Big update focused on video creation, workflows, reference tools, and stability across iPhone and iPad. New Features • Create Videos: Create videos directly in Sogni • Clip Mixer: Full-featured video editor with timeline editing, clip trimming, reordering, export, waveform audio visualization, still-image clips, aspect ratio options, and multi-clip import • PaintOver Video: Bring your drawings to life in 4K video across supported video workflows, and save drawings to the gallery for reuse • Sound-to-Video (S2V): Generate videos driven by audio input (import from Files or Photos, or record directly) • Motion Transfer: Transfer motion from reference videos (WAN Lightning model) • First/Last Frame Controls: Define start and end frames for video generation, with video import to choose specific frames • Background Render Queue: Full background queue support with concurrent requests and result handling, plus a queue button and live status on the main view • Reference Tools Upgrades: Import gallery items as guide/reference/end-frame/motion references, plus Zoom / Pan / Roll controls for precise positioning • New Models: Added support for LTX2 video models and the new Z-Image base model • New Workflows View: Purpose-oriented quick access to tools, other Sogni apps, and helpful guidance Fixes & Improvements • Multiple bug fixes, stability improvements, and performance optimizations across queueing, Clip Mixer, gallery previews, PaintOver/reference tools, layouts, and overall iPhone/iPad experience

• New: Change Perspective. Re-render your image from a new camera angle, while keeping the subject and overall style consistent. • Fixes a bug that could affect the progress view layout. • Minor layout adjustments.

• New image models: – Qwen Image 2512 – Qwen Image 2512 Lightning • Fixes a bug that could cause recovered jobs to not load. • Bug fixes and optimization enhancements.

• New next-gen image models: – Z-Image Turbo – FLUX.2 [dev] – Qwen Image Edit 2511 – Qwen Image Edit 2511 Lightning • New Enhancer: Generative Filters, featuring one-click realism boosts, restoration, focus adjustments, color tuning, and more. • New Z-Image upscaler delivering consistent, high-quality images up to 2048 px. • Z-Image Turbo is now the default fast Supernet model. • Support for up to three context images when using FLUX.2 or Qwen Image Edit models. • Renamed the Model Explorer group “Flux” to “Next-Gen Diffusion”. • Added a new Model Explorer group: “Image Editing & Mixing”. • Added sample images, model descriptions, and in-app help content. • Fixed an issue where the prompt field appeared as a single line on launch. • Additional bug-fixes and optimization improvements. • Revised UI colors. • New app icon.

• Chroma models are now organized into two groups in the Model Explorer. • Refined Premium Spark purchase view. • More updates and fixes for Tahoe/iOS 26. • Improved app launch performance and reliability.

• UI refinements. • Optimized Settings view performance. • Turnstile fixes for macOS/iOS 26. • Enhanced Rewards view. If you missed the previous update: • UI layout adjustments and refinements for iOS/iPadOS 26. • Updated UI background colors for improved visual consistency. • Strengthened model management logic for greater stability. • Displays recent style searches. • Model Explorer highlights the parent of the active model for easier navigation. • Other various fixes and adjustments.

• UI layout adjustments and refinements for macOS Tahoe 26 and iOS 26. • Updated UI background colors for improved visual consistency. • Strengthened model management logic for greater stability. • Displays recent style searches. • Model Explorer highlights the parent of the active model for easier navigation. • Other various fixes and adjustments.

• Improved Premium Spark purchase experience • Added quick search for styles • Minor fixes and optimizations

• New setting to optionally embed generation settings metadata in exported images. • Supports embedded image metadata from fast and relaxed network. • New Spark Points balance breakdown view. • Unverified email alert badge in settings view.

• Added new Sampler and Scheduler settings. • Support for DPM++ SDE sampler and schedulers (Karras, KL Optimal). • Set DPM++ 2M as the default sampler for Fast Network. • Renamed Scheduler to Sampler and Time Step Spacing to Scheduler for consistency with industry-standard terminology. • Set DPM++ SDE as the default sampler for Instant-ID ControlNet. • Images now auto-add to Gallery when Kontext auto-refresh is ON. • Style prompt clears automatically after setting a Kontext image. • Fixed progress bar step/step count bug. • Fixed: LEOSAM’s FilmGirl Ultra should not use LCM defaults. • Optimization enhancements.

• Fixed bug with recommended range warnings. • When restoring an image from Gallery or ME, the image’s model is also restored if it uses Supernet and the model is available. • Live camera snapshots now use the highest-resolution photo if not preprocessed for face/pose capture. • Disabled negative prompts for Krea. • Added support for Previews with Flux models. • Optimization enhancements.

• Flux Kontext – edit and evolve images with powerful visual prompts.  – Maintain character consistency across different scenes, angles, and outfits.  – Mix two reference images to blend ideas (e.g., place a subject from one image with an object from another).  – Perform precise local edits with simple instruction prompts.  – Progressive edits with auto-refresh for step-by-step refinement.  – Use any image, video, or live camera capture as a Kontext reference. • New Scheduler and Time-Step Spacing options. • Optimized default settings for each model. • Updated help content for easier guidance. • New Flux models:  – FLUX.1 Kontext [dev] (Premium)  – FLUX.1 Krea [dev] (Premium)  – Chroma v.46 [Flash]  – Chroma v.48 [Detail Calibrated]

• Security enhancements • New Premium Spark boosted status • Sample images added for Flux and other new models in Model Explorer • UI refinements • New Stable Diffusion models available: Analog Madness SDXL v2 Animagine XL 4.0 CyberRealistic v9 CyberRealistic XL v6 Hyphoria Real [Illustrious] v0.5 Pony Realism v2.3 Ultra

• Optimization improvements. • Removed deprecated testnet code. • Minor bug fixes.

• Account related bug fixes • Ready for Supernet mainnet • Enhanced Spark Points experience • Performance optimizations

• Account related bug fixes • Ready for Supernet mainnet • Enhanced Spark Points experience • Performance optimizations

• Ready for Supernet mainnet • Enhanced Spark Points experience • Minor bug fixes • Performance optimizations

• Supports Spark in-app purchase. • Updated app and asset icons. • Fixed an issue where the on-device processing selection button could become unresponsive. • Help content updated. • UI refinements and performance optimizations.

• Enhanced Spark Points rewards system. • New email settings, including the option to change your email address. • Improved error display in the login view. • Updated help content. • UI refinements. • Performance optimizations.

• Performance optimizations. • Bug fix: Corrected the step/guidance range warnings for InstantID. • Various layout tweaks, fixes, and improvements.

• New! Depth Map ControlNet: Image preprocessing and support for Depth, Normal Bae, and Segmentation models. • New! Live camera support for Depth Map preprocessing. • New! Live camera support for Sketch, Guide Image, and PaintOver tools. • Display overlay of Guide Image and ControlNet during generation progress. • Steps and Guidance sliders now indicate when values are outside the recommended range for the selected model type and scheduler. • Gallery: Added ability to select all items within a filtered group. • Gallery: Favorites filter now cycles through three states — favorites only, not favorites, and no filter. • Layout refinements for iPad.

• New: Pose and Facial Expression capture with OpenPose ControlNet. • New: Face Transfer using Instant-ID ControlNet. • New: PaintOver — guide your creations using traditional painting tools. • Use device camera for ControlNet. • Real-time OpenPose preprocessor rendering with live camera feed. • Camera Timer. • ControlNet Strength control. • ControlNet Emphasis control. • ControlNet Scheduling with Start and End controls. • Updated help content and tooltips for ControlNet and Guide Image tools. • Adds recommended sizes for Standard and LCM models; lists larger presets as experimental. • Layout adjustments. • Bug fixes.

• Auto-resume active and unclaimed jobs after connection interruptions or app relaunch. • Significant optimization improvements in the on-device Stable Diffusion pipeline. • Minor layout adjustments.

• Important: Fixes a data race bug in the Safety Filter that could cause it to either miss sensitive content or crash the app. • Safety Filter: Optimized NSFW content detection. • Restore Image Settings: Disables the 'Restore Steps' button if the image step count exceeds what the active model or scheduler supports. • Exposes new Spark Points color code. • Supernet: Improved transaction processing.

• Displays new Supernet status messages. • Supernet API and Socket enhancements. • Layout adjustments and optimization enhancements.