SEELE TV / Prompt archive

z-image prompts: prompt writing

Use “z-image prompts” to shape prompt-authoring brief within general prompt planning. Focus on subject and action, composition and beat order, constraints and end state, then keep each variation anchored to the same subject, action, setting, and intended ending.

Production workflowPrompt directions

Search this collection

Collection categories

Generation method

Choose how the production brief begins.

Popular prompts / Model flexible

All video prompts

4 directions

Prompt 01Media reserved

Text generationScene16:915 sec

Z Image Prompts — Establish the world

Create a 15 sec 16:9 video direction for “z image prompts” in the context of general prompts.
Subject and action: Show the subject entering the setting, performing one clear action, and reaching a visible end state across three connected beats.
Camera and edit: Begin with a restrained wide establishing frame, move to a medium action shot, and finish on one legible detail.
Continuity: Preserve subject identity, wardrobe, hero-object details, geography, lighting direction, and direction of travel across every shot.
Sound: Use original location ambience, tactile action sounds, and no copyrighted music.
Production focus: Make reviewed z image prompts workflow and general prompt planning checklist visible through the scene rather than explaining it with text overlays.
Delivery: 16:9, 15 sec, text-led; realistic motion and material behavior; no logos, fake interface, duplicated subjects, impossible physics, or unsupported result claims.

Start Creating Source reserved

Prompt 02Media reserved

Text generationSocial9:1612 sec

Z Image Prompts — Build a vertical social cut

Create a 12 sec 9:16 video direction for “z image prompts” in the context of general prompts.
Subject and action: Communicate the premise in the first beat, demonstrate one change in the middle, and hold the result long enough to read.
Camera and edit: Use an immediate close opening, two readable handheld reframes, and a stable final composition designed for a vertical crop.
Continuity: Preserve subject identity, wardrobe, hero-object details, geography, lighting direction, and direction of travel across every shot.
Sound: Keep speech original and concise; connect cuts with room tone and motivated practical sounds.
Production focus: Make reviewed z image prompts workflow and general prompt planning checklist visible through the scene rather than explaining it with text overlays.
Delivery: 9:16, 12 sec, text-led; realistic motion and material behavior; no logos, fake interface, duplicated subjects, impossible physics, or unsupported result claims.

Start Creating Source reserved

Prompt 03Media reserved

Reference generationReference16:918 sec

Z Image Prompts — Preserve a supplied reference

Create a 18 sec 16:9 video direction for “z image prompts” in the context of general prompts.
Subject and action: Introduce the referenced subject, show one physically plausible interaction, and return to a composition that can be checked against the source.
Camera and edit: Use the supplied reference as the identity, material, palette, and proportion constraint; cover it with wide, medium, and detail views.
Continuity: Preserve subject identity, wardrobe, hero-object details, geography, lighting direction, and direction of travel across every shot.
Sound: Use grounded ambience and synchronized object sounds; do not imply audio that is not established by the scene.
Production focus: Make reviewed z image prompts workflow and general prompt planning checklist visible through the scene rather than explaining it with text overlays.
Delivery: 16:9, 18 sec, reference-led; realistic motion and material behavior; no logos, fake interface, duplicated subjects, impossible physics, or unsupported result claims.

Start Creating Source reserved

Prompt 04Media reserved

Reference generationContinuity4:320 sec

Z Image Prompts — Stress-test continuity

Create a 20 sec 4:3 video direction for “z image prompts” in the context of general prompts.
Subject and action: Repeat one subject, one hero object, and one spatial relationship through setup, action, reaction, and resolved end frame.
Camera and edit: Stage four connected shots with consistent screen direction, eyelines, lens logic, and motivated camera movement.
Continuity: Preserve subject identity, wardrobe, hero-object details, geography, lighting direction, and direction of travel across every shot.
Sound: Carry one continuous ambient bed across edits and add only original, scene-motivated effects.
Production focus: Make reviewed z image prompts workflow and general prompt planning checklist visible through the scene rather than explaining it with text overlays.
Delivery: 4:3, 20 sec, reference-led; realistic motion and material behavior; no logos, fake interface, duplicated subjects, impossible physics, or unsupported result claims.

Start Creating Source reserved

How to use the Model flexible archive

Treat the prompt as a production brief.

Define the prompt-authoring brief behind z-image prompts

For Z-image Prompts, state the subject, environment, action objective, emotional beat, and end condition in plain production language. These invariants keep general prompt planning variants comparable instead of producing unrelated ideas. Clarify the intended medium and outcome, then write subject, action, context, composition, constraints, and an observable end condition. Prefer concrete relationships over adjective lists, and separate facts from proposed visual treatment. Write the decision owner and intended handoff beside the brief so a search phrase cannot be mistaken for a verified product capability or an instruction that has already been executed. For this decision, preserve the evidence table, and ask the source custodian to record source fidelity before the evidence refresh.

Apply the general prompt planning structure

Turn the phrase into a production brief with a medium, subject, action, setting, composition, ordered beats, constraints, and a reviewable end state. Separate the durable creative direction from syntax that belongs to a particular interface. This makes the prompt useful even when tools, model names, or accepted parameters change. For “z-image prompts”, keep a visible distinction between required content, optional treatment, exclusions, and facts that need evidence. That structure gives controlled variants a stable baseline and lets a reviewer identify which instruction caused a material change. For this decision, preserve the review copy, and ask the source custodian to record revision intent before the delivery pass.

Prepare authorized inputs for still-image composition

This query calls for an authorized subject reference, intended use, composition, pose or object arrangement, lighting, background, protected details, and delivery format. Specify spatial relationships and light before aesthetic modifiers. Use observable attributes, preserve factual and identity details, and define how the image will be reviewed at its destination size. Record the source, permission, intended audience, protected details, and reviewer before testing language. The goal is a traceable creative proposal, not an assumption that a named platform, model, or workspace will perform the requested action. Before approval, preserve the rights memo, and ask the rights reviewer to record temporal order before the evidence refresh.

Build controlled variants and observable acceptance checks

For this owner, the first review pass should make image observable rather than merely decorative. Change one meaningful dimension per version and label the hypothesis, invariant details, expected difference, and rejection condition. The prompt is ready for review when every phrase changes a meaningful decision, contradictions are removed, and a second reader can describe the expected result without inventing missing context. Keep failed variants in the decision record so the final wording is explainable rather than selected by impression alone. For the working record, preserve the rights memo, and ask the policy reviewer to record visible continuity before the release review.

Review authorization, safety, and changing product facts

Do not treat a generated suggestion as evidence, a real event, an endorsement, or permission to reproduce another person's identity or copyrighted work. Use only authorized source material, preserve attribution and provenance, avoid deceptive identity or factual claims, and verify any changing product or platform statement in current first-party documentation. Treat every named model, competitor, access term, platform rule, identity use, commercial claim, and output specification as a dated evidence question. If authorization or first-party support is missing, keep the language editorial, stop the handoff, and record the unresolved gap instead of inventing a workaround. Before moving on, preserve the rights memo, and ask the channel editor to record source fidelity before the dated decision.

Approve a reversible prompt handoff

Read the prompt once for intent, once for visual or temporal coherence, and once for rights and factual risk. Remove decorative terms that do not change an observable decision, then test controlled variants rather than rewriting every instruction at the same time. Before approving “z-image prompts”, check purpose, source rights, identity consent, factual support, continuity, disclosure, destination requirements, and the named review owner. Preserve the original brief and version notes. This handoff supplies authored guidance only and neither runs generation nor guarantees access, quality, speed, licensing, publishing, downloads, or outcomes. Before moving on, preserve the reference set, and ask the channel editor to record evidence freshness before the dated decision.

Evidence boundary

Use the source, rights and current workspace controls as the acceptance boundary.

Before you hand off

Questions to resolve.

Does this “z-image prompts” page execute a prompt or generate media?

No. It is an editorial planning and evaluation page. It does not upload a source, call a model, expose verified controls, execute generation, publish media, or display a generated result. At this stage, preserve the failure note, and ask the accessibility reviewer to record input provenance before the release review.

How should a reviewer evaluate this prompt-authoring brief?

Keep one stable brief, change one instruction at a time, record the expected difference, and compare the result with explicit acceptance and rejection criteria. The prompt is ready for review when every phrase changes a meaningful decision, contradictions are removed, and a second reader can describe the expected result without inventing missing context. At this stage, preserve the authorization record, and ask the factual editor to record camera logic before the release review.

What evidence boundary applies to these general prompt planning?

Use only authorized source material, preserve attribution and provenance, avoid deceptive identity or factual claims, and verify any changing product or platform statement in current first-party documentation. Verify changing model, product, price, access, policy, license, input, output, and entitlement statements in dated first-party sources. Search demand and prompt wording are not capability evidence. At this stage, preserve the rights memo, and ask the source custodian to record claim scope before the release review.

Continue the workflow

Take a prepared brief into the workspace.

Continue in the SEELE workspace to inspect the currently available Film & CG workflow.

Try it free