Checklist the per-video bar — engine/sim
89.7/100
quantitative quality · weights learn from your reviews (
engine.sim.memory review topic-et-nft good|bad)⚠ 1 flag(s) — not yet ship-ready: too_complex · see docs/strategy/VIDEO-CHECKLIST.md
Composition comp · template family · expected output
9:16 Reelrendered1:1 Squarepending16:9 Widepending9:16 4Kpending1:1 4Kpending16:9 4KpendingGIF (SMS)pending
expected output: 1/7 rendered — same matrix the /media preview surfaces for this asset.
Composition layer × scene 9 scenes · 66.7s · comp_id + rendered still + tier + the script
| # | Layer (comp_id · still · tier) | Beat | Timecode | Motion | Logo | Audio | VO / on-screen / caption |
|---|---|---|---|---|---|---|---|
| 1 |  matches intent shared field signature-3d | open | 0–7.5s | spatial-parallax | icon·ember-fill | ♪ — | Most NFT projects fall apart on the boring parts: generating thousands of consistent assets and getting the metadata right. on-screen: On-chain assets, done right |
expected on screen: black ground · cone hero in the shared Signal Field · Augur leads · node-graph · spatial-parallax · icon·ember-fill logo · caption bottom-left spec (the prompt): comp_id shared Signal Fieldvisual node-graphshape coneground blacktreatment ember-fillmotion spatial-parallaxpower summoninstrument summon→three-mark | |||||||
| 2 |  matches intent ProcessFlow template | legacy | 7.5–14.3s | crossfade-8f | icon·wireframe | ♪ — | The old way was an artist hand-layering traits, then a spreadsheet praying the rarity math and metadata matched the art. on-screen: Old way: hand-layer 10k traits |
expected on screen: black ground · a ProcessFlow panel over a dimmed Signal Field · Augur leads · crossfade-8f · icon·wireframe logo · caption bottom-left spec (the prompt): comp_id ProcessFlowshape coneground blacktreatment wireframemotion crossfade-8fpower morphinstrument decay→three-symboliccurate steps | |||||||
| 3 |  matches intent NumberedList template | teach | 14.3–21.5s | kinetic-build | icon·wireframe | ♪ — | We start by defining the trait set and rarity rules, the design language of the collection, before generating anything. on-screen: Step 1: define the trait set |
expected on screen: black ground · a NumberedList panel over a dimmed Signal Field · Augur leads · node-graph · kinetic-build · icon·wireframe logo · caption bottom-left spec (the prompt): comp_id NumberedListvisual node-graphshape coneground blacktreatment wireframemotion kinetic-buildpower morphinstrument morph+laser→html-in-canvas-panelcurate items, nodes | |||||||
| 4 |  matches intent ChecklistCard template | teach | 21.5–30.1s | kinetic-build | icon·wireframe | ♪ — | Then we diagram the pipeline: a generator combines traits, renders each piece, and writes metadata that matches the image exactly. on-screen: Traits -> generator -> tokens |
expected on screen: black ground · a ChecklistCard panel over a dimmed Signal Field · Augur leads · node-graph · kinetic-build · icon·wireframe logo · caption bottom-left spec (the prompt): comp_id ChecklistCardvisual node-graphshape coneground blacktreatment wireframemotion kinetic-buildpower morphinstrument morph+laser→three-diagramcurate items, nodes | |||||||
| 5 |  matches intent CheatSheet template | teach | 30.1–37.800000000000004s | kinetic-build | icon·wireframe | ♪ — | Each piece is rendered through a style-locked model on Replicate, so ten thousand assets share one coherent look instead of drifting. on-screen: Style-locked AI renders |
expected on screen: black ground · a CheatSheet panel over a dimmed Signal Field · Augur leads · node-graph · kinetic-build · icon·wireframe logo · caption bottom-left spec (the prompt): comp_id CheatSheetvisual node-graphshape coneground blacktreatment wireframemotion kinetic-buildpower morphinstrument morph+laser→html-in-canvas-codecurate nodes, points, uses | |||||||
| 6 |  matches intent NodeGraphCard template | teach | 37.8–45.9s | kinetic-build | icon·wireframe | ♪ — | It flows clean: render the set, pin images and JSON to storage, then verify every token's metadata points at the right art. on-screen: Render -> pin -> verify metadata |
expected on screen: black ground · a NodeGraphCard panel over a dimmed Signal Field · Augur leads · node-graph · kinetic-build · icon·wireframe logo · caption bottom-left spec (the prompt): comp_id NodeGraphCardvisual node-graphshape coneground blacktreatment wireframemotion kinetic-buildpower morphinstrument morph+laser→three-flowcurate hub, nodes | |||||||
| 7 |  matches intent RankList template | proof | 45.9–53.3s | receipts-count | icon·wireframe | ♪ — | A full collection generates with matching art and metadata, no mismatched tokens, no last-minute panic before mint. on-screen: Consistent at full scale |
expected on screen: black ground · a RankList panel over a dimmed Signal Field · Augur leads · receipts · receipts-count · icon·wireframe logo · caption bottom-left spec (the prompt): comp_id RankListvisual receiptsshape coneground blacktreatment wireframemotion receipts-countpower receiptsinstrument spotlight→html-in-canvas-receiptscurate rows, statsLabels | |||||||
| 8 |  matches intent shared field signature-3d | futurist | 53.3–60.4s | spatial-parallax | icon·wireframe | ♪ — | Soon the art isn't static, it can respond to on-chain events, so a collection evolves with the people who hold it. on-screen: Art that reacts on-chain |
expected on screen: black ground · cone hero in the shared Signal Field · Augur leads · spatial-parallax · icon·wireframe logo · caption bottom-left spec (the prompt): comp_id shared Signal Fieldshape coneground blacktreatment wireframemotion spatial-parallaxpower spatial-parallaxinstrument laser-fire→three-forward | |||||||
| 9 |  matches intent shared field signature-3d | resolve | 60.4–66.7s | coalescence | icon·ember-fill | ♪ swell | Planning a collection? We'll build the generator and get the metadata airtight. Start at temerarii.xyz. on-screen: Build your collection |
expected on screen: black ground · cone hero in the shared Signal Field · Augur leads · coalescence · coalescence · icon·ember-fill logo · caption bottom-left spec (the prompt): comp_id shared Signal Fieldvisual coalescenceshape coneground blacktreatment ember-fillmotion coalescencepower coalescenceinstrument coalescence→three-coalescence | |||||||
Format stack 3 aspects · same scenes[], re-cropped
9:16
1080×1920
Stories · TikTok · YouTube Shorts · Reels
1:1
1080×1080
LinkedIn · Facebook · Instagram
16:9
1920×1080
X/Twitter · YouTube · LinkedIn video
Channels 12 destinations
LinkedInX/TwitterYouTubeInstagramFacebookThreadsTikTokPinterestBlueskyEmailSMSBlog
Social captions supplemental published copy · per channel (comp_id level)
tiktokMost NFT projects die on the boring parts. (AI-assisted.)
Not the art, the plumbing: generating thousands of consistent pieces and getting the metadata to match. Here is the build: define the trait set and rarity rules first. Diagram the pipeline, traits to generator to tokens. Render each piece through a style-locked model so ten thousand assets share one look. Then pin the images and JSON, and verify every token points at the right art. temerarii.xyz.
instagramNFT projects rarely die on the art.
They die on the plumbing.
The build:
Define the trait set and rarity rules.
Diagram traits to generator to tokens.
Render through a style-locked model.
Pin images and JSON.
Verify every token points at the right art.
Build your collection at temerarii.xyz
#NFT #GenerativeArt #Web3 #BuildInPublic #Temerarii
linkedinNFT projects rarely fall apart on the art. They fall apart on the boring parts: generating thousands of consistent assets and getting the metadata right.
The build, end to end:
1. Define the trait set and rarity rules first, the design language of the collection, before generating anything.
2. Diagram the pipeline: a generator combines traits, renders each piece, and writes metadata that matches the image exactly.
3. Render each piece through a style-locked model on Replicate, so ten thousand assets share one coherent look instead of drifting.
4. Pin images and JSON to storage, then verify every token's metadata points at the right art.
Done right, the full collection generates with matching art and metadata, no mismatched tokens, no last-minute panic before mint.
Planning a collection? We build the generator and get the metadata airtight. temerarii.xyz
xNFT projects die on the boring parts: consistent art at scale and metadata that matches. The fix: define traits, diagram traits-to-tokens, render style-locked, pin images plus JSON, verify every token points at the right art. temerarii.xyz
facebookMost NFT projects do not fall apart on the art. They fall apart on the boring parts: generating thousands of consistent pieces and getting the metadata right.
The build: define the trait set and rarity rules first. Diagram the pipeline, traits to generator to tokens. Render each piece through a style-locked model so ten thousand assets share one look instead of drifting. Then pin the images and JSON to storage, and verify every token's metadata points at the right art.
Planning a collection? We build the generator and get the metadata airtight. Start at temerarii.xyz.
threadsNFT projects rarely die on the art, they die on the plumbing: consistent assets at scale and metadata that matches. The build: define traits and rarity, diagram traits-to-tokens, render style-locked, pin images plus JSON, verify every token points at the right art. Build your collection at temerarii.xyz
pinterestHow to build an NFT collection the right way: define your trait set and rarity rules, diagram the generator pipeline, render style-locked AI art on Replicate, pin images and metadata to storage, and verify every token points at the correct art. A plain-language guide to generating thousands of consistent on-chain assets with airtight metadata, no mismatched tokens before mint. temerarii.xyz
blueskyNFT projects rarely die on the art, they die on the plumbing: consistent assets at scale and metadata that matches. Define traits and rarity, diagram traits-to-tokens, render style-locked, pin images plus JSON, verify every token points at the right art. Build it at temerarii.xyz
youtubeHow to Build an NFT Collection That Doesn't Break at Mint
Most NFT projects do not fall apart on the art. They fall apart on the boring parts: generating thousands of consistent assets and getting the metadata right. This video walks the build end to end.
The steps:
- Define the trait set and rarity rules first, the design language of the collection, before generating anything.
- Diagram the pipeline: a generator combines traits, renders each piece, and writes metadata that matches the image exactly.
- Render each piece through a style-locked model on Replicate, so ten thousand assets share one coherent look instead of drifting.
- Pin the images and JSON to storage, then verify every token's metadata points at the right art.
Done right, the full collection generates with matching art and metadata, no mismatched tokens, no last-minute panic. And soon the art is not static, it can respond to on-chain events, so a collection evolves with the people who hold it.
Planning a collection? We build the generator and get the metadata airtight. temerarii.xyz