GPT Image 2 and Seedance 2.5 Workflow
A workflow creates a GPT Image 2 frame for approval, then animates it with Seedance 2.5 using EvoLink CLI with cost checks.
- 620 ★ on the repository
- Last commit
Extended access
Why this level
- The workflow sends images and prompts to an external service and creates paid generation tasks.
Install
In your terminal, with SkillFoxx CLI
npx skillfoxx add workflows/gpt-image-2-and-seedance-2-5-workflowDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- The workflow sends images and prompts to an external service and creates paid generation tasks.
This is third-party code. Review the repository files before installing.
What it does
This workflow takes a product image through two separate stages. An agent first creates a GPT Image 2 scene and shows the result. After approval, that image becomes the first frame for Seedance 2.5, and the agent polls the task until the video is complete. The workflow installs EvoLink CLI and its skill, checks model schemas and provides an API example. Parameters and approval are checked before each paid generation. The final video is saved locally, with final typography added in an editor.
Who it is for. For designers and marketers preparing short product videos with available EvoLink models.
Good fit when
- Approve the product scene before animation.
- Animate an approved still image.
- Inspect a model schema before a paid request.
- Save video from the completed generation task.
Not a fit when
- You lack permission to use the input image.
- You require exact product and logo preservation.
- You expect free generation without a service account.
Example request
Check parameters and cost first, then propose one product still. Generate video only after I approve the image and price.Limitations
Node.js 22 or later, an EvoLink account and access to the chosen models are required; inspect their current schemas first. Each paid stage is charged separately, so approve image and video costs before submission. Generation may distort products, logos and text; review the still before animation and add typography afterward. Historical community examples include other model versions and do not validate the current API; use the current schema for a new request.
How to disable. Stop new generations and remove the companion skill and CLI if needed. Inspect already created paid tasks and stored media separately in the account.
FAQ
Why use an intermediate still?
The user reviews product details, composition and logo before animation.
Does task creation return the finished video?
No. Poll the original identifier until completion.
Can it generate silent video?
The API example uses `generate_audio: false`.
Is draft mode available?
The guide describes a draft and separately charged final conversion; check availability first.
How is the first frame supplied?
The API receives the approved URL in `image_urls`.
Discussion
No questions or reviews yet.
Related
WorkflowsTwo skills for generative video and images: video writes Seedance, Kling and Veo prompts by dramaturgy rules, image picks the model and its syntax
The skill breaks a sales video into a storyboard and writes a prompt pack for the Seedance video model in Jimeng.
A skill that turns a video idea into Seedance 2.5 settings, reference roles and one paste-ready prompt for the video model.
motion-video-production: a skill for motion videos
motion-video-production
A skill that takes an agent through seven stages for a 15 to 90 second video, a script checking each stage before the next
A skill that takes a product name to a 30-second Apple-keynote-style video for Seedance 2.5, with keyframes and a quality check.
A skill that improves Seedance prompts, plans storyboards and generates video through Atlas Cloud, plus a library of ready prompts
README in short
The guide separates API instructions from creative prompts. Example prose describes intent; technical parameters come from the selected model schema.