10+ Surreal Seedance 2.0 Prompts That Look Absolutely Insane
Combining reference image analysis via LLMs with second-by-second timeline prompting provides AI creators a repeatable framework to execute complex, surreal visual effects.
What this lesson covers
Yaroflasher details a step-by-step pre-production and generation workflow for creating surreal AI video clips using Seedance 2.5. He covers extracting prompt concepts from reference images with Claude, keyframe creation, and multi-image compositing inside FlashBoards.
Key takeaways from the creator
AI-extracted notes, not independently verified product claims. Timestamp links let you check each point in the original video.
- 01:28 ↗
Organizing surreal visual references on digital mood boards during pre-production provides a structured baseline for prompt generation.
- 02:13 ↗
Feeding reference images into Claude or DeepSeek allows creators to automatically extract detailed, structured prompts for surreal concepts.
- 02:50 ↗
Specifying exact second-by-second action timelines within Seedance prompts ensures tight temporal control over generated video events.
- 03:32 ↗
Inputting a personal character photo alongside a generated background image enables multi-image compositing within Seedance 2.5.
- 08:07 ↗
Adding explicit prompt instructions to exclude audio prevents Seedance from automatically generating unwanted background music.
Workflow outlined in the video
- Gather visual references on Pinterest and organize them inside a digital mood board for pre-production planning.
- Upload reference imagery to Claude or DeepSeek to reverse-engineer descriptive image-generation prompts.
- Generate high-quality background keyframes using base image models like Nano Banana 2.
- Construct video prompts with second-by-second breakdowns and amateur camera tags for controlled motion.
- Combine base image inputs with character portrait uploads in Seedance 2.5 to composite original subjects into surreal scenes.
- Instruct Seedance explicitly in the prompt to avoid music generation if custom audio post-production is planned.
Before you use this workflow
These notes describe the source video at its publication date. Model access, pricing, connectors and interfaces may have changed. Check the original source and the provider’s current documentation before installing an add-on, connecting an account or spending credits.
ReelStack has not independently tested this workflow. Preview one representative shot and check motion, continuity and output quality before applying it to a full production. No result, cost saving or model capability is guaranteed.
Explore the tools
How to interpret the numbers
4,920 views captured 27 September 2026. ReelStack recommendation score: 31/100. Formula: radar-v5. This is ReelStack’s calculation, not a YouTube rating or a measure of factual accuracy.
Show the calculation
- 45% performance: 0.59× views vs 6 other channel videos observed at a similar age. View-evidence factor 83% (views / (views + 1,000))
- 25% freshness: 3/100 with a 14-day half-life
- 20% momentum: 4 views/day vs 4 channel baseline (3 comparable uploads), with the same view-evidence factor
- 10% engagement: 82/100; likes + 4× comments, smoothed with a 500-view neutral prior