Skip to content
Layer
PricingEnterpriseLog inSign up

Model catalogue

Every leading AI model, in one place

Image, video, 3D and audio models from 54 providers, side by side. See what each one makes and what it supports, then run it in your browser on one balance of Creative Units.

Start creatingBrowse the catalogue
Made with Z-Image TurboZ-Image TurboMade with Meshy V6Meshy V6Made with GPT Image 2GPT Image 2Made with Gemini 3.1 Flash ImageGemini 3.1 Flash ImageMade with MiniMax H3 ReferenceMiniMax H3 ReferenceMade with Hunyuan 3D v3.1 ProHunyuan 3D v3.1 Pro
Made on Layer with the models named on each picture.
129
Image models
178
Video models
47
3D models
47
Audio models
54
Model providers

Top rated

Where to start

The strongest models in the catalogue, by rating. Usage rankings return as the week fills in.

  1. 01Mureka 9.5 InstrumentalMurekaAudio
  2. 02Mureka 9.5 SongMurekaAudio
  3. 03Stable Audio 3 Small MusicStability AIAudio
  4. 04Stable Audio 3 MediumStability AIAudio
  5. 05Lyria 3.5GoogleAudio
  6. 06MiniMax Music 3MiniMaxAudio
  7. 07SSonilo Video to Music 1.1SoniloAudio
  8. 08SSonilo Music 1.1SoniloAudio

Just added

New on Layer

The latest models to join the catalogue, ready to run the day they land.

The catalogue

Browse every model

Filter by what a model makes and what it supports, or search by name, nickname or provider.

MeshyMeshy V6Meshy V6. High-fidelity 3D asset creation focusing on PBR, quad mesh, and face rigging.2QwenZ-Image TurboUltra-fast 6B parameter image model from Tongyi-MAI, optimized for near real-time generation.2936ElevenLabsElevenLabs TTS V4aka Eleven v4ElevenLabs' expressive v4 speech model with audio tags, stability, and similarity control.1335OpenAIGPT Image 2.5 SunburstOpenAI's premium GPT Image 2.5 variant: extra precision across edits and 1024px to 4K output, trading longer generation times for tighter control.1222GoogleGemini Omni FlashGoogle's fast multimodal video model — 720p clips with synchronized native audio from text or a still image.1368GoogleGemini Omni Flash ReferenceReference-guided video generation with up to 5 reference images for consistent characters and style.1368OpenAIGPT Image 2.5 FlareOpenAI's default GPT Image 2.5 variant: fast, high-quality generation with natural lighting, richer textures, and precise edits up to 4K.1207AlibabaWan 3.0Alibaba's Wan 3.0 video model with up to 30s clips, 480p/720p/1080p output, and native audio.1362OpenAIGPT Image 2OpenAI image model with strong text rendering, UI generation, and photorealism. Native output up to 4K with three quality tiers.1186AlibabaWan 3.0 ReferenceReference-guided Wan 3.0 video with up to 10 images, 5 videos, and 5 audio files.1362MeshyMeshy RemeshRebuilds a 3D model's topology as triangles or quads at a face count you choose.ElevenLabsElevenLabs TTS V4 Turboaka Eleven v4 TurboLower-latency Eleven v4 Turbo speech with audio tags, stability, and similarity control.1333MiniMaxMiniMax H3MiniMax H3 (Hailuo-03) next-gen open-weight video with native stereo audio at 2K and 24 FPS.1356GoogleNano Banana 2.1aka Gemini Nano Banana 2.1Google's Nano Banana 2.1 image model for text-to-image and prompt-guided edits.1176MiniMaxMiniMax H3 ReferenceReference-guided MiniMax H3 video at 2K that follows a reference clip shot for shot while the prompt changes the subject or action.1356xAIGrok Imagine Image 2.0xAI's Grok Imagine Image 2.0 model for high-quality text-to-image generation and editing.1166ByteDanceSeedance 2 USUS-hosted Seedance 2 with clips up to 15s from text, frames, or references, 480p to 4K, with audio.1339GoogleGemini 3.1 Flash Imageaka Nano Banana 2Google's fast, high-quality image generation model with multimodal reasoning.1140PixVersePixVerse v6Latest PixVerse video model with improved quality and audio generation, supporting up to 1080p resolution.1339MeshyMeshy T2.5Meshy T2.5. Text or single image to a clean multi-part triangle mesh, sharper than T2, with textures, PBR, and optional rigging.GoogleGemini 3.8 Flash TTSGoogle's expressive text-to-speech model with style direction and inline vocal events.1283ByteDanceSeedance 2Professional-grade video model with cinematic quality, up to 4K output, and synchronized audio generation.1339ByteDanceSeedream 5.0 ProTop-tier reasoning-first image generation from ByteDance, with built-in online search.1131ByteDanceSeedance 2 FastFast, cost-effective variant of Seedance 2 with 720p output and synchronized audio generation.1339MetaMuse Image 1.0Meta's Muse Image model with faithful instruction-following and precise multi-reference editing.1129ByteDanceSeedance 2 Fast ReferenceFast reference-guided video generation with multi-modal inputs and synchronized audio.1339ByteDanceSeedance 2 ReferenceGenerate videos guided by reference images, videos, and audio with precise style and character control.1339MicrosoftMAI Image 2.5Microsoft's photorealistic image model with strong typography and native editing.1127MeshyMeshy Auto SplitSplits a 3D model into separately printable parts, automatically or along parts you name.QQwen 3 TtsQwen 3 TTSMultilingual TTS with zero-shot voice cloning and prompt-based voice design.1269xAIGrok Imagine Video 1.5xAI's Grok Imagine 1.5 image-to-video model, animating images into 480p or 720p clips.1331MicrosoftMAI Image 2.5 ProMicrosoft's flagship image model for high-fidelity generation and native editing.1123xAIGrok Imagine VideoxAI's video generation model capable of creating high-quality 720p video from text and images.1328OpenAIGPT Image 1.5OpenAI image model with strong instruction following and adherence to prompts.1123xAIGrok Imagine Video ExtendExtend an existing video with xAI's Grok Imagine, continuing motion from the source ending.1328AlibabaHappy Horse 1.1Alibaba's text-to-video and image-to-video model generating 720p or 1080p clips with native audio and multilingual lip-sync.1314Black Forest LabsFLUX.3 ImageBlack Forest Labs' FLUX.3 image model for native 1K to 4K generation and multi-reference editing.1122MeshyMeshy UV UnwrapLays out new UV coordinates on a 3D model, ready for texturing.GoogleGemini 3.8 Flash Lite TTSThe lighter, lower-cost tier of Google's Gemini 3.8 text-to-speech model.1259KlingKling v2.5 Turbo ProHigh-speed video model. Produces rapid, professional-quality 1080p video for fast-paced content.1298GoogleGemini 3 Pro Imageaka Nano Banana ProGoogle's state-of-the-art image generation and editing model.1118AlibabaHappy Horse 1.0Alibaba's text-to-video and image-to-video model generating 720p or 1080p clips with native audio and multilingual lip-sync.1294GoogleGemini 3.1 Flash-Lite Imageaka Nano Banana LiteGoogle's fastest, most cost-efficient Gemini image generation model.1107AlibabaHappy Horse 1.0 ReferenceReference-guided video generation with up to 9 reference images for consistent characters and style.1294ViduVidu Q3 ProVidu's Q3 Pro video model with up to 16s clips, 720p/1080p output, and native audio.1290MeshyMeshy V6 Lite RetextureRetextures an uploaded 3D model from a text style or a reference image, with optional PBR maps.GoogleGemini 3.1 Flash TTSGoogle's most controllable TTS model with 200+ audio tags for vocal style and delivery.1212xAIGrok Imagine ImagexAI's image generation model capable of creating high-quality images from text prompts.1095KlingKling O3 4KGenerate native 4K videos with Kling's Omni 3 model. Cinema-grade output in one step.1280QwenQwen Image 2.1Qwen Image 2.1 text-to-image and editing with configurable size, guidance, and seed.1081KlingKling O3 4K ReferenceGenerate native 4K videos guided by reference images and elements. Cinema-grade output.1280KlingKling O3 ProGenerate high-quality videos from prompts and reference elements, or edit existing footage. Pro tier for premium quality.1280Luma AILuma UNI-1 MaxThe highest-fidelity tier of Luma UNI-1, for hero-quality stills and premium edits.1079KlingKling V3 4KGenerate native 4K videos directly from prompts or images. Cinema-grade output in one step.1277MeshyMeshy V6 RetextureRetextures an uploaded 3D model with Meshy 6 from a text style or a reference image.ElevenLabsElevenLabs TTS V3aka Eleven v3ElevenLabs' most expressive TTS model with inline audio tags for emotion and delivery.1187IdeogramIdeogram V4.5Ideogram's text-to-image and editing model with accurate typography and three quality tiers.1070KlingKling V3 ProGenerate high-quality videos with advanced control. Pro tier with negative prompts.1277ByteDanceSeedream 5.0 LiteFast, high-quality image generation from ByteDance, optimized for creative advertising.1062PixVersePixVerse v5Powerful, user-friendly video model producing high-quality, stylized 1080p video with consistent motion.1276KlingKling O3 StandardGenerate videos with prompts, images, or reference elements. Standard tier for balanced quality and speed.1271QwenQwen Image 2 ProQwen Image 2 Pro tier with higher quality text-to-image generation and enhanced detail.1058MeshyMeshy V7 RetextureRetextures an uploaded 3D model with Meshy 7 from a text style, a reference image or up to four views.xAIxAI TTS V1xAI's text-to-speech model with speech tags for expressive delivery in 20+ languages.1157KlingKling V3 StandardGenerate videos with prompts and images. Standard tier with negative prompts.1270AlibabaWan 2.7 ProAlibaba WAN 2.7 Pro image model for high-quality text-to-image generation and multi-image editing.1050KlingKling v2.6 ProGenerate videos from images with native audio generation and fluid motion.1266RunwayRunway Gen-4.5Runway's high-fidelity image-to-video model with improved prompt adherence and motion quality.1265Luma AILuma UNI-1Luma's unified image model for high-fidelity generation and prompt-based editing.1043GoogleVeo 3.1 FastSpeed-optimized Veo 3.1 model. Delivers high-quality video rapidly for dynamic workflows.1259ByteDanceSeedream 4.5A new-generation image creation model from ByteDance, for both generation and editing.1043TencentHunyuan 3D v3.1 RemeshRebuilds a GLB or OBJ mesh with Hunyuan 3D smart topology at a low, medium, or high polygon density.ElevenLabsElevenLabs Multilingual V2Multilingual text-to-speech with natural voice selection and stability controls.1093GoogleVeo 3.1 Fast Reference to VideoSpeed-optimized reference-guided Veo 3.1: character-consistent video from up to three reference images.1259KreaKrea 2 LargeKrea's flagship text-to-image model for high-fidelity generations with distinctive aesthetic range.1034ByteDanceSeedance 1.5 ProNext-generation Seedance video model with improved quality, 1080p output, and integrated audio generation.1256MiniMaxMinimax Hailuo-2.3 StandardLatest standard video model. Improved prompt understanding and visual consistency for daily creation.1256IdeogramIdeogram V4Ideogram's latest text-to-image model with crisp visuals, accurate text, and image-to-image support.1026MiniMaxMinimax Hailuo-2.3 ProPinnacle of Hailuo T2V series. Cinematic quality with superior coherence, detail, and artistic control.1255Black Forest LabsFLUX.2 [flex]1026HHeygenHeyGen Voice TurboThe faster, lower-cost tier of HeyGen Voice, with the same 39 languages and voice cloning.TripoTripo Smart Retopology v3Tripo's newest retopology: rebuilds a high-poly mesh as clean low-poly topology at a target face count, unwraps fresh UVs and bakes the original textures onto the result.GoogleVeo 3.1Flagship video update: refined control, enhanced visual fidelity, and improved subtle motion details.1253Black Forest LabsFLUX.2 [max]1021GoogleVeo 3.1 Reference to VideoReference-guided Veo 3.1: lock characters and objects across shots using up to three reference images.1253MiniMaxMinimax Hailuo-02 ProPremium video model engineered for professional-grade 1080p output, superior fidelity, and smoother motion.1249KreaKrea 2 TurboSpeed-optimized open-source version of Krea 2 — high-fidelity images in seconds, with the full Krea aesthetic range.1020MiniMaxMinimax Hailuo-02 StandardRobust video model producing crisp 768p video. Offers a solid balance of quality and reliable performance.1246HHeygenHeyGen VoiceHeyGen's natural speech model in 39 languages, with instant voice cloning from one clip.TripoTripo Smart UVRe-unwraps a mesh's UVs with AI-placed seams and packed islands, then remaps its existing textures, rig and animation onto the new layout. Geometry is kept as-is.Black Forest LabsFLUX.2 [dev]1019AlibabaWan 2.5Powerful video model. Optimized for top-tier 1080p cinematic quality and consistency.1245GoogleVeo 3.1 LiteCost-effective Veo 3.1 variant. Balances quality and affordability for high-volume video creation.1242Black Forest LabsFLUX.2 [dev] Edit1019ByteDanceSeedance ProHigh-quality video model. Tuned for maximum visual fidelity and broadcast-quality 1080p output.1234Black Forest LabsFLUX.2 [klein] 9B1015GoogleVeo 3Next-gen video model with enhanced control over narrative, tone, and shot composition. Includes audio.1225MireloMirelo SFX 2.0 Video to AudioSynchronized sound-effect stems timed to an input video.TripoTripo P2Tripo P2. Text or a single image to a textured 3D mesh with PBR, quad topology, and a 48 to 50,000 face budget.Black Forest LabsFLUX.2 [klein] 9B Edit1015AlibabaWan 2.6State-of-the-art multimodal video generation model from Alibaba, with native audio support1222LightricksLTX Video 2.5 FastSpeed-optimized LTX 2.5 audio-video model with 720p–4K output and clips up to 20 seconds.1215Black Forest LabsFLUX.2 [pro]1012LightricksLTX Video 2.5 Fast Audio-to-VideoSpeed-optimized LTX 2.5 mode that generates video timed to a supplied audio clip.1215QwenQwen-Image Edit 2511Latest Qwen image editing model. Supports prompt-guided transformations with enhanced quality.991Luma AIRay 3.2Luma's cinematic video model: generate from text or frames, restyle footage, and reframe to any aspect ratio.1215MireloMirelo SFX 2.0Text-to-sound-effects with duration, negative prompt, and format control.MeshyMeshy V7.1Meshy V7.1. Text, image, and multi-image to 3D with PBR, quad mesh, and optional rigging.MiniMaxMinimax Hailuo-2.3 FastHigh-speed T2V variant. Optimized for rapid creation, iteration, and social media content workflows.1207QwenQwen-Image Edit 2511 Multiple AnglesQwen Image Edit 2511 with the Multiple Angles LoRA. Re-renders the input image from a chosen camera angle.991KlingKling v2.1 MasterPremium 1080p video model. Maximum visual fidelity, capturing intricate details and lifelike expressions.1207QwenQwen Image 2Qwen Image 2 standard text-to-image model with strong prompt adherence and diverse style support.990LightricksLTX Video 2.0 ProHigh-fidelity video model designed for professional-quality results, offering superior detail and nuanced audio.1201GoogleGemini 2.5 Flash Imageaka Nano BananaGoogle's image generation and editing model capable of multimodal reasoning.985LightricksLTX Video 2.5 ProQuality-optimized LTX 2.5 audio-video model for high-fidelity 720p and 1080p output.1194MurekaMureka Podcast 1.0Spoken audio from a script, split across built-in voices.TencentHunyuan 3D UV UnwrapRebuilds an existing mesh's UV layout so it is ready to texture. Geometry is kept as-is and the result is untextured.LightricksLTX Video 2.5 Pro Audio-to-VideoQuality-optimized LTX 2.5 mode for final visuals synchronized to music, dialogue, or soundtrack.1194HHidreamHiDream O1 Image 1.0HiDream's full O1 Image model — create, edit, and personalize images up to 2K in one native model.975LightricksLTX Video 2.0 FastVersatile video model integrating video and audio creation in one seamless, speed-optimized workflow.1191QwenQwen-Image Edit 2509Advanced image editing model. Enhanced performance for fine-grained manipulation.965KlingKling v2.1 ProRefined Kling model delivering professional-grade 1080p video with improved clarity and motion.1185MurekaMureka 9.5 InstrumentalVocal-free music from a text description.TencentHunyuan 3D v3.1 PartSplits a 3D FBX model into separate parts with Hunyuan 3D v3.1.KlingKling Image V3Kling V3 image model. High-quality images with negative prompts, supports up to 2K resolution.952KlingKling v2.0 MasterMaster-grade video model. Enhanced realism and physics simulation for cinematic, high-impact clips.1180LightricksLTX Video 2.3Latest LTX video model with sharper details, cleaner audio, and portrait support for professional content creation.1157Black Forest LabsFLUX.2 [klein] 4B938LightricksLTX Video 2.3 FastSpeed-optimized LTX video model with extended duration support up to 20 seconds and portrait mode.1150Black Forest LabsFLUX.2 [klein] 4B Edit938ByteDanceSeedance LiteVersatile and efficient video model. Optimized for speed and ideal for short clips and rapid prototypes.1138MurekaMureka 9.5 SongComplete songs with vocals from a description or supplied lyrics.HHitem3DHi3D v3.0Hi3D v3.0 image-to-3D at 2048³ with PBR materials and face counts up to 5M.KlingKling v1.6 ProPowerful video model for high-fidelity, imaginative content with complex character motion.1137TencentHunyuan Video 1.5High quality open-source video model from Tencent Hunyuan.1134Black Forest LabsFLUX.1 Kontext [max]Premium model for max editing performance, superior typography, and visual narrative consistency.932MiniMaxMiniMax H3 Max ReframeReframe a video with MiniMax H3 Max, outpainting the new canvas while keeping the source audio and timing.1118Black Forest LabsFLUX.1 Kontext [pro]Pro-grade multimodal model for fast, iterative editing, style transfer, and consistency.917MiniMaxMiniMax H3 Max RelightRelight a video with MiniMax H3 Max, keeping the source subjects, motion, camera, and audio.1118Stability AIStable Audio 3 Small SFXFast sound effects with restyle, extend and inpaint.UthanaUthana AnimateRetargets a Uthana motion — trained, or generated from a prompt or video — onto your character.MiniMaxMiniMax H3 MaxMiniMax H3 Max post-trained video with native stereo audio at 480p, 768p, or 1080p.1118Bria AIBria FIBO Edit Restore 1.0Bria's one-shot photo restoration, trained on licensed data.915MiniMaxMiniMax H3 Max ExtendExtend a video clip with MiniMax H3 Max: 5-15 seconds of new footage at 480p, 768p, 1080p, or 2K.1118QwenQwen-ImageOpen-source T2I model. Excels at high-res images from complex text, notable for clear, stylized text.903MiniMaxMiniMax H3 Max InsertInsert a new 5-13 second scene into a video with MiniMax H3 Max, then return to the original footage.1118Black Forest LabsFLUX.1 Krea [dev]Open-weight model co-developed with Krea AI. Excels in photorealism and aesthetics.896MiniMaxMiniMax H3 Max ReferenceReference-guided MiniMax H3 Max video up to 1080p that follows a reference clip shot for shot while the prompt changes the subject or action.1118Stability AIStable Audio 3 Small MusicFast, low-cost music up to two minutes, with restyle, extend and inpaint.UthanaUthana Auto-Rig CharacterUthana's automatic character rigging model, preparing an uploaded mesh with a skeleton.MiniMaxMiniMax H3 Max TurboMiniMax H3 Max Turbo post-trained video with native stereo audio at 480p, 768p, or 1080p.1118Black Forest LabsFLUX.1 Kontext [dev]Open-weight, multimodal model for context-aware image editing. Excels at iterative edits via text.883ByteDanceSeedance 2.5 USUS-hosted Seedance 2.5 with clips up to 30s from text, frames, or references, and native audio.1104HHidreamHiDream O1 Image DevHiDream's distilled O1 Image Dev model — create, edit, and personalize images up to 2K in one native model.880ByteDanceSeedance 2.5ByteDance's Seedance 2.5 video model with up to 30s clips, 480p/720p/1080p output, and native audio.1104ByteDanceSeedance 2.5 ReferenceReference-guided Seedance 2.5 video with up to 30 images, 10 videos, and 10 audio files.1104Black Forest LabsFLUX 1.1 [pro]Next-gen FLUX model. 6x faster with enhanced prompt adherence and top-tier quality for production.870Stability AIStable Audio 3 MediumFull songs and long scores up to six minutes, with restyle, extend and inpaint.MeshyMeshy T2Meshy T2. Text or single image to a compact, cleanly built multi-part mesh with textures, PBR, and optional rigging.GoogleVeo 2Legacy video model generating high-definition, long-form cinematic video content.1099Black Forest LabsFLUX 1.1 [pro] UltraDelivers ultra-high-res (up to 4MP) images with superior photorealism, detail, and speed.855Black Forest LabsFLUX.3 EditEdit an existing video with FLUX.3 from a text instruction, preserving motion, timing, and framing.1091Black Forest LabsFLUX.1 SRPO [dev]12B flow transformer fine-tuned with SRPO for exceptional photorealism and polished composition.826Black Forest LabsFLUX.3 ExtendExtend an existing video clip with FLUX.3, continuing motion and native audio from the source ending.1091Black Forest LabsFLUX.3 KeyframesGuide FLUX.3 video generation with up to 10 keyframe images pinned across the clip.1091VEEDVEED Clean Audio 1.0Remove background noise from speech while keeping quiet and distant words intact.Hyper3DRodin BangSegments a 3D mesh into parts with Hyper3D Bang!Black Forest LabsFLUX.1 [dev]Powerful, open-weight 12B image model. Excels in image quality, prompt adherence, and commercial use.823Black Forest LabsFLUX.3Frontier video model from Black Forest Labs with native audio, lipsync, and first/last frame control.1091Black Forest LabsFLUX.1 [schnell]Ultra-fast, open-source model. Generates high-quality images in 1-4 steps for rapid prototyping.740RunwayRunway Aleph 2Runway's next-generation video-to-video model for restyling and transforming existing footage from a prompt.1088RunwayRunway Gen-4 TurboRunway's speed-optimized image-to-video model for rapid, high-quality clip generation.1088KreaKrea 3Krea 3 text-to-image and multi-reference editing at 1K or 2K.GoogleLyria 3.5Google DeepMind's latest music model, writing full-length songs with vocals from one prompt.Hyper3DRodin Gen-2Hyper3D Rodin Gen-2 delivers sharper geometry and cleaner textures from a single image or prompt.GoogleGemini Omni Flash 1.1 ReferenceReference-guided video generation with up to 10 images and 3 clips of up to 10 seconds each for consistent characters and style.1067Black Forest LabsFLUX.3 Klein Base EditBlack Forest Labs' FLUX.3 Klein Base editor for multi-reference edits at 1K to 4K.GoogleGemini Omni Flash 1.1Google's multimodal video model — 720p, 1080p, or 4K clips with synchronized native audio from text or a still image.1067Black Forest LabsFLUX.3 Klein BaseBlack Forest Labs' FLUX.3 Klein Base for native 1K to 4K text-to-image.AlibabaWan 2.1State-of-the-art video model. Generates detailed, stylistically diverse clips with fluid motion.1000xAIGrok Imagine Video 1.5 LitexAI's lower-cost Grok Imagine Video 1.5 Lite, generating 480p, 720p, or 1080p clips from text or a still image.974Black Forest LabsFLUX.3 KleinBlack Forest Labs' distilled FLUX.3 Klein model for fast 1K to 4K generation and multi-reference editing.MiniMaxMiniMax Music 3High-performance MiniMax music model for complete songs up to five minutes with structure tags and seed control.Hyper3DRodin Gen-2.5Hyper3D Rodin Gen-2.5 pushes structural detail and surface quality further, with selectable quality.TencentHunyuan VideoImpressive open-source video model. Excels at stable, coherent sequences with high visual quality.920falText Removal 1.0Remove all the text from an image.KlingKling O1Generate new videos from first and last frame images.887Bria AIBria FIBO Edit Rewrite Text 1.0Rewrite the text in an image, keeping its typography.KlingKling O1 ReferenceGenerate new videos guided by prompts, images or videos.887Bria AIBria Video Green ScreenBria's chroma keyer for footage shot on a green screen, with spill suppression.Bria AIBria Eraser 1.0Bria's eraser for painted areas, trained on licensed data.SSoniloSonilo Video to Music 1.1Frame-synced, licensed music scored from video pacing, mood, and timing.HHitem3DHi3DHi3D image-to-3D with multi-view support, PBR materials, and configurable face counts.KlingKling v4 Video EditEdit existing videos with a prompt, reference images, and character elements, at 720p or 1080p.falObject RemovalLow-cost object removal by name or by painted area.KlingKling v4Generate 720p or 1080p videos up to 30 seconds from a prompt, first and last frames, or reference images, clips, and elements.KlingKling v4 Flash ReferenceGenerate fast 720p videos from reference images, clips, and character elements.IdeogramIdeogram Object Removal 3.0Ideogram's prompt-free eraser for painted areas.KlingKling v4 FlashGenerate fast 720p videos from a prompt or a first frame, with optional native audio.FFinegrainFinegrain EraserRemove objects along with their shadows, reflections and lighting.SSoniloSonilo Video to Sound Effects 1.1Synchronized, royalty-free sound effects timed to actions visible in a video.HHitem3DHi3D PartsSplits a 3D model into parts for editing, printing, or modular asset workflows.Black Forest LabsFLUX.3 Max KeyframesGuide FLUX 3 Max video with up to 10 keyframe images spaced across a 720p or 1080p clip.falExpression Edit 1.0Change a face's expression to the one you describe.Black Forest LabsFLUX.3 MaxBlack Forest Labs' post-trained FLUX 3 Max video model, with native audio and first/last frame control at 720p or 1080p.ByteDanceOmniHuman v2ByteDance OmniHuman v2 animates a still photo from audio, with optional prompt control of motion and camera.falExpression Change 2.0Give a face one of twenty named expressions.MireloMirelo SFX 2.0 Video to VideoAdds synchronized sound effects and returns the video with its new soundtrack.SSoniloSonilo Music 1.1Licensed, commercial-use-safe music from a text prompt with exact duration control.HHitem3DHi3D TextureTextures an existing Hi3D-compatible geometry mesh from a reference image.falImage2PixelTurn an image into pixel-perfect pixel art.falID-V2VRestyle a video from an edited first frame, keeping motion and identity.DDecartDecart Lucy Edit ProEdit outfits, objects or faces in a video from a prompt.Bria AIBria FIBO Edit Colorize 1.0Bria's one-shot colorization, trained on licensed data.DDecartDecart Lucy RestyleRestyle a video from a prompt, keeping its motion and detail.TTelestyleTeleStyle 2.0Repaint an image in the style of a reference image.HHeygenHeyGen Translate SpeedFaster lip-synced translation of a clip.SSoniloSonilo Sound Effects 1.1High-quality, commercial-use-safe sound effects from text with exact duration control.TencentHunyuan 3D v3.1 FastFast Hunyuan 3D model for rapid 3D generation with PBR material support.IdeogramIdeogram Layerize Text 3.0Split a flat graphic into a clean background and live text layers.HHeygenHeyGen Translate PrecisionTranslate a clip into another language with re-synced lips.ElevenLabsElevenLabs DubbingDub a clip's speech into another language in the speakers' own voices.falPATINA Tileable 1.0Tileable PBR materials from a prompt or a photo: texture plus base color, normal, roughness, metalness and height.LightricksLTX Video 2.3 Quality Clean PlateRemove the people from a clip, leaving the empty set.falPATINA 1.0Read a texture's base color, normal, roughness, metalness and height maps, packed for any game engine.falVOID Video InpaintingRemove an object and every interaction it causes in the scene.ByteDanceSeed Audio 1.0Bytedance Seed Audio TTS with preset voices and zero-shot voice cloning.TencentHunyuan 3D v3.1 ProLatest Hunyuan 3D model with enhanced quality, multi-view input, and PBR material support.Pruna AIP-Image UpscalePruna's sub-second upscaler, scaling images up to 8x and 128 megapixels.MurekaMureka Lyrics Video 1.0A formatted lyrics video from an audio track.KandinskyKandinsky 6.0 LiteKandinsky Lab's lightweight video model, generating 5-second 480p or 1080p clips from text or a still image.Pruna AIP-ImagePruna's sub-second text-to-image and multi-image editing model built for production volume.MiniMaxMiniMax H3 Max RecastRecast the people in a video with MiniMax H3 Max, keeping the source motion, camera, cuts, and audio.ByteDanceSeedream 5.0 Flash LayerizeSplit a finished image into editable layers, fast, with Seedream 5.0 Flash Layerize.MireloMirelo SFX 1.6Sound effects generation and editing with text-to-audio and audio inpainting.TripoTripo P1Game-ready Tripo model: a single image to clean low-poly 3D with PBR textures.Pruna AIP-Video ReplacePruna's character swap: replaces the person in a video with one from reference images.Pruna AIP-Video AnimatePruna's motion transfer: a reference image performs the motion and audio of a source video.ByteDanceSeedream 5.0 FlashFast, budget-friendly image generation and editing from ByteDance's Seedream 5.0 line.Pruna AIP-Video EditPruna's video editor: change a clip of up to 15 seconds with a prompt and optional reference images.HiggsfieldSoul CinemaHiggsfield's text-to-image model with a fixed cinematic, film-still look.Pruna AIP-Video Avatar TTSPruna's talking avatar that voices a written script with a built-in voice.MiniMaxMinimax Music V2.5Updated MiniMax music model with improved vocal quality and arrangement control.TripoTripo v3.1High-detail Tripo model for production assets with dense geometry and refined textures.HiggsfieldSoul 2Higgsfield's photographic text-to-image model for fashion, editorial and character imagery.Pruna AIP-Video AvatarPruna's fast, low-cost talking avatar: a photo lip-synced to an audio track.Pruna AIP-Video 2 ProPruna's highest-quality video model, with speed and quality modes at 480p or 768p.RecraftRecraft V4 Pro VectorRecraft's pro V4 text-to-vector tier, with higher fidelity than the standard vector tier.Pruna AIP-Video 2Pruna's quality-focused successor to P-Video, at 720p or 1080p.RecraftRecraft V4 VectorRecraft's V4 text-to-vector model. Generates scalable vector art (SVG) directly from a prompt.Pruna AIP-VideoPruna's fast video model for text-to-video and image-to-video at 720p or 1080p.GoogleGemini TTSGoogle's text-to-speech model with multi-speaker support and natural expressiveness.TencentHunyuan 3D 3.0Professional-grade 3D model optimized for high-quality, detailed assets with advanced features.MiniMaxMiniMax H3 Max 3D to VideoRender a Blender proxy animation as realistic video with MiniMax H3 Max, keeping its camera and motion.GoogleGoogle Virtual Try-On 1.0Google Virtual Try-On: dress a person photo with a clothing product image.PixVersePixVerse VibeMV 1.0PixVerse music video model that turns a song into a full video timed to the track.Topaz LabsTopaz Dust-Scratch V2Topaz film clean-up for dust and scratches.KlingKling V2.6 Standard Motion ControlKling's motion control: the character in your image performs the motion of a reference video.Topaz LabsTopaz Recover 3 RestoreTopaz's generative restoration, rebuilding natural detail.KlingKling V2.6 Pro Motion ControlKling's motion control: the character in your image performs the motion of a reference video.ElevenLabsElevenLabs Audio IsolationIsolate clean voice from noisy recordings by removing background noise and music.MicrosoftTrellis 2aka TRELLIS.2-4BOpen-source, high-quality 3D model from Microsoft, leveraging a novel field-free sparse voxel structure.KlingKling V3 Standard Motion ControlKling's motion control: the character in your image performs the motion of a reference video.Topaz LabsTopaz Denoise MaxTopaz's generative denoiser, rebuilding detail as it cleans.KlingKling V3 Pro Motion ControlKling's motion control: the character in your image performs the motion of a reference video.Topaz LabsTopaz Denoise ExtremeTopaz's most aggressive conventional denoiser.HiggsfieldGenjutsu Object SwapHiggsfield's video model that swaps an object in a source clip for one shown in reference images.Topaz LabsTopaz Denoise StrongTopaz denoising tuned for heavier noise.HiggsfieldGenjutsu Motion TransferHiggsfield's video model that moves a referenced character through the motion of a source clip.CassetteAICassetteAI Sound EffectsReal-time sound effects generation in under 1 second, up to 30 seconds long.ByteDanceBytedance Seed 3DPowerful 3D model focusing on high-quality objects from a single image. Adept at geometry & texture.LightricksLTX Video 2.3 Quality OutpaintSpatially outpaint a source video to a new aspect ratio with LTX 2.3 Quality.Topaz LabsTopaz Denoise NormalTopaz general-purpose denoising at the source resolution.MiniMaxMiniMax H3 Max Lip SyncMiniMax H3 Max lip-sync: animate a still to a voice track at 480p, 768p, 1080p, or 2K.Topaz LabsTopaz Transparency UpscaleTopaz upscaling that preserves the alpha channel end to end.Black Forest LabsFLUX.3 Video Upscale CreativeFLUX.3-powered video upscaler that adds detail, up to 4K.Black Forest LabsFLUX.3 Video UpscaleFLUX.3-powered source-faithful video upscaler, up to 4K.Topaz LabsTopaz Bloom RealismTopaz's creative upscaler with its invented detail biased toward photorealism.RRikoroseDeepFilterNet3Real-time speech enhancement and noise suppression at 48 kHz full-band audio.MetaSAM 3D Align 1.0Meta SAM 3D Align places body and object meshes into a spatially coherent scene from one image.Topaz LabsTopaz SDR to HDRTopaz SDR-to-HDR conversion for grading and mastering.Topaz LabsTopaz Bloom 2Topaz's creative image upscaler, reinventing detail with an adjustable creativity dial.Topaz LabsTopaz Themis 2Topaz motion deblur, faithful to the source footage.Topaz LabsTopaz Recovery V2Topaz's upscaler for extremely low-resolution sources.Topaz LabsTopaz Nyx XLTopaz's video denoiser tuned for extreme noise.MetaSAM Audio SeparateFoundation model for audio source separation using text, visual, or temporal prompts.MetaSAM 3D Body 1.0Meta SAM 3D Body reconstructs accurate human body shape and pose from a single image.Topaz LabsTopaz Nyx HFTopaz's precision video denoiser for pipeline-ready output.Topaz LabsTopaz Standard MAXTopaz's precision-leaning generative upscaler.Topaz LabsTopaz Nyx FastTopaz's half-price video denoiser for high-volume work.Topaz LabsTopaz Recover 3Topaz's restorative upscaler, rebuilding natural detail in damaged images.Topaz LabsTopaz NyxTopaz's high-quality video denoiser, preserving texture.Topaz LabsTopaz RedefineTopaz's prompt-guided generative upscaler.Topaz LabsTopaz AionTopaz's frame interpolator for extreme and complex motion.IInworld AIInworld TTS 1.5 MaxInworld's premium TTS model optimized for expressive game character voices.MetaSAM 3D Objects 1.0Meta SAM 3D Objects reconstructs textured 3D geometry from a single real-world image.Topaz LabsTopaz ChronosTopaz's frame interpolator tuned for real-world motion.Topaz LabsTopaz Wonder 3.5Topaz's generative image upscaler, rebuilding detail with fewer repeated patterns.Topaz LabsTopaz ApolloTopaz's general-purpose frame interpolator, retiming footage up to 120fps.Topaz LabsTopaz Text RefineTopaz's precision upscaler that keeps text and hard shapes crisp.Topaz LabsTopaz Astra 2Topaz's creative video upscaler, reinventing detail for maximum visual impact.Topaz LabsTopaz Starlight Fast 2Topaz's fastest and cheapest generative video upscaler.Topaz LabsTopaz CGITopaz's precision upscaler for rendered art and CG rather than photographs.ElevenLabsElevenLabs Voice ChangerTransform the voice in an audio recording to a different target voice.TripoTripo AnimateRigs a 3D mesh and applies a preset animation from the animation library, returning an animated GLB.Topaz LabsTopaz Starlight SharpTopaz's faster generative video upscaler with sharper output.Topaz LabsTopaz Low Resolution V2Topaz's precision upscaler tuned for small, compressed sources.Topaz LabsTopaz Starlight MiniTopaz's generative video upscaler tuned for archival restoration.Topaz LabsTopaz High Fidelity V3Topaz's detail-preserving precision upscaler for professional photography.Topaz LabsTopaz Starlight HQTopaz's highest-quality generative video upscaler.Topaz LabsTopaz Starlight Precise 2.6Topaz's generative video upscaler, rebuilding detail that the source never had.Topaz LabsTopaz Standard V2Topaz Gigapixel precision upscaling, faithful to the original image.Stability AIStable AudioOpen-source text-to-audio model for sound effects, field recordings, and instrument samples.TripoTripo RemeshRebuilds a high-poly 3D mesh as a low-poly model at a target face count, baking the original textures onto the result.Topaz LabsTopaz Theia Fine Tune DetailTopaz's manually tuned precision upscaler, biased toward detail.MetaSAM 3.1 ImageMeta's SAM 3.1 for fast multi-object image segmentation.Topaz LabsTopaz RheaTopaz's maximum-detail precision upscaler.Topaz LabsTopaz Gaia 2Topaz's animation-tuned precision upscaler, and its cheapest tier.Black Forest LabsFLUX Pro VTOVirtual try-on from Black Forest Labs: dress a person photo with a garment reference.Topaz LabsTopaz Gaia CGTopaz's precision upscaler for rendered and CG video.KlingKling Video to AudioGenerate synchronized sound effects, dialogue, and ambient audio from video content.TripoTripo RetextureRetextures an existing mesh from a text prompt or reference image, keeping geometry intact.ByteDanceSeedream 5.0 Pro LayerizeSplit a finished image into independently editable layers with Seedream 5.0 Pro Layerize.Topaz LabsTopaz Gaia HQTopaz's precision upscaler for refining already-clean footage.RecraftRecraft V4.1 VectorRecraft's V4.1 text-to-vector model. Generates scalable vector art (SVG) directly from a prompt.Topaz LabsTopaz Artemis High QualityTopaz's precision upscaler that denoises and sharpens as it enlarges.Topaz LabsTopaz Dione DVTopaz's deinterlacing precision upscaler for legacy tape sources.RecraftRecraft V4.1 Pro VectorRecraft's V4.1 Pro text-to-vector model. Generates scalable vector art (SVG) directly from a prompt.Topaz LabsTopaz IrisTopaz's precision upscaler specialised in recovering facial detail.GoogleLyria 3 ProPremium tier of Google's Lyria 3 with highest fidelity and compositional complexity.TripoTripo RigAuto-rigs a 3D mesh, returning a rigged GLB. Humanoid meshes come back with a Mixamo-named skeleton for direct use in game engines; other body plans use Tripo's own naming, which Mixamo cannot describe.falImage to SVGConvert raster images to clean, scalable SVG vector graphics with fine-grained control over detail.Topaz LabsTopaz Proteus NaturalTopaz's softer precision upscaler, tuned to look untouched.IdeogramIdeogram Remove BackgroundFast, clean background removal from Ideogram.Topaz LabsTopaz ProteusTopaz's precision video upscaler, enhancing detail without inventing it.VEEDVEED Lipsync 2.0Production-quality lipsync that re-articulates a source video to match any new audio track.RecraftRecraft Creative UpscaleUpscale for a sharper, cleaner, higher-resolution result.SSyncsync.so Avatar (Image to Video)Turns a single still image into a talking character lip-synced to a voice track.GoogleLyria 3Google DeepMind's next-generation music model with enhanced composition and vocal quality.TripoTripo SegmentSegments a 3D mesh into parts, returning a part-grouped model for further editing.PPixelcutPixelcut Background RemovalHigh-quality image background removal from Pixelcut.ByteDanceOmniHuman 1.5ByteDance's latest OmniHuman, bringing a still photo to life from audio with improved motion and expression.SSyncsync.so Lipsync 2 ProHigh-quality realistic lipsync that preserves unique facial details from any new audio track.RecraftRecraft Crisp UpscaleBoost resolution while refining small details and faces.falAuto CaptionRecraftRecraft V4.1Professional design model with extended prompt support (10,000 characters) and advanced style customization.ElevenLabsElevenLabs MusicPremium AI music generation from ElevenLabs with composition planning and section control.TripoTripo v3.0Latest 3D model for production-quality assets with superior textures and clean geometry.VEEDVEED SubtitlesRecraftRecraft V4.1 ProProfessional design model with extended prompt support (10,000 characters) and advanced style customization.SSyncsync.so Lipsync 3sync.so's most powerful lipsync model, re-articulating a source video to any new audio track.ByteDanceLatentSyncFast, affordable video-to-video lipsync that syncs mouth motion to any audio track.QwenQwen-Image LayeredSplit an image into layers using Qwen-Image Layered.MetaSAM 3.1 VideoMeta's SAM 3.1 for multi-object video segmentation and tracking.KlingKling Image O3Kling Omni 3 image model. High-quality images with text rendering capabilities up to 4K resolution.MiniMaxMinimax Music V2.6Latest MiniMax music model with native audio-visual generation capabilities.MeshyMeshy RiggingAuto-rigs humanoid 3D models and optionally applies a preset animation, returning rigged GLB/FBX.SSoniloSonilo Video Music 1.1Mux frame-synced, licensed music onto any video; optionally keep original speech.SSoniloSonilo Video Sound Effects 1.1Add synchronized, royalty-free sound effects mixed into the finished video.RecraftRecraft V4Professional design model with extended prompt support (10,000 characters) and advanced style customization.PPixelcutPixelcut Video Background RemovalRemove video backgrounds with Pixelcut for clean cutouts.RecraftRecraft V4 ProRecraft's pro V4 tier, with higher fidelity and finer detail than the standard tier.Bria AIBria Video Background Removal v3Bria's v3 video background removal for advanced video editing.AACE StudioACE-StepFast open-source music generation with lyrics alignment, remixing, and audio editing.Hyper3DRodin Gen-1.5Advanced 3D generation model creating high-quality, textured T-pose avatars from a single image.QwenQwen-Image 2512Latest Qwen text-to-image model with enhanced quality, detail, and prompt adherence.falVideo SubtitlesBria AIBria Video Background RemovalRemove video backgrounds for advanced video editing.ByteDanceSeedVR2 Image UpscalerByteDance's SeedVR2 model for high-quality image upscaling.Bria AIBria Video Increase ResolutionBria's advanced AI technology designed to increase the resolution of video content efficiently.Topaz LabsTopaz Generative EnhanceTopaz Generative Enhance for enhanced details.ByteDanceSeedVR2 Video UpscalerPowerful video upscaling model from ByteDance, optimized for high-quality resolution and fidelity improvement.Stability AIStable Audio 2.5Enterprise-grade audio generation with multi-part compositions and audio inpainting.TencentHunyuan 3D v2 Miniaka Hunyuan3D-2miniLightweight, efficient 3D version optimized for less powerful hardware. Delivers good quality assets.Topaz LabsTopaz EnhanceEnhance image quality with advanced upscaling.ESRGANESRGAN Video UpscalerESRGAN model for video upscaling, enhancing resolution and detail.Topaz LabsTopaz Video UpscalerProfessional-grade video upscaling solution utilizing Topaz AI technology for high-quality enhancement.ESRGANESRGAN UpscalerVery fast upscaling with good quality.Luma AIRay 2 FlashHigh-speed variant of Ray 2, optimized for rapid video creation. Perfect blend of speed and quality.Clarity AIClarity Creative UpscalerUpscale images with high fidelity or creativity.Luma AIRay 2Large-scale, state-of-the-art video model for stunning realistic and coherent 1080p motion.GoogleLyria 2Google DeepMind's high-fidelity 48 kHz music model with fine-grained creative control.TripoTripo v2.5Incremental 3D update. Refined performance, improved mesh topology, and texture fidelity.ByteDanceOmniHumanAdvanced video model bringing a still image of a person to life using audio, producing expressive videos.RecraftRecraft Vectorize ImageConvert raster images to vector graphics using Recraft.MultiTalkAI AvatarSpecialized model for creating realistic, audio-driven talking avatars with accurate lip-sync and expressions.Nankai UniversityBiRefNet v2High-quality image background removal.GoogleVeo 3 FastSpeed-optimized Veo 3 variant for rapid video creation and iteration, ideal for short-form content.ByteDanceSeedream 4.0Unified architecture for image generation and editing. Allows fluid movement from concept to refinement.Sand AIMagi DistilledFast, efficient open-source I2V model. Animates still images using an autoregressive approach.CassetteAICassetteAI MusicUltra-fast music generation producing 3-minute tracks in under 10 seconds at 44.1 kHz.TencentHunyuan 3D v2aka Hunyuan3D 2.0Powerful, open-source 3D model producing high-res, textured 3D objects from text or image inputs.LayerFramepackHighly efficient, open-source I2V model that generates video by predicting the next frame.RecraftRecraft V3Versatile image model for graphic design. Generates legible, stylized text and scalable vector art (SVG).TencentHunyuan Video FoleySpecialized model to automatically create and sync sound effects (foley) for video content.Black Forest LabsFLUX.1 [pro]Flagship commercial T2I model offering superior prompt adherence, quality, and stylistic outputs.MiniMaxMinimax Video 01 LiveSpecialized video model. Optimized for a dynamic, live-action feel with naturalistic camera work.ElevenLabsElevenLabs Sound EffectsGenerate custom sound effects from text descriptions with duration and prompt control.MiniMaxMinimax Video 01Accessible video model. Generates engaging 720p clips from text with good visual consistency.MicrosoftTrellisOpen-source 3D model creating high-quality objects with realistic materials and geometry from text.Stability AIStable Diffusion 3aka SD3Latest open-weight MM-DiT model. Major improvements in quality, prompt following, and text rendering.

Audio model FAQ

Which is the best AI audio model?+
ElevenLabs TTS V4 by ElevenLabs leads Layer's audio models with an Artificial Analysis Arena Elo of 1335, ahead of 8 other scored audio models.
What are the top audio models on Layer?+
The top audio models by Elo rating are: 1. ElevenLabs TTS V4 (Elo 1335), 2. ElevenLabs TTS V4 Turbo (Elo 1333), 3. Gemini 3.8 Flash TTS (Elo 1283), 4. Qwen 3 TTS (Elo 1269), 5. Gemini 3.8 Flash Lite TTS (Elo 1259). Ratings come from blind votes in the Artificial Analysis Arena.
How are audio models ranked on this page?+

Audio models are ranked by their Artificial Analysis Arena Elo: people compare two generations made from the same prompt without being told which model made which, and a model preferred more often scores higher. An Elo is a standing inside one modality, so models are only ever ranked against others of their own kind. A model with no arena score yet sits below the scored ones, ordered by how much it is used on Layer and how recently it was released.

How many audio models does Layer have?+

Layer gives you 47 audio and voice models from 18 providers — ElevenLabs, Google and Stability AI among them — in one workspace, on one balance, behind one API.

Which audio models can I train on my own artwork?+
3 of them can be fine-tuned on a studio's own art, Qwen 3 TTS among them. Upload a reference set, train a style, and every generation from it carries your look rather than the model's default one.
How much do audio models cost?+
Nothing is charged per seat. Generating on Layer spends Creative Units, each model has its own rate, and you pay only for what you generate — every model page states its current price, and the pricing page lists them all.

More questions? Check out our Help Center.

Pick a model and start creating

Every model in the catalogue runs in one workspace, on one balance of Creative Units. No extra subscriptions.

Start creatingTalk to sales