Back to directory

GPT-Image-2-Seedance-2.5-Workflow

A curated collection of workflows, prompt templates and creator examples for combining GPT Image 2 image generation with Seedance 2 video generation, plus installable agent skills that add both generators to a coding agent.

GPT-Image-2-Seedance-2.5-Workflow

This repository collects workflows, prompt templates and real creator examples for a two-step generative pipeline: GPT Image 2 produces a consistent starting image, and Seedance 2 animates that image into video. Examples are drawn from social-media creators, community experiments and production workflows, organized around storyboard techniques such as taking a single image through a grid storyboard into a finished shot sequence.

Two installable skills, distributed through their own npm packages, add GPT Image 2 image generation and editing and Seedance 2 video generation directly to a coding agent's toolset; installers can auto-detect a known skills directory for Claude Code, OpenCode, Cursor or OpenClaw, or prompt for a location. Using the workflow requires an EvoLink API key and, for the newest Seedance version, enrollment in its early-access program.

More in Generative media

See all 146
  • Blender Copilot

    github.com

    A Copilot-style AI chat panel inside Blender that runs its agent loop in Blender's own Python process, executes the model's generated code against the live scene, and wraps every conversational turn in a single undo step.

  • A ComfyUI add-on that patches ComfyUI-GGUF so Qwen-Image-2.1 models can run fully as GGUF files, fixing a text-encoder mismatch and missing architecture detection until upstream support arrives.

  • A ComfyUI node that expands a short prompt into a full styled prompt, negative prompt and aspect ratio for Qwen-Image-2.1, using one of 17 photographic styles.