More models, each with the settings it was made for — and edit photos by describing the change. New models on ComfyUI • Edit with instruction: pick a FLUX.1 Kontext model, choose a photo and type what to change ("make the sky purple, keep everything else"). No mask needed. • FLUX.2 (dev, klein 4B / 9B and klein Base) and Chroma1-HD now create, remix and edit. • Split-file models: the picker lists diffusion models next to your checkpoints, grouped by family, and sets up FLUX.1 (dev, Krea, schnell), Z-Image Turbo and Base, SD 3.5 and Qwen-Image for you. Text encoders and VAEs are found on your server automatically. • Wan 2.2 5B video: text to video and image to video on the Video screen, with the right sizes and defaults. • Each model shows whether it's ready, or exactly which file it still needs — and whether your server's GPU can run it. Per-model settings • Give any model its own steps, prompt strength, sampler, size, Avoid text, LoRAs, prompt tags and more. • They sync to your other devices through iCloud (turn off under Cloud Sync), and you can export and import them. • Better starting settings for FLUX, Z-Image, SD 3.5, SDXL Lightning / Turbo / Hyper and SD 1.5. Pony and Illustrious now use CLIP skip 2, as they were trained. A prompt assistant that knows your model • Enhance and Describe an image write tags for Illustrious, Pony and SD 1.5, plain sentences for FLUX, SD 3.5, Qwen-Image and Z-Image, and short instructions when you edit with Kontext. • Tips under the prompt and one-tap fixes in Expert when a setting doesn't suit the model. Fixes • A missing model file, text encoder or node gets one clear message before anything is sent. • LoRAs now apply to Remix and Edit on ComfyUI. • The Sampler and Scheduler lists match what your ComfyUI server offers. • The Video screen no longer asks for VideoHelperSuite when your server doesn't need it, and its Wan 2.2 pickers only offer text-to-video models. • Many smaller fixes.

Widgets, iCloud sync, FLUX and more. • Widgets: see your latest image and generation status on the Home and Lock Screen, follow progress in a Live Activity, and add Quick Generate, Gallery and server controls to Control Center. • iCloud sync (opt-in): keep your images, videos, saved workflows, settings, servers, folders, favorites and prompt library in step across your iPhone and iPad, in your own iCloud. Choose to sync all images or just favorites, and whether password-protected folders stay on this device or sync locked behind the same password. Server tokens and passwords never leave your device. • Describe an image: pick a photo and a vision model writes a prompt for you. • Make variations: turn any result into a batch of seed variations in one tap. • Find your ComfyUI or SwarmUI server by scanning your Wi-Fi. • Proper FLUX support on ComfyUI. • Long jobs that finish while the app is in the background are saved. • iPad: sidebar navigation and More options in an inspector. Fixes • Sharing an image into the app from Photos now works. • Better Remix and Edit results on ComfyUI. • Batches never run a prompt twice. • SwarmUI Cancel is faster and each image keeps the seed that made it. • Many smaller fixes and cleanups.

Fixes a crash that could happen after opening Styles & Recent on the Generate screen and then saving a change (for example adding a server).

A redesigned, simpler Mobile Comfy Creator. • New setup: choose where your AI runs and connect in one screen. Type an address like 192.168.1.5:8188 and the app detects ComfyUI or SwarmUI, tests it, and shows your GPU and model count. • Redesigned Generate screen: pick a Mode (Create, Remix, Edit, Video), a Shape and a Quality (Fast, Balanced, Best, tuned for your model). Everything else lives under More options. • A pinned Generate bar shows whether you're ready, plus live progress and Cancel for both ComfyUI and SwarmUI. Progress follows you to other tabs. • Results appear right on the Generate screen with Share, Save to Photos, Remix and New seed. • Get a notification when a generation finishes in the background. • Save as PNG or JPEG. Save your favorite prompts to My Snippets and reuse recent ones. • Gallery: long-press any image to share, favorite, move or delete it. Fixes • Cancelling a batch or a SwarmUI generation now stops the work on your server. • Switching between SwarmUI and ComfyUI keeps a model that server actually has. • Better defaults for FLUX and Lightning models. • Quick Generate from Shortcuts and Control Center now really generates. • Clear error messages when a server can't be reached or a prompt enhancement fails. • Many stability and reliability improvements across workflows, batches, video and the gallery.

Gallahadd Software LLC cutover: updated Privacy Policy, Terms of Use, and Support links to gallahadd.com. Bug fixes for cold launch stability and ComfyUI seed handling. Improved Settings About links and Report Issue fallback.

1.4 — iOS 26 Connectivity + Polish • Fixed Tailscale and VPN connectivity: servers reachable in a browser but not the app now connect correctly. Root cause was a combination of ATS policy, oversized health-check payloads, and VPN certificate handling — all addressed. • Faster, more reliable server health checks over high-latency connections. • iOS 26 design refresh: Liquid Glass on overlay controls and context menus; modernized navigation, titles, and styling throughout. • Auto-reconnect to your last server on app launch. • Clearer, more actionable connection error messages. Thanks to everyone who wrote in — if 1.3 didn't connect over Tailscale or over your VPN, please try 1.4 and let me know how it goes.

bug fixes and general improvements to flow.