tendre.AIDownload

Changelog

Every update to tendre.AI, the local-first AI image and video app, version by version.

v0.1.50

  • NEW: local video WITH sound (LTX 2.3). Generate clips 5 to 20 seconds long with sound, directly on your card, free and unlimited. Replaces the old silent video engine.
  • Cloud video: up to 20 seconds with sound, and 1080p for short clips.
  • NEW: TendreEngine, the unified engine in a single clean folder. Installation 5 to 10 times faster (dedicated download server, multi-connection downloads, speed displayed).
  • Video installation runs in the background: start creating while it downloads (discrete bar, cancelable, resumes automatically after interruption).
  • Create (licenses): attach an image with a paperclip or drag-and-drop to transform it into an image (img2img) or animate it as video.
  • If local video is not installed, the app offers it to you on startup (one click).
  • Redesigned wizard (feature lists, local or cloud video choice), clearer warnings (GPU memory, starting image too small), window maximized on startup.
  • Terms of use on first launch are translated into 9 languages.
  • Pro mode remains available even without a local model: generation then goes through the cloud (no more forced switch to Starter mode if you chose Pro).
  • Support rule clarified: local generation on NVIDIA RTX series 20 or newer (8 GB and above). Older cards (GTX 9xx/10xx) automatically use the cloud, where generation is much faster for them.

v0.1.49

  • NEW: Pro mode without GPU. If no compatible NVIDIA card is detected, Generate and Retoucher automatically use the cloud (image and brush retouch), with a clear banner. Element integration stays reserved for local GPU.
  • Chat: characters now have consistent outfits and appearances in intimate scenes, with proper coordination.
  • Chat: the character no longer invents your name. Automatic name extraction is stricter (a false name remembered could come back in conversation).

v0.1.48

  • Components: import your own models with one click. An "Import a model (.safetensors)" button copies the file (e.g. downloaded from Civitai) to the right place, no need to navigate folders anymore.
  • Chat: the tension gauge (flame) disappears from the interface. Your character warms up naturally, without a displayed counter.

v0.1.47

  • Chat: photos sent by your character (cloud) now cost 2 credits. The cloud image in the Generate tab remains free, and in Pro mode with GPU, chat photos stay generated locally, no credits.
  • Chat: coherent images in intimate scenes. No more clothing instructions that stuck to the prompt when tension rose: intimate scenes no longer receive contradictory clothing instructions.

v0.1.46

  • Cloud image is FREE for now (0 credit): take advantage to generate without GPU.
  • Retoucher (inpainting and element integration) is now accessible WITHOUT a license: retouch your images locally, freely.
  • Retoucher is translated into 9 languages of the application.

v0.1.45

  • NEW: Retoucher becomes a proper little editor. A toolbar above the image (Move, Brush, Mask, Eraser), undo/redo action by action (Ctrl+Z / Ctrl+Alt+Z), and a larger image on screen.
  • NEW: integrate an element (logo, badge, object as PNG) into an image. Place it directly on the image: drag to move, corner to resize, Ctrl + corner for perspective, circle above to rotate. The AI then blends it into the material (texture, folds, lighting) while keeping its exact shape and colors.
  • Mask tool cuts the element to make it pass behind an object or person (e.g. a shoulder in the foreground). Option: automatically confine the element to the person underneath, with mask preview.
  • Paint a zone and generate without a prompt: the zone is remade in harmony with what surrounds it. No prompt (positive or negative) is added secretly in Retoucher: what you type is exactly what gets sent.
  • The chosen style also applies to retouches: the zone is rendered as photo, drawing or painting according to the style.
  • The prompt assistant (AI button) now clearly shows why it cannot respond (engine not installed, busy...) instead of failing silently.
  • Character training becomes "LoRA Training", highlighted just below My Characters.
  • LoRA generation: the "delete" button was removed to avoid erasing a LoRA by accident.

v0.1.44

  • NEW: give your characters a VOICE. Import an audio sample in the Library (Voice tab), and your spoken videos adopt this tone, mouth synchronized. In cloud video, a voice selector; in chat, each character keeps their voice.
  • Cloud video much more responsive: the engine starts much faster (models built into the server).
  • Chat: the character no longer teleports to their favorite scene on their own. The scene location stays where your conversation is until you change it.
  • Chat: characters no longer impose a default outfit or expression (goodbye permanent swimsuit and smile): the scene decides.
  • LoRA Library: a file's type can be freely changed, and the LoRA add menu is sorted by type.

v0.1.43

  • Chat: character behaviors are contextual and appropriate to conversation tone. Expressions now match the scene properly, removing forced default smiles and adopting serious looks, pouts or closed eyes when the scene calls for it.
  • LoRA Library: a file's type can be freely changed (choosing "Scene" no longer locks the type permanently), errors are displayed, and known files are recognized regardless of name case.
  • LoRA generation: the "Add a LoRA" menu is sorted by type (character, scene, style, action), like the main selector.

v0.1.42

  • New LoRA Library (side bar, Library section): all your LoRA files with their type, trigger word and links; import, reorganize, delete.
  • LoRA generation: stack multiple LoRA (scene, style, action...) each with its own strength.
  • LoRA are sorted by type (character, scene, style, action) in all menus.
  • Characters: delete via the trash icon on each card (including LoRA characters).
  • Chat: if a required LoRA is missing on your PC, the photo automatically goes through the cloud.

v0.1.41

  • Mobile chat: videos finally save (default folder automatic, like photos).
  • Chat: characters maintain consistent, appropriate appearances based on conversation intimacy level.

v0.1.40

  • Chat: character warmth lasts 30 minutes before starting to cool down (then one level per quarter hour).
  • Chat: character behavior stays appropriate to conversation tone and context.

v0.1.39

  • Chat: notification on your device when a character replies while the app is not on screen (adjustable in Settings).
  • Chat: the reply arrives and the notification sends even if you quit the app while the character is typing.
  • Chat: character warmth naturally cools down when conversation pauses (returns to calm after an hour).
  • Chat: the unlock prompt displays as a normal message in the conversation.
  • Mobile: updates are proposed automatically on app startup.
  • Generation: cloud photos and chat replies much faster (renewed engines).

v0.1.38

  • Chat: you can scroll back and read the conversation while the character is typing (scrolling no longer forces you to the bottom).
  • New: a "Check for updates" button in Settings, to install the latest version whenever you want.
  • Activation screen redesigned: the license offer and benefits are clearer.
  • License activation reliability improved.

v0.1.37

  • Chat: your very first message no longer fails on startup. While the engine wakes up, the app waits and reconnects automatically, never showing an error.
  • Chat: the "typing" indicator is now animated while waiting for a response.
  • Video: the engine selector clearly displays "Local" and "Cloud".
  • New application icon.
  • Fidelity improvements on intimate scenes at the most intense level.

v0.1.36

  • Chat: at low tension, your characters stay clothed.
  • Chat: at the most intense level, intimate scenes are rendered more faithfully and coherently with your request.
  • Chat: the character truly follows the action you requested in the photo, even when teasing in the text.
  • Translations completed in nine languages.

v0.1.35

  • Chat: two photo and video buttons to the left of the text input to automatically receive an image (or clip) with each response, whenever you want.
  • Chat: a notification sound when your character responds (with a button to mute it).
  • Chat: videos arrive faster (the video engine prepares itself as soon as the conversation heats up).
  • Candy: her photos now resemble her in cloud mode too, and her appearance has been refined.
  • Chat: smoother flow when you chain photos and videos, and successive photos truly vary when the scene changes (no more nearly identical images).
  • Chat: "show me", "I'd like to see you" and their variants trigger a photo send in all languages.
  • Chat: several display fixes (a video that could disappear while loading, inconsistent scene) and consistency between text and image.
  • Your creations are organized in Documents\Tendre.AI by default on new installations.

v0.1.34

  • New premium character: Candy, 26, nuclear and solar safety engineer, solar and playful. First companion with her own identity model (LoRA) automatically downloaded when unlocked: her photos really look like her.
  • Chat: each character has their SEDUCTION DIFFICULTY (displayed in flames on their card): some follow right away, others must be earned message after message, whether in real-time or when resuming a conversation.
  • Chat: more HUMAN characters: each has their own pace, keeps you waiting with charm if you move too fast, and reacts with wit if treated like an object, never breaking the mood.
  • Chat: character cards in portrait format with age, gender, profession, and difficulty; tension gauge live in the conversation header.
  • Chat: the cost of a clip is displayed on the "Turn into film" button; your first name is pronounced only in the first video; at high intensity levels the character truly executes the action from the image, with confidence.
  • Chat: reinforced visual progression (no surprise intimacy changes at low tension) and better consistency between what the character says and what their photo shows ("show me..." is respected).
  • Your creations (images, videos, trainings) are now organized in Documents\Tendre.AI by default (new installations): no more unfindable hidden folders.
  • Cloud chat: new, more reliable engine (no more empty responses, faster startup).

v0.1.33

  • Chat: seduction must be EARNED. Tension rises in stages (charm, flirt, sensual, intimate, intense) at your message pace; the character resists with their personality if you move too fast, settles down if you calm things, and images are LOCKED to the level reached (no surprise intimacy at mild conversation levels).
  • Chat: videos have real continuous action and a spoken line suited to the moment (your first name at tender levels, scene intensity at high levels).
  • Sasha: anatomy 100% consistent with her trans identity, in her words and images.
  • Chat: change your first name by simply asking the character ("call me..."), in all languages.
  • Chat: no more responses mixed with English and messages that erased themselves for no reason (refined locks).
  • Interface: in Starter mode, settings and help now join the bottom of the sidebar, as in Pro mode.
  • Cloud: the chat engine now starts itself on demand and shuts down after 30 minutes of inactivity (first response of a session in 1 to 3 minutes, instant after).

v0.1.32

  • Chat: the character types at human speed (natural typing with variations) instead of displaying their response all at once; their photo prepares while they type and arrives just after, like a real conversation.
  • Chat: no more responses written "in your place" (the character no longer responds by playing your role) and overly long responses.
  • Chat: text smileys become emojis (<3, :), ;p...) in both directions, and characters can slip them into their messages, like in real texts.
  • Characters: premium character cards now follow application updates. Lyra now fully lives in her high fantasy world (no more anachronisms), wavy platinum blonde hair, slender figure.

v0.1.31

  • Chat in Starter mode: conversations now run IN THE CLOUD, with no downloads or graphics card needed. Same characters, same natural feel as local: it works instantly, even on a small phone.
  • Chat in demo (without license): chat freely with Lea and Lucas, 20 messages a day. Asking for a photo, video, or another character displays a license activation invitation directly in the conversation (one-click purchase).
  • The Chat tab is always visible. In Pro mode without a chat engine, a button installs it in one click from the tab (~8 GB, once only).
  • Character selection: available characters display first, locked ones show a clear lock icon and premium ones show their price.
  • Free trial reliability and security strengthened server-side.

v0.1.30

  • Chat: NATURAL PROGRESSION of seduction. Conversation tension is tracked continuously: it rises at your pace (charm, lingerie, intimate, intense), falls if you calm down, and photos and the character's tone follow this level. No more characters too direct from the first message: the first photo is clothed, intimacy builds.
  • Chat in DEMO (without license): chat freely with Lea and Lucas (unlimited text, local engine). Photos, videos, and other characters lead to license activation.
  • Chat: shorter and faster responses (reinforced instruction + adjusted cap), end of parasitic stage directions like "(Photo of me...)" in bubbles, and the "Photo with each response" box reappears on its own when the local engine finishes starting.
  • Chat: "Clear conversation" also erases the summary memory in progress (no memory can resurface afterward), and the Chat tab displays at launch (it sometimes waited for a tab change).
  • Cloud: evening capacity increased (2 hot workers, up to 4 at peak) for instant renders even during high traffic.

v0.1.29

  • Chat: two new PREMIUM characters unlockable with credits, Sasha (100 credits) and Lyra (200 credits). An unlocked character stays unlocked forever (even after reinstall).
  • Chat: ILLUSTRATED mode (local engine required): check "Photo with each response" and the character accompanies each message with a photo of their scene, generated free on your graphics card.
  • Chat: photos flow with true continuity (same location, same lighting, scene evolves through the conversation), requested framing is respected, and doubled faces are corrected.
  • Chat: change your character's attitude by asking them ("be more docile", "be dominant", "be shy"...): it persists until you say otherwise. "Clear conversation" restores their original character.
  • Chat: the character knows local time and date (coherent greetings and activities), no longer invents shared memories, describes their photos faithfully, and no longer over-reacts to casual questions.
  • Chat: click a photo to open it fullscreen (scroll wheel zoom), side portrait reduced, conversation and image thread enlarged. Megan is now a nurse, swimmer, and more playful.
  • Without license: local VIDEO generation is now free and unlimited (like images): only the cloud engine requires a license. Your GPU, your creations.
  • Pro mode: if your NVIDIA card is compatible but the local engine isn't installed, a banner offers one-click installation.

v0.1.28

  • Security: strengthened content protection filter. It now applies uniformly to ALL generations (images, videos, LoRA, retouching, chat), locally and in the cloud, with a clear message when a prompt is blocked.
  • Cloud reliability: automatic failover to a second datacenter if the main one is saturated (renders continue instead of failing during peak hours).

v0.1.27

  • Companion chat: your characters can now send you VIDEOS of themselves (about 5 seconds, with sound) when you ask ("film yourself..."), in addition to photos.
  • Chat: "Turn into film" button on each received photo, to animate that photo into a short sound clip.
  • Chat: the character gets to know you. They ask for your first name through the conversation, remember it (for all characters), and address you personally.
  • Chat: in Pro mode with local engine, character photos are generated on your NVIDIA card with face locking (superior fidelity), free; the cloud is used otherwise.
  • Characters: Megan's figure refined (athletic, swimmer).

v0.1.26

  • Chat companion: your characters can now send you photos of themselves directly in the conversation ("send me a photo", "I want to see you", "show me..."), generated in the cloud while they write their response. The requested framing (full body, selfie, etc.) is respected.
  • Chat companion: much more natural conversations. Short responses calibrated to your messages, no more breaking character, the character keeps their identity, gender and your language even in long conversations.
  • Chat: the chat cast is now made up of the app's official characters (with their story), separate from the characters you create for image generation.
  • Chat: you can stop the response in progress by sending your next message, and freely scroll back through the conversation while the character is writing.
  • Create: each image or video in the stream can be deleted (cross in the corner), from disk and gallery.
  • Credits: displayed amounts switch to the new scale (10 credits = 1 video of 5 s, 2 credits = 1 photo); existing balances were automatically converted, value doesn't change.
  • Cloud reliability: a render lost in the queue is automatically relaunched, no action needed from you.

v0.1.25

  • Starter mode simplified: on first launch, choosing Starter goes straight into cloud mode, no engine installation or model downloads. Perfect to get started in seconds.
  • Clearer choice screen: Starter mode (100% cloud, no installation) and Pro mode (local generation, NVIDIA card with over 8 GB required) are now explicitly described.
  • Automatic switch to cloud if no image model is installed: if the local engine is present but has no checkpoint (nothing to generate locally), the app automatically switches to cloud mode instead of failing. As soon as a model is added, it goes back to local.

v0.1.24

  • Application digitally signed (verified publisher: PifletteProd). Windows "unknown publisher" warning is gone on install: Windows now recognizes Tendre.AI as trusted software.

v0.1.23

  • Starter mode: you choose Image or Video with two icons to the left of the prompt (no more automatic detection, you decide).
  • Starter mode: videos are much better quality. An image is first generated from your text, then animated, which matches what you ask for much more closely.
  • Machines without compatible NVIDIA card: streamlined installation, you go straight into cloud mode without downloading the engine (7 GB saved).
  • Scroll bar adapted to dark theme.

v0.1.22

  • Starter mode: videos are now generated in 720p vertical with sound (ideal format for mobile and social networks), and faster.
  • Starter mode: your creation stream is preserved when you switch tabs and come back.

v0.1.21

  • Fixed download errors (error 520) on large renders, especially HD video: images and videos are now retrieved as binary (lighter and more reliable) instead of text format that would max out on large files.

v0.1.20

  • Activation screen: the "Import my license" button is now a proper visible button (blue outline).

v0.1.19

  • Starter mode: your prompt is automatically translated to English before generation. You can write in your language, models (trained in English) then give much better results.
  • "Activate my license" button more visible in the free trial end message.

v0.1.18

  • Free trial: without a license, 3 images and 1 video offered in the cloud to discover the app (ideal for machines without compatible NVIDIA card). Then a license unlocks unlimited generation locally or with cloud credits.
  • Starter mode display fixes (progress bar, assistant layout).

v0.1.17

  • New Starter mode: a single field to describe what you want, the app generates the image (or video) and guesses the rest. Choose on first launch, changeable anytime in settings.
  • Image generation in the cloud: machines without compatible NVIDIA card can now generate via the cloud.
  • Duo of characters: two coherent characters in the same image.
  • New Soundify tab: automatically adds a soundtrack to a silent video.
  • Reorganized gallery: folders shown in grid, with subfolders for videos and editing.
  • Clearer installation assistant: models are shown as thumbnails with an example image.

v0.1.16

  • Compatibility with OLDER graphics cards (GTX 900 / GTX 1000, TITAN X, Quadro M/P, MX): the installation assistant detects these cards and automatically installs the engine version that supports them. Before, generation would fail on these machines ("no kernel image").

v0.1.15

  • IMPORTANT fix: when generation failed on the engine side (missing model, memory...), the app showed NOTHING (no image or error). The exact reason for failure is now displayed clearly.
  • Translations completed in 9 languages: style selectors (image and video), groups and chat model in the Models tab, base status in the sidebar.

v0.1.14

  • The app now requests administrator rights on launch (Windows prompt): ComfyUI installation works in all folders, including Program Files.
  • Setup wizard: if the chosen folder is protected or inaccessible, a clear message explains it and suggests a better location (instead of a technical error).
  • Chat: the welcome message from provided characters displays in your app's language (and changes with it).
  • Chat: the personality of characters provided with the app is locked (yours stay editable).
  • Activation screen: direct button to buy a license on tendre.ai.
  • Gallery: Resume and Delete buttons redesigned (clearer, accidental deletion protected by their discrete appearance).

v0.1.13

  • IMPORTANT fix: on first launch (or after updating from an old version), the database could fail to open ("duplicate column") and block the app. Migration is now protected.
  • Fix: if the saved ComfyUI folder no longer exists (different machine, disk unplugged, cleanup), the app reopens the setup wizard instead of failing with "access denied".
  • New: "Pool house" scene FREE, installed automatically (downloaded once in background). Your character in a real place, right from setup.
  • New: BATCH generation. Choose 1/2/4/8 images per click, generated in sequence with variations, saved as they render.
  • New: GENERATION queue. While one image renders, write your next prompt and add it to the queue: everything chains automatically.
  • New: RESUME button in gallery (images and videos): reload in one click the prompt, seed, character, scene, format and settings from any creation to replay or vary it.
  • Anonymous counter of active users (random identifier, no personal data).

v0.1.12

  • New: IMAGE and VIDEO STYLES. A selector of moods (cinematic, portrait, etc.) that enriches your prompt in one click, on both Generate and Video sides.
  • New: TRANSITION (morphing). Give a start image and an end image, the app creates the video that morphs from one to the other. New dedicated tab.
  • New: VIDEO CHAINING and SEQUENCES. Chain your shots (the last frame of one clip becomes the start of the next) and organize them automatically in a named folder (01_name, 02_name...). You can also import a video to continue it.
  • Gallery reorganized: nested folders (parents and children) with breadcrumb, instead of a flat list.
  • Video: 8 second duration available for 480p with sound.
  • Video: the app remembers your engine (cloud or local) and fixes the "not ready" banner that stayed wrongly displayed in cloud mode.
  • Chat: characters warmer, more open to romance.
  • Settings: license import button (file .tendrelic).
  • Generation: removed "fully clothed" from prompt, which blocked mechanical limbs and prosthetics in your creations.
  • Misc interface fixes (checkboxes, alignments, browse button).

v0.1.11

  • New: SCENE creation (places). Describe a scene (indoor/outdoor, time, mood) or import photos, and the app trains a LoRA that keeps that place coherent across all your generations. Thumbnails in the scene list.
  • New: PUT your CHARACTER IN your SCENE. Scene selector at generation (InstantID character or LoRA character), with a strength slider, to blend identity and place.
  • Interface: forms in two columns (Generate, Video, LoRA) to better use screen space, settings accessible via a gear icon at the bottom of the sidebar.
  • Removed custom video LoRA field and audio mode description, mouse shortcut legend under the retouching zone.

v0.1.10

  • Cloud video credit pricing adjusted: 720p now costs double 480p beyond 5 seconds (10 s and 15 s), reflecting its true compute cost. The 5 second clip stays at 1 credit regardless of size.

v0.1.9

  • Cloud video: 720p now renders in true high definition even on long clips (10 s and 15 s), instead of downscaling to 480p.
  • Cloud video: removed custom LoRA field (security: no longer reference free files on the remote volume).

v0.1.8

  • Chat companion: chat with your characters via a 100 percent local and unrestricted text AI.
  • 5 base characters shipped with the app (3 free, 2 to unlock), face and personality included.
  • Inpainting: touch up a specific zone of an image from a simple prompt.
  • Image preview: zoom with scroll wheel and pan with middle click.
  • Integrated prompt optimization assistant during generation.
  • Video gallery: prompt copy button.
  • Reorganized menu (Characters first, collapsible sections).
  • Interface fully translated in 9 languages.

v0.1.7

  • Previous reference version (auto-updater, Ed25519 license, LTX cloud video, LoRA training).