Start with the work. Trace it back to the maker and method.

Creator Amrutraj →

A video prompt depicting Elon Musk traveling to Mars inside a Starship and interacting with an AI.

Creator Aatif J →

A warm and natural portrait prompt depicting a young man laughing heartily in a cozy, rustic cafe.

Creator AI Theory →

A comprehensive video generation prompt for creating a 10-second stop-motion animation with Gemini Omni. The prompt follows a scripted sequence about mental stress and an AI assistant app, using a handmade paper-cut art style.

Creator 真坂参志郎 →

A narrative prompt depicting a nostalgic Showa-era scene of a grandmother and grandchildren together, focusing on character interaction and dialogue.

Creator PixieVerse →

An ultra-fast-paced anime action edit for the character Kael Drayn, featuring a hardcore sci-fi aesthetic and variable frame-rate effects.

Creator Heather Green →

A detailed prompt for generating a whimsical alphabet set in a 1970s graphic style, featuring playful rounded lettering, bold outlines, and bright soft-toned decorations.

Creator Pan →

A creative prompt for generating a high-maintenance luxury beauty and skincare routine with a tsundere ASMR personality, presented in a vintage camera shooting style.

Creator Rob →

This workflow is not flashy — it solves a real tattoo-design communication problem. A PrimitiveStringMultiline node takes a one-line idea, a ComfySwitchNode toggles between common tattoo styles such as blackwork, fine-line and geometric, StringConcatenate assembles the final prompt, and a ResolutionSelector presets canvas ratios for patch, sleeve or flash-sheet layouts. The result is a guided input flow rather than a single block of prompt text, which is why it's worth keeping around — the same style-switch-plus-canvas-preset pattern transfers directly to other stylized image generation needs.

Creator Purz →

What makes this worth including is that it draws a clear capability boundary for 4K video generation. The source page doesn't publish a node-level breakdown, but its capability tags tell the real story: character consistency, multiple angles, lip sync, style reference and style transfer all showing up together — abilities that usually conflict in reference-to-video pipelines, where most tools can hold composition but lose identity or lip sync. Seeing all of them handled inside a single Seedance 2.0 node makes this a useful reference point for judging whether the model fits character-driven short-video work.

Creator enigmatic_e →

What's worth including here isn't the final video, it's the pattern of using an LLM as a prompt intermediary. Two reference images and a short description go into GeminiNode, which expands them into a detailed prompt in the format Seedance 2.0 responds well to; that generated prompt, together with the reference images, then feeds ByteDance2ReferenceNode for the actual render, with a MarkdownNote in between that lays the LLM-written prompt out for a human to read and edit. For anyone who keeps re-tuning prompt formatting for the same video model, this two-stage LLM-assist-then-generate structure is directly reusable.

Creator Julien Durand | MJM →

This case earns its place by solving one of the more annoying problems in video editing: consistency. Edit a single frame of a video — say, painting a red shirt onto a boxer — and the workflow propagates that change across every frame while canny edge control keeps the original motion and structure from drifting. Compared with manually retouching frame by frame or regenerating the whole clip, this single-frame-edit-plus-propagation approach is much cheaper, and it's a good fit for wardrobe swaps, color fixes, or logo replacements where consistency across the whole clip matters.

Creator v92388375-gif →

GoodCase reconstructed this prompt from the public result image and the creator's MIT-licensed Skill method, then ran two independent generations without the source image or a fixed seed. Both runs preserved the violet single-ink engraving, rococo frame, grape cluster, title, and labels at the requested 3:4 ratio. A/B stability: 8.7/10. This is not the creator's disclosed original prompt; the original model, seed, and exact prompt are unknown.

Creator v92388375-gif →

GoodCase reconstructed this prompt from the public result image and the creator's MIT-licensed Skill method, then ran two independent generations without the source image or a fixed seed. Both runs preserved the mint single-ink halftone, engraved botanical texture, editorial typography, and requested copy; one run drifted from 3:4. A/B stability: 7.8/10. This is not the creator's disclosed original prompt; the original model, seed, and exact prompt are unknown.

Creator 小森映像 →

A professional advertising prompt for generating a refreshing mint gum product photo, with ice fog, water droplets, and premium commercial lighting effects.

Creator v92388375-gif →

GoodCase reconstructed this prompt from the public result image and the creator's MIT-licensed Skill method, then ran two independent generations without the source image or a fixed seed. Both runs preserved the oversized cropped butterfly, deep-teal single ink, bitmap engraving, editorial title, labels, paper texture, and 3:4 ratio. A/B stability: 9.3/10. This is not the creator's disclosed original prompt; the original model, seed, and exact prompt are unknown.

Creator Jiade 05 →

A delightful first-person anime cooking video prompt featuring a little bunny assistant and a chef making a fluffy omelet in a cozy pastel kitchen.

Creator Northimage →

A refined multi-shot video prompt for creating a realistic 9:16 handheld selfie vlog documenting a woman at a Japanese summer festival. The video should feature consistent character details, a rhythmic chant, and a traditional festival atmosphere.

Creator Sam Aoteman →

A multi-scene video prompt for creating a 1990s Disney-style hand-drawn animation starring a raccoon and a turtle in the forest.

Creator Nexus AI →

A complex cinematic video prompt presenting a psychological horror scene about a man and his perceived reflection. The shot moves from a symmetrical medium shot to a dramatic slow-motion mirror shatter, ending with an infinite mirrored void and a hard cut to black.

Creator Ashley Ward →

A prompt for Grok Imagine designed to generate authentic 1970s Paris documentary footage featuring a gritty 16mm film aesthetic with organic grain and natural lighting.

Creator Cinemonroll →

A whimsical video prompt depicting animated shrimp celebrating a birthday on a beach, with one singing and the others playing piano keys.

Creator Cencen →

A cinematic 3D animated chase-scene prompt inspired by classic American silent comedy, with complex physics effects and character interactions.

Creator PixelAIGC →

A video prompt describing a conversation among friends at a bar about the differences between boys' and girls' toys in childhood.

Creator 设计师学Ai →

This workflow can be used with one click on liblibai, with plugins and models already installed. Recommended large model: majicMIX realistic, or other realistic-style SD1.5 large models. Recommended LoRA: Lin He - Wuhua Tianbao - e-commerce commercial product modeling and rendering premium-assist LoRA. If you do not have a membership, you can use other SD1.5 e-commerce-style LoRAs. The workflow tutorial is being updated. Workflow steps: 1. In the first Load Image module, upload the product image. 2. In the second Load Image module, upload the product style reference image. 3. Load the correct models required in the workflow. If you are not sure how to adjust them, you can watch the video tutorial (video tutorial pending update). 4. Click Generate. Workflow compiled and published by [Designer Learns Ai]. If you like this workflow, remember to follow me. My homepage has more workflows published. Workflow page; for commercial use, you must also verify the base model, LoRA, nodes, and input materials. License: not specified on the original page, pending manual review.