two is Runway’s next-generation AI performance capture and character animation tool: it ingests a short driving performance (a webcam or phone video of someone acting a scene) plus a character reference (image or video) and generates an animated character performance that transfers body, facial expression and hand motion to the character. Act-Two is offered inside Runway’s web product and as a model available through API ecosystem.
Model Type: Video
Seedream 4.0 (model identifier doubao-seedream-4-0-250828) is ByteDance’s newest image-creation foundation model that unifies text→image generation and image editing in a single architecture. The model was announced in early September 2025 and is positioned for high-resolution (up to 4K) generation, multi-reference workflows, and fast inference for production use.
Model Type: Image Generation
Hailuo 02 API is an asynchronous, HTTP‑based service from MiniMax that lets developers generate professional‑grade, cinematic videos from either text or image prompts.
Model Type: Video
Qwen3-Max-Preview is Alibaba’s latest flagship preview model in the Qwen3 family — a trillion+-parameter, Mixture-of-Experts (MoE) style model with an ultra-long 262k token context window, released in preview for enterprise/cloud use. It targets *deep reasoning, long-document understanding, coding, and agentic workflows.
Model Type: Chat
Kimi K2 is an open‑source, trillion‑parameter Mixture‑of‑Experts language model with a 128K‑token context window, optimized for high‑performance coding, agentic reasoning, and efficient inference.
Model Type: Chat
Gemini 2.5 Flash Image (aka “Nano banana” ) is Google’s newest native image generation + editing model in the Gemini 2.5 family. It focuses on multi-image fusion, precise natural-language edits, and fast multimodal workflows.
Model Type: Image Generation
DeepSeek-V3.1 is the newest upgrade in DeepSeek’s V-series: a hybrid “thinking / non-thinking” large language model aimed at high-throughput, low-cost general intelligence and agentic tool use. It keeps OpenAI-style API compatibility, adds smarter tool-calling, and—per the company—lands faster generation and improved agent reliability.
Model Type: Chat
