KNOWN STATE — INDEPENDENT INFORMATION COLLECTION

We use KNOWN STATE because this site is an independent collection of information from cited sources and recorded observations as of the stated review date. This collection is in no way official and is not documentation, guidance, or endorsement issued by OD or its operators. Information and account behavior can change.

INDEPENDENT WEBSITE — NO AFFILIATION

duhployed.com is independently owned and operated. It is not affiliated with, associated with, owned by, operated by, sponsored by, endorsed by, or approved by OD, Dream Studio USA, Inc., or any of their parent companies, holding companies, subsidiaries, affiliates, or related entities.

Third-party trademarks belong to their respective owners. Read the independence and trademark notice.

OD / learning library
Learning library / Ivory ghost setup and scene
Download document ↓Find related resources →

Ivory ghost setup and scene

Matching setup, scene, edit example, and failure checks.

Prompt structure reviewed. Efficacy unverified; limited native observations available. Read the native trial report.

The manifest review_status is a retained source-export label; it is separate from current native trial coverage.

Native efficacy of this exact published file is unverified. The report distinguishes manually authored image diagnostics, historical generator replies and exact-version instruction trials.

Role
Application guide
Category
Character examples
Revision
Ivory skeleton revision; 2026-10-31 accepted-form and source-handoff revision
Target / route
Read alongside the matching ghost pack
Copy destination
Read the guide; copy only the matching appearance or resolved scene text to its stated destination.
Primary pack
Ivory ghost example

Before copying

Read the stated destination and application notes first. They identify whether to copy complete instructions into an authoring LLM, paste its generated output, or read a guide. Replace requested placeholders. Nothing in the template runs automatically or performs an OD generation.

  • Text structure and application reviewed; no live OD generation or preservation benchmark was run.

Published text

OD VIVID 1.0 — REALISTIC GHOST
CPD, ENGINE PLACEMENT AND REFERENCE SCENE

TARGET
An original adult female apparition rendered as a live-action supernatural film effect. The preferred reference is the second image: a lifelike pale face and silver-white hair above a complete, intact skeletal body inside a faint blue transparent outline. Its visible skeletal body extends from the neck through the fingers and toes; the face remains human. The first image's opaque gown and mostly flesh-covered limbs are not the target.

INSTALLATION
1. Select the realistic character workflow and Vivid 1.0 for image generation. The engine text cannot select the model for you. Replace the previous rendering engine within this character's intended scope.
2. Paste only OD_Ivory_Ghost_CPD.txt into Custom Physical Details. The Known State realistic-character workflow recommends beginning with the same focused appearance prompt in Custom Face Details too, where that field is available. Keep the two fields consistent while evaluating the base.
3. Place the art-engine text once in Extra Details as image-prompt-writing rules for the chat LLM. Keep personality in Additional Personality Details. Extra Details is documented as chat-facing; automatic injection of this engine into every image-generation route is not established. For manual Generate, include its short style core in the scene prompt, as below.
4. Review other active appearance fields and presets for conflicting face, hair, flesh coverage, physique or rendering instructions. Correct conflicts at their source; appending more emphasis cannot reliably settle contradictory inputs. Keep the native settings as close to the intended form as available controls permit.
5. Keep the hall, levitation pose, mist and lighting in the scene prompt. They are not permanent identity. Use the saved CPD without Fluidity score tags, weighted blocks or BREAK separators; natural-language Vivid prompting is the documented starting point.

REFERENCE SCENE — SELECTED CHARACTER / GENERATE
Paste the paragraph below into the scene prompt with the character selected. Its permanent appearance should already be supplied by the card.

photorealistic live-action rendering, lifelike surface detail, natural perspective, coherent light and shadow, selective focal sharpness. Full-length view of the apparition suspended above a stone floor in a tall Gothic hall, with space around her hair, hands and feet. Her own intact ivory skeletal body is clearly visible from neck to toes through a faint blue transparent outline, beneath her lifelike human face. Her right arm is raised toward image left, her left arm extends lower toward image right, and both hands remain clear of the torso. Her knees are gently bent and both feet are distinct. Long silver-white hair extends toward image right; wisps of translucent vapor trail behind her lower body. Cool-white light from high behind her left shoulder creates a soft white rim and gently reflected light on her face and bones. Thin shoulder mist leaves the face, ribs and limb joints clear. Dark stone arches recede behind her.

For Free Play or another standalone input that does not supply the card, insert the CPD after the style-core sentence, then use the remaining scene description. Avoid repeating identity that the chosen route already supplies.

EDIT THE PREFERRED REFERENCE — ALTERNATIVE WORKFLOW
Select and supply the second original image to the actual image editor. Use this edit prompt instead of rebuilding the character from text:

Refine this supplied image as a photorealistic live-action supernatural film still. Preserve the same adult woman's face, silver-white hair, exact skeletal proportions and joint positions, pose, camera, crop, Gothic hall and existing lighting. Retain one intact ivory skeletal body connected from the neck through both hands and both feet, aligned with her existing faint blue transparent human outline. Keep the face lifelike and the bones clearly distinguished from the transparent envelope. Refine bone surface detail and edge clarity without changing their shape or size. Keep the spectral outline thin and transparent, and any mist sparse enough for the existing bones and facial features to remain readable.

Make one category of refinement at a time. Return to the clean original if the face or anatomy drifts; do not adopt an unwanted edit as the new character definition.

HOW THE SUPPLIED COMMENT WAS USED
Translucent outer form, desaturated facial color, soft white rim light and sparse shoulder mist support this target. They have separate jobs: the envelope supplies transparency, bones supply readable anatomy, and lighting integrates both into the scene. Double exposure is omitted because it may create overlapping faces, bodies or skeletons. Mist and rim light are scene choices, not permanent body traits.
If making a video later, begin from an approved still using an available image-to-video route. A source still supplies a visual anchor but does not guarantee facial or skeletal consistency. No video generation is required for this CPD package.

CHECK THE ACTUAL RESULT
Compare the face and skeletal proportions against the preferred reference. Check that the bones form her own connected body, hands and feet remain complete in a full-length scene, and the outer envelope stays faint enough to reveal them. A portrait crop will necessarily omit lower anatomy. Clothing or foreground objects can also hide bones; transparency of her body does not make unrelated materials transparent.
The CPD and engine are designed to reduce conflicting instructions; they have not been tested through live OD generation. If required presets continue forcing an opaque human torso, text alone may not achieve the target. Use the supplied reference in the editor or a supported reference-based route for closer control.

KNOWN STATE GUIDANCE REVIEWED — 27 OCTOBER 2026
Vivid 1.0's photorealistic positioning:
https://ourdream.ai/generate
Natural descriptions for Vivid, focused prompts and cautious emphasis:
https://guide.ourdream.ai/characters/image-prompting
Permanent appearance fields and realistic-character setup:
https://guide.ourdream.ai/characters/creation-workflow
Chat-facing field responsibilities:
https://guide.ourdream.ai/characters/story-and-personality
Selected-character appearance versus scene details:
https://guide.ourdream.ai/characters/photo-shoot-and-gallery
Clean-base editing and consistency:
https://guide.ourdream.ai/characters/consistent-images

These sources support the format and workflow. The opacity split and omission of double exposure are design choices for this reference, not documented guarantees of model behavior.

ACCEPTED FORM, COVERAGE AND SOURCE RECORD
Choose canonical permanent identity or an explicitly requested temporary current-form profile before generating text. For a changing character, supply the accepted transition, form/stage, complete relevant visible appearance and unchanged anchors. A partial mixture is intentional only when defined. Do not blend every form, infer new anatomy or copy obsolete skin/hair back over a changed feature.
Only a canonical CHARACTER result is intended to replace permanent CPD. A CURRENT-FORM profile stays with the actual scene/image handoff unless a permanent revision is explicitly intended. A saved character or preset may still inject an older appearance: inspect and reconcile those inputs rather than assuming an ED block, snapshot or tracker overrides them.
The skin-tone automatic-clothing-coverage workaround was withdrawn by its supplied author after confounded initial tests and contrary clean-character results. Keep stable identity separate from what the current garments and crop reveal; field placement does not guarantee occlusion. An affection score, stage label or SCE heading does not establish permission, undressing or a completed action.
For editing, select actual accepted source pixels. Record source -> crop -> attempted edit -> accepted result, including failed passes and each displayed charge, outside the generation prompt. State the change and its explicit preservation exception; inspect each subject, pose and background geometry separately. Multiple-image identity/composition transfer is only an experiment when the route actually accepts those inputs.
The supplied abbreviation PD is not expanded; do not guess its field. Replacing smoke or mist with vapors is an untested lexical suggestion, not a verified fix. Emphatic copy wording, nested weights and a selected success do not isolate a reliable cause. A still crop is not camera motion, and native video output must be distinguished from later external splicing or audio work.
Current-form worksheet: https://duhployed.com/learn/modules/current-form-continuity.html
Tracker design review: https://duhployed.com/learn/modules/affection-tracker-review.html
Scenario worksheet: https://duhployed.com/learn/modules/scenario-engineering.html

8962 bytes · SHA-256: 19322fd47c1fdc7088187c4d6de5d0120cddbcfd2038ffcd90e00e44b81535fd

Related resources

Ivory ghost example · All Freebies · Download all art Freebies

The fourteen companion-toolkit starters remain a separate collection. For actual trials, record the model, route, settings, input, and observed result.