> ## Documentation Index
> Fetch the complete documentation index at: https://support.myapps.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Providers

> Every AI model available in Pixio V2 Generate

# All Models

Every model you can use in Pixio V2 Generate is listed below. **Your plan** decides which are available and whether they use credits or are free. Expand a category to see models and descriptions—no horizontal scrolling.

<AccordionGroup>
  <Accordion title="Image generation" icon="image">
    * **Flux Dev** — Create images from text and attach your own LoRAs (characters, styles, products). Great for custom looks and consistent subjects.
    * **Flux Dev Inpainting** — Change only the parts you mask: fix faces, replace objects, or add details without touching the rest of the image.
    * **Flux Pro** — High-fidelity text-to-image with strong composition and prompt following. Use when you need polish and control.
    * **Flux Pro Fill** — Use a mask to fill or replace areas (e.g. new background, object, or outfit) while keeping the rest intact.
    * **Flux Pro Fill Finetuned** — Same as Flux Pro Fill but with your own fine-tuned model for a specific look or subject.
    * **Flux Pro Ultra** — Top-tier Flux quality: best for final assets when detail and coherence matter most.
    * **Flux Pro Ultra Finetuned** — Flux Pro Ultra driven by your custom fine-tune for branded or signature styles.
    * **Flux Krea** — Fast, versatile text-to-image. Good for exploration and quick iterations.
    * **Flux Krea Image to Image** — Take an image and steer it with a prompt—style transfer, variations, or guided edits.
    * **Flux SRPO** — Newer Flux text-to-image with improved prompt understanding and image quality.
    * **Flux SRPO Image to Image** — Newer Flux image-to-image for guided transformations from a single source image.
    * **Flux Schnell** — Fastest Flux option: low latency, good for real-time or high-volume drafts.
    * **Flux 2 Flash** — Quick Flux 2 generations with a focus on speed and clean outputs.
    * **Flux 2 Flash Editing** — Edit existing images quickly with Flux 2 Flash (style, content, or composition changes).
    * **Flux 2 Turbo** — Balanced Flux 2: fast and high quality for most text-to-image needs.
    * **Flux 2 Turbo Editing** — Edit images with Flux 2 Turbo—recompose, restyle, or change content from a prompt.
    * **Flux 2 Pro** — Higher-quality Flux 2 for when you need better detail and prompt adherence.
    * **Flux 2 Pro Edit** — Pro-level image editing with Flux 2: precise, prompt-driven changes.
    * **Flux 2 Max** — Highest-quality Flux 2; use for final deliverables and maximum fidelity.
    * **Flux 2 Max Edit** — Most capable Flux 2 editing: complex or subtle changes with strong consistency.
    * **Flux 2 Flex** — Flexible Flux 2 with good control over style and composition from the prompt.
    * **Flux 2 Flex Edit** — Flexible image editing with Flux 2 Flex for creative or iterative changes.
    * **Flux 2 LoRA** — Flux 2 with LoRA support so you can lock in a character, style, or product across generations.
    * **Flux 2 LoRA Edit** — Edit images with Flux 2 while applying your LoRAs for consistent look or subject.
    * **Flux 2 Klein** — Lighter Flux 2 variant (9B); good quality with lower cost and faster runs.
    * **Flux 2 Klein Editing** — Edit images with Flux 2 Klein for prompt-driven changes at lower cost.
    * **Kontext Pro** — FLUX Kontext for text-to-image: strong prompt following and coherent scenes.
    * **Kontext Pro Editing** — Edit a single image with FLUX Kontext Pro (change content, style, or composition).
    * **Kontext Pro Editing Multi** — Edit using multiple reference images with Kontext Pro for multi-image control.
    * **Kontext Max** — Highest-tier Kontext text-to-image for maximum quality and prompt control.
    * **Kontext Max Editing** — Edit images with Kontext Max for the most demanding or subtle edits.
    * **Kontext Max Editing Multi** — Multi-image editing with Kontext Max for complex, reference-driven changes.
    * **SDXL** — Stable Diffusion XL: solid all-round text-to-image, good resolution and LoRA support.
    * **SDXL Inpainting** — Fix or replace masked regions only; leaves the rest of the image unchanged.
    * **SDXL Image to Image** — Transform an image with a text prompt (style, content, or mood).
    * **SD 1.5** — Classic Stable Diffusion: fast, widely compatible, many community LoRAs.
    * **SD 3 Medium** — Better prompt following and quality than SD 1.5; good default for SD3.
    * **SD 3 Medium Image to Image** — Image-to-image with SD 3 Medium for guided transformations.
    * **SD 3.5 Medium** — Improved SD 3.5 balance of speed and quality.
    * **SD 3.5 Large** — Highest-quality SD 3.5 option when you need the best output.
    * **Reve** — Runway's artistic text-to-image; strong aesthetics and creative style.
    * **Reve Remix** — Remix one or more images with a new prompt while keeping the vibe.
    * **Reve Fast Remix** — Faster Remix for quick remixes and iterations.
    * **Reve Edit** — Edit an image with a prompt; Runway's quality and style.
    * **Reve Fast Edit** — Quicker Reve Edit for faster turnaround.
    * **Recraft V2** — Create both raster and vector images; good for design and scalable assets.
    * **Recraft V3** — Recraft's latest text-to-image with improved quality and control.
    * **Recraft V3 Vectorize** — Turn a raster image into clean, editable vector art.
    * **Recraft V4 (Vector)** — Generate vector graphics directly from text for logos and illustrations.
    * **Recraft V4 Pro (Vector)** — Pro-grade vector generation with finer control and quality.
    * **Qwen-Image** — Alibaba Qwen: strong prompt following and detailed, coherent images.
    * **Qwen-Image Edit** — Edit images with Qwen; prompt-driven changes with good consistency.
    * **Qwen-Image Edit Plus** — Multi-image edit with Qwen for reference-based changes.
    * **Qwen-Image Edit Plus Lora** — Qwen editing with LoRA support for custom styles or subjects.
    * **Qwen Image Max** — Highest-quality Qwen image model for best detail and prompt match.
    * **Qwen Image Max Edit** — Edit with Qwen Image Max for the most capable Qwen edits.
    * **Frames (Text to Image)** — Runway Frames: text-to-image tuned for motion-friendly, cinematic frames.
    * **Runway Gen-4 (Text → Image)** — Runway Gen-4 text-to-image; high quality and style control.
    * **Runway Gen-4 (References → Image)** — Gen-4 with multiple reference images for style or subject consistency.
    * **Kling V3 Text to Image** — Kling's latest text-to-image with strong realism and prompt following.
    * **Kling V3 Image to Image** — Transform an image with Kling V3 (style, content, or composition).
    * **Kling O3 Text to Image** — Kling O3 text-to-image; upgraded quality and coherence.
    * **PixCraft Image** — Midjourney-style image generation: polished, aesthetic outputs from text (and optional reference).
    * **Ideogram Generate (V3)** — Ideogram 3: text-to-image that handles text and typography in the image well.
    * **Ideogram Edit (V3)** — Edit with masks in Ideogram 3; change regions while keeping the rest.
    * **GPT Image 1** — OpenAI's image model: good prompt following and coherent, natural-looking images.
    * **GPT Image 1 (mini)** — Lighter, faster GPT image model for quick or lower-cost generations.
    * **GPT Image 1 Edit** — Edit images with GPT Image 1 (prompt-driven changes).
    * **GPT Image 1 (mini) Edit** — Lighter GPT Image edit for faster iterations.
    * **GPT Image 1.5** — Newer GPT image model with improved quality and control.
    * **GPT Image 1.5 Edit** — Edit images with GPT Image 1.5.
    * **Sana Base** — Nvidia Sana: solid text-to-image with good composition and detail.
    * **Sana v1.5** — Sana v1.5 for higher quality and better prompt adherence.
    * **Sana v1.5 fast** — Faster Sana v1.5 when speed matters.
    * **Sana Sprint** — Fast Sana option for quick drafts and exploration.
    * **Image 01** — MiniMax image model: good balance of quality and speed from text.
    * **Image 01 Subject Reference** — MiniMax with a subject reference image for consistent character or object.
    * **Mystic** — Freepik Mystic: ultra-realistic, photographic-style text-to-image.
    * **Pixio Image Edit** — Pixio's own image editor: blend or edit multiple images with prompts.
    * **Virtual Try On** — Upload a person and a garment; get a realistic try-on result.
    * **Fashn Tryon v1.6** — Fashion try-on: garment on model with control over pose and fit.
    * **Fashion Photoshoot** — Generate fashion shots from a garment image and a face (e.g. model + outfit).
    * **Imagen 4** — Google Imagen 4: high-quality text-to-image with strong prompt following.
    * **Imagen 4 Ultra** — Highest-quality Imagen 4 for maximum fidelity and detail.
    * **Imagen 4 Fast** — Faster Imagen 4 for quicker generations.
    * **Nano-Banana** — Lightweight Google model for fast, decent-quality text-to-image.
    * **Nano-Banana Pro** — Improved Nano-Banana with better quality and control.
    * **Nano-Banana Pro Edit** — Edit images with Nano-Banana Pro.
    * **Nano-Banana Edit** — Edit images with Nano-Banana.
    * **Lyria 2** — Google Lyria 2: text-to-image with strong aesthetic and coherence.
    * **Bria Base** — Bria's base text-to-image; good for general use and iteration.
    * **Bria Fast** — Bria's faster option for low-latency drafts.
    * **Bria HD** — Bria's high-resolution option when you need extra detail.
    * **Bria 3.2** — Bria 3.2: improved quality and prompt following.
    * **Seedream v3** — ByteDance Seedream v3: solid text-to-image with good style range.
    * **Seedream v4** — Seedream v4: better quality and prompt control.
    * **Seedream v4 Edit** — Edit images with Seedream v4.
    * **Seedream v4.5** — Latest Seedream with improved coherence and detail.
    * **Seedream v4.5 Edit** — Edit images with Seedream v4.5.
    * **Dreamina v3.1** — ByteDance Dreamina: creative, stylized text-to-image.
    * **WAN 2.5 Text to Image** — Alibaba WAN 2.5: text-to-image with good realism and control.
    * **WAN 2.6 Text to Image** — WAN 2.6 text-to-image; upgraded quality and prompt following.
    * **WAN v2.2 Text to Image** — WAN v2.2 text-to-image for latest WAN quality.
    * **WAN 2.6 Image to Image** — Transform images with WAN 2.6 (style or content changes).
    * **WAN Effects** — Apply cinematic or creative effects to an image (e.g. lighting, mood).
    * **Hunyuan Image V3** — Tencent Hunyuan: strong text-to-image with good composition and detail.
    * **Grok Imagine Text-to-Image** — xAI Grok: text-to-image with solid quality and prompt following.
    * **Grok Imagine Image Edit** — Edit images with Grok (prompt-driven changes).
    * **Upscale** — Increase resolution of an image (2×, 4×, etc.) with preserved detail.
    * **Photo Restoration** — Restore old or damaged photos: fix scratches, color, and resolution.
    * **Background Removal** — Remove or replace the background; keep subject clean for compositing.
    * **Advanced Face Swap** — Swap one or two faces in a target image with control over identity and blend.
  </Accordion>

  <Accordion title="Video generation" icon="video">
    * **Gen-4 (Image to Video)** — Runway Gen-4: turn an image into video with strong motion and consistency.
    * **Gen-4 Turbo (Image to Video)** — Faster Gen-4 image-to-video for quick iterations.
    * **Gen-4 Aleph (Video to Video)** — Runway Gen-4 video-to-video: transform or restyle existing video.
    * **Gen-4 Act-Two** — Character-driven Runway video: drive a character with a reference and motion.
    * **Gen-4 Upscale (4K)** — Runway 4K video upscale.
    * **Gen-3 Turbo (Image(s) to Video)** — Runway Gen-3 Turbo: one or more images to video.
    * **Gen-3 Turbo Extend** — Extend the length of a Runway video.
    * **Gen-3 Turbo Expand (Outpaint)** — Expand or outpaint a Runway video frame.
    * **Runway Gen-4 Turbo** — Runway Gen-4 Turbo (first-party).
    * **Runway Gen-3a Turbo** — Runway Gen-3a Turbo.
    * **Runway Gen-4 Aleph** — Runway Gen-4 Aleph (first-party).
    * **Runway Act Two (Character)** — Runway Act Two character video.
    * **Vidu Q1/Q2/Q3** — Vidu text-to-video, image-to-video, reference-to-video, extend (multiple variants).
    * **Pika v1.5/v2.1/v2.2/v2 Turbo** — Pika text-to-video, image-to-video, Pikascenes, Pikaffects.
    * **PixVerse Create / Extend / Upscale** — PixVerse text or image to video; first+last frame; extend; 4K upscale.
    * **Kling** — Text-to-video, image/frames/elements to video, effects, extend, motion control; V2.6, V3, O3 Standard/Pro variants.
    * **Kling o1** — Reference video/image to video, first/last frame, edit video.
    * **Kling Create Voice** — Create custom voice for Kling.
    * **Hailuo Video** — MiniMax Hailuo: text or image to video.
    * **PixCraft Video** — PixCraft image-to-video.
    * **Luma Generate / Reframe / Modify / Upscale / Add Audio** — Luma Dream Machine video generation and tools.
    * **LTX 2 / LTX 2 Fast / LTX 2 Pro** — LTX text, image, video, audio to video; extend; retake.
    * **Fabric 1.0 / 1.0 Fast** — Veed talking-head: image + audio to lip-synced video.
    * **Sora 2 / Pro / Remix** — OpenAI Sora 2 video generation and remix.
    * **Character 3** — Hedra: lip-synced character video from image + audio.
    * **Extract First/Last Frame, Merge Videos** — Pixio video utilities.
    * **Veo 3.1** — Google Veo: text, reference, image, first–last frame to video; Fast variants; extend.
    * **Grok Imagine** — Text-to-video, image-to-video, video edit.
    * **Seedance v1 Pro/Lite** — ByteDance: text, image, reference to video; Fast variants.
    * **OmniHuman v1.5** — ByteDance talking head from image + audio.
    * **WAN 2.5/2.6/v2.2** — Alibaba WAN text/image/reference to video; video-to-video; VACE edit; Animate Replace/Move.
    * **Hunyuan Video / Motion / Custom / Avatar** — Tencent Hunyuan text/image/video to video; motion; avatar talking head.
  </Accordion>

  <Accordion title="Audio & music" icon="music">
    * **Songcraft Generate** — Generate full tracks from a description (Suno-style).
    * **Stable Audio 2.5** — Text to audio, inpaint, or audio-to-audio.
    * **Tempolor** — Song (vocals), instrumental, stems splitter.
    * **Mureka** — Create (AI lyrics, advanced, instrumental), extend, regenerate segment.
    * **Music V2** — MiniMax music generation.
    * **Pixio Music** — Pixio music generation.
    * **Speech 02/2.5/2.6/2.8 Turbo & HD** — MiniMax TTS (multiple quality/speed options).
    * **Voice Clone** — MiniMax voice cloning.
    * **Text to Speech / Voice Clone (IVC) / Text to Dialogue** — ElevenLabs TTS and voice tools.
    * **Music (Compose) / Sound Effects** — ElevenLabs music and SFX.
  </Accordion>

  <Accordion title="Lipsync & sync" icon="microphone">
    * **Lipsync 1.9 / 2.0 / 2.0 Pro** — Sync lipsync (and beta variants).
    * **Lipsync 2 / 2 Pro** — Sync lipsync 2.
    * **React 1** — Sync React: emotion/reaction for video.
  </Accordion>

  <Accordion title="3D" icon="cube">
    * **Tripo** — Text/image/multiview to 3D; texture, refine, animation (pre-rig, rig, retarget); stylize, convert, import; mesh segmentation/completion; high-to-low poly.
    * **Meshy** — Text to 3D (preview, refine); image and multi-image to 3D.
    * **Hunyuan3D V2 / V2.1 / V2 Turbo, Mini, Multi-View** — Tencent Hunyuan 3D from image or multi-view.
    * **Hunyuan 3D V3 / V3.1** — Text, image, sketch to 3D; Rapid/Pro; optimize; segment.
  </Accordion>

  <Accordion title="LoRA & training" icon="wand-magic-sparkles">
    * **Flux Dev LoRA Training** — Train a LoRA on Flux Dev.
    * **Flux Dev Portrait LoRA Training** — Train a portrait LoRA on Flux Dev.
    * **Flux Pro LoRA Training** — Train a LoRA on Flux Pro.
    * **Flux Turbo LoRA Training** — Train a LoRA on Flux Turbo.
  </Accordion>

  <Accordion title="Argil" icon="user">
    * **Argil Avatars Train** — Train an avatar (face + voice).
    * **Argil Avatars Text-to-Video** — Generate avatar video from text.
    * **Argil Avatars Audio-to-Video** — Talking-head video from avatar + audio.
  </Accordion>

  <Accordion title="PixCraft edit" icon="pen">
    * **PixCraft Edit (Buttons)** — Use PixCraft UI actions (vary, upscale, etc.) on a previous PixCraft job.
  </Accordion>
</AccordionGroup>

***

Your **plan** (Free, Starter, Pro, Premium, Maker) determines which of these are available and whether any are free. The Generate UI may show more variants (e.g. different Kling or Pika versions) under the same brand.