LOCAL-FIRST // APPLE SILICON

Your visual production pipeline. Under control.

Build reusable Concepts. Generate images and video. Restore, upscale, compare, and preserve every creative decision in one private production console.

LOCAL MLX + Metal CLOUD xAI Imagine FILES Stay yours
ALi Imagine luminous geometric signal mark
SIGNAL // 01
ENGINE READY
PROJECTALI IMAGINE STUDIO
LOCAL ENGINESKREA · FLUX 3 · LTX · QWEN
STATUSNOMINAL
PROVENANCEIMMUTABLE
00

THE REAL STUDIO // V0.9.9

One window.
The whole visual pipeline.

Generate, direct motion, review outputs, and preserve the creative trail without leaving the project.

ALi Imagine running a 20-second LTX 2.5 local audio-to-video render with the result, source frame, performance audio, and render progress visible
LTX 2.5 // LOCAL MLX Direct image, motion, audio, and delivery from one stage.
ALi Imagine Create workspace showing a generated cybernetic portrait
CREATE Media-first controls with the result always visible.
ALi Imagine Library showing generated images and video outputs
GALLERY Every image, video, version, and lineage in one place.
01

Qwen Prompt Assist

Install the public Qwen 3.8 model and its private runtime in one guided action, then refine model-aware prompts locally.

02

LTX 2.5 video

Text, image, first + last frame, and performance-audio workflows on Apple Silicon with native MLX.

03

Concepts + LoRAs

Build reusable characters and styles, then attach compatible LoRAs to the Concept that owns them.

04

Drag in keyframes

Drop images from Finder straight into start and end frame slots, then direct the transition between them.

05

Native 2× upscale

Run the dedicated LTX 2.5 upscale path with visible queue progress and preserved source audio.

06

Immutable outputs

Keep settings, sources, render metadata, and every derived version attached to the finished asset.

FIELD TEST // 03:33

Built inside the signal.
Finished as a film.

A complete ALi Imagine production built from numbered first-and-last keyframes, reusable character Concepts, local LTX motion, immutable outputs, and a final editorial pass.

43 clips 44 keyframes LTX-2.5 motion PIX-7 direction
Watch on YouTube
01

THE INSTRUMENT

Media is the hero.
The system remembers the rest.

ALi Imagine surrounds the work with only what matters: sources, signal, engine state, outputs, and complete lineage.

02

ONE CREATIVE TRAIL

Reference to reusable identity
to finished asset.

No disconnected model buttons. Four clear surfaces, one project, and a recoverable creative trail.

01 / CONCEPTS

Teach the project what matters.

Collect references, character sheets, guidance, datasets, and certified adapters as reusable creative knowledge.

02 / CREATE

Route intent through the right engine.

Generate images and video locally or through xAI without changing the project’s core workflow.

03 / GALLERY

Review the asset, not the noise.

Compare, favorite, derive, reveal, export, and revisit every immutable version from a full-screen media surface.

04 / SYSTEM

Know what is actually ready.

Install and verify local engines, models, credentials, hardware tests, and capability certification explicitly.

03

CONCEPTS // REUSABLE IDENTITY

Characters survive
the changing engine.

References, character sheets, guidance, and certified adapters become project knowledge. The engine may change. The creative identity remains traceable.

The Pixel Records signal crew assembled above Neko City
PROJECT CANONThe Signal CrewShared world · stable identity
ALi ascending inside a luminous future signal chamber
CHARACTER / ALiIdentity across states
KITKAT controlling a dense audiovisual console
CHARACTER / KITKATControlled chaos
Astral KITKAT opening a portal into archived worlds
STATE / ASTRALIdentity can transform
PIX-7 activating the luminous ALi Imagine signal core
SYSTEM / PIX-7Signal verified
REFERENCE→CONCEPT→RECIPE→ASSET

Every frame keeps the path back to what made it.

Astral KITKAT opening the first portal frame
FIRST FRAME021
PIX-7 activating the destination signal core
LAST FRAME022

FIRST + LAST // LTX-2.5 MLX

Direct the beginning.
Lock the destination.

Build controlled transitions between numbered keyframes. LTX receives the exact opening and closing composition while the project preserves both sources, the generated clip, and its complete recipe.

ENGINE
LTX-2.5 MLX + METAL
CONTROL
FIRST + LAST FRAME
OUTPUT
IMMUTABLE VIDEO ASSET
04

PROVIDERS ARE PLUGINS

Local when possible.
Cloud when useful.

The project and its assets do not belong to an API. Engines execute recipes; they do not own the system.

LOCAL / IMAGE

Krea 2 MLX

Fast Apple Silicon image generation, image transformation, and Concepts guidance.

METAL · BF16 · OFFLINE
LOCAL / IMAGE

FLUX 3 Image Klein

Choose Distilled for speed or Base at 50 steps with CFG 3.5. Draft 512 through native 4K, generative 2× upscale, ten references and layout boxes.

MLX / METAL · 5.6B · 16 STEPS
LOCAL / PROMPT + VISION

Qwen 3.8 27B 4-bit

Local prompt refinement and source-frame analysis with a public, resumable model install that needs no Hugging Face token.

MLX SERVE · 4-BIT · OFFLINE
LOCAL / VIDEO

LTX-2.5 Native MLX

Text-to-video, image-to-video, first-and-last-frame control, native audio, and adjustable diffusion steps.

METAL · BF16 · ADJUSTABLE STEPS
LOCAL / VIDEO + AUDIO

Hailuo H3 MLX

Prepared FL2VA and Ref2VA integration. Local H3 execution is disabled in public builds pending authorization; private tests do not establish public availability.

PREPARED · AUTHORIZATION-GATED
LOCAL / VIDEO UPSCALE

LTX 2× Pixel Spatial

Creative 2× detail for generated and imported videos. Keeps aspect, timing, frame count, source audio, and immutable originals.

2 STEPS DEFAULT · ADJUSTABLE 2–8 · METAL
CLOUD / IMAGE + VIDEO

xAI Imagine

Remote image generation, editing, video generation, video editing, and extension through one adapter.

KEYCHAIN · ASYNC · LOCAL DOWNLOAD

ASSET-FIRST

The result is never an orphan.

Every output retains its source, signal, seed, engine, model, adapter, settings, checksum, timings, and parent version. Originals are never overwritten. Every operation derives.

REFERENCESCharacter references entering the concept chamber
→
CERTIFYALi identity certification frames
→
GENERATEALi ascended as a finished immutable asset

CODEX + DAVINCI RESOLVE / MACOS

Bring Codex into your edit.

Capture a frame, prepare an ALi video shot, review the result, and place the take back on your Resolve timeline. The ALi Resolve skill gives Codex the workflow. ALi Imagine MCP adds engine status, supported settings, source imports and persistent generation jobs through an authenticated local connection.

REGISTER ALi MCP · ALi Imagine 0.9.18+
codex mcp add ali-imagine -- python3 "$HOME/Library/Application Support/ALi-Imagine/mcp/server.py"

Launch ALi Imagine once to install the client, then run this command and reopen your Codex chat. Python 3 is required. The client reads a user-only local token; never paste API keys into MCP configuration. Check ali_status and engine availability before submitting. Source imports, first/last-frame and lip-sync workflows retain request and job identity; results require review before timeline placement.

  1. Unzip the skill. Keep the ali-resolve folder in Downloads.
  2. Ask Codex to install it. Use Codex on the same Mac as ALi Imagine and Resolve.
  3. Check the connection. Open both apps and your Resolve timeline before trying a shot.
PASTE INTO CODEX
Install the ALi Resolve skill from ~/Downloads/ali-resolve into ~/.agents/skills/ali-resolve. Read its README.md, back up any existing version, and check the required software. Do not generate media or change my timeline.
THEN CHECK YOUR CONNECTION
Use $ali-resolve to check my ALi and Resolve connections. Tell me the active project and timeline. Do not generate anything or change my timeline.

Requires the ALi Resolve plugin, Python 3, and Resolve external scripting access. Generation needs a configured, ready runtime. Public H3 execution remains authorization-gated; experimental settings are not a promise of model availability. This ZIP contains the Codex skill, not the apps, plugin, or models. Start with the connection check; older ALi versions may need an update.

No Sirius or ChatGPT manifest.json is needed for this workflow. Current helper: macOS, whole-number timeline frame rates. Download checksum.

ALi IMAGINE v0.9.43

Install the complete studio.
Add large models only when you need them.

Grok now offers Image 2.0 quality, Full/Lite video choices, fourteen Full video references, timed middle frames and up to three preset voices. Character Guidance can fill empty continuity fields from references while preserving your edits. Use original reference images directly as Qwen Looks. Choose and order up to ten references in the main Concepts image grid, with automatic saving and covers made from your selected images. Qwen can borrow subjects and composition as well as style; choose references to suit your scene.

Includes Qwen Turbo, Full and Unlocked, QWEN 2×, Refine, raw prompting, FLUX 3, Explore and the earlier video workflows. Existing projects, models, MCP, Resolve and paired-Mac workflows remain available. Qwen uses the noncommercial Qwen Research License. FLUX models require separate Hugging Face access and setup. H3 execution remains authorization-gated. Qwen 2× now preserves inherited Look continuity metadata. The library avoids duplicate style cards, and stored LoRAs remain available in Concepts. Explore orbit remains experimental: reliable full 360° coverage and frozen geometry are unverified. See the release notes for limits.

NOTARIZED RELEASE Developer ID signed and Apple notarized for direct macOS download. No Control-click exception is required.

01 Download DMG 02 Drag to Applications 03 Open ALi Imagine normally 04 Open System → Install compatible Qwen when wanted