All tools

Every model and tool on Imagera

180+ media models, plus LoRA training, music modes and your libraries, across 21 operations and 110 studios, with real samples and credit prices.

Models by operation

Studios and tools

Show

All models 254

Sort

Imagera Warlord Pro

Up to 30 seconds at 1080p with native audio in one pass

Text to video20 cr

Imagera Warlord Pro (Image)

First and last frame control across a 30-second take

Image to video20 cr

Imagera Warlord Pro Reference

Images, clips, audio, documents and web pages as references

Reference to video20 cr

Imagera Hermes Lipsync

Hand it a photo and a track and the person in the photo speaks it: lips, jaw, breath and blinks timed to the audio rather than smeared across it, with the face, hair, light and room held exactly as you gave them. Any face at any framing from tall portrait to wide shot — the photo sets the shape — and any resolution from 480P up to a 2K master. Five to fifteen seconds of audio per take; anything past 14.8 seconds is cut, so split a longer script into takes. Speech, singing, a two-person line, a lyric over a beat: if you can record it, the photo can say it. A nine-second take comes back in about twenty seconds.

Lipsync35 cr

Imagera Hermes Camera Control

Your photo, with the camera actually moving

Image to video

Imagera Flora Edit

Prompt-edit a clip, 1–15s · 50 MB · 720p

Video to video15 cr

Imagera 3D Quality — From Image

Detailed, textured 3D models. From one picture.

Image to 3D155 cr

Imagera 3D Quality — From Images

Detailed, textured 3D models. From several pictures of one object.

Image to 3D155 cr

Imagera 3D Quality

Detailed, textured 3D models. From a prompt.

Text to 3D155 cr

Imagera Hermes Image

Cinematic stills from a prompt, 1K or 2K

Text to image15 cr

Imagera Hermes Image Edit

Re-stage a subject from up to 9 references, 1K or 2K

Edit image15 cr

Imagera Live AI Director

Live movies, directed as they play. Start with a scene, image or soundtrack.

Text to video865 cr

Imagera Hermes Turbo

The fastest clip in the lineup, from a sentence

Text to video30 cr

Imagera Hermes Turbo (Image)

Your still, moving, at the Turbo rate

Image to video30 cr

Imagera Hermes Max

A finished clip in about seven seconds

Text to video55 cr

Imagera Hermes Max (Image)

Your still, moving, almost immediately

Image to video55 cr

Imagera Hermes Max (Reference)

Compose from photos, clips and voice — fast

Reference to video55 cr

Imagera Lip Sync — Fast

Put a voice track onto a still photo so the mouth matches it. The distilled pass — quick, and the cheaper of the two.

Lipsync25 cr

Imagera Lip Sync — Studio

Put a voice track onto a still photo so the mouth matches it. The full pass — slower, and it holds detail the fast tier softens.

Lipsync30 cr

Imagera Horizon Lipsync

Put a new voice track on a video you already have, mouth matched to the new words. Billed by the second of finished video.

Video to video65 cr

Imagera Horizon Fast

Put a new voice track on a video you already have, mouth matched to the new words. Billed by the second of finished video.

Video to video35 cr

Imagera Horizon Studio

Put a new voice track on a video you already have, mouth matched to the new words. Takes clips up to 10 minutes.

Video to video45 cr

Imagera Warlord

Up to 30 seconds at 1080p with native audio in one pass

Text to video20 cr

Imagera Warlord (Image)

First and last frame control across a 30-second take

Image to video20 cr

Imagera Warlord Reference

Images, clips, audio, documents and web pages as references

Reference to video20 cr

Imagera Hermes Spicy

Unrestricted video from a prompt · 18+

Text to video50 cr

Imagera Hermes Spicy (Image)

Unrestricted motion from your photo · 18+

Image to video50 cr

Imagera Hermes Spicy (Reference)

Unrestricted shots from photos, clips and voice · 18+

Reference to video50 cr

Tripo P2 — From Image

High-fidelity textured 3D models. From one picture.

Image to 3D140 cr

Tripo P2

High-fidelity textured 3D models. From a prompt.

Text to 3D140 cr

Imagera Hermes Video Gen

Prompt to film with native audio, up to 4K

Text to video30 cr

Imagera Hermes Video Gen (Image)

Bring a still to life, or tween two frames

Image to video30 cr

Imagera Hermes Video Gen (Reference)

Compose a shot from photos, clips and voice

Reference to video30 cr

Imagera Typeset 3

Image generation with readable lettering in posters, signs and layouts.

Text to image15 cr

Imagera Typeset 3 (Edit)

Image editing that keeps lettering readable while changing the rest of the frame.

Edit image15 cr

Seedream 5 Pro

High-fidelity image generation for detailed, structured compositions.

Text to image15 cr

Seedream 5 Pro Edit

High-fidelity image editing with consistent visual references.

Edit image15 cr

Nano Banana 2 Lite

Efficient image generation and reference-guided editing.

Text to image15 cr

Imagera Warrior

Pro quality, 4K, premium detail

Text to image15 cr

Imagera Warrior Edit

Pro quality, 4K, multi-image edit

Edit image15 cr

PixVerse V6 Text To Video

Text-to-video generation with motion, audio and visual style control.

Text to video20 cr

PixVerse V6 Image To Video

Image-to-video generation with motion, audio and visual style control.

Image to video20 cr

PixVerse V6 Reference To Video

Reference-to-video generation with motion, audio and visual style control.

Reference to video20 cr

PixVerse V6 Transition

Interpolate a first and last frame into a clip with motion and audio.

Image to video20 cr

PixVerse V6 Extend

Continue an existing clip with matching motion, audio and visual style.

Video to video20 cr

Tripo H3.1 — From Image

From one picture.

Image to 3D40 cr

Tripo H3.1 — From Views

From front, side and back views.

Image to 3D40 cr

Tripo H3.1

From a prompt.

Text to 3D30 cr

Seedream 5 Lite

Efficient image generation for detailed, structured compositions.

Text to image15 cr

Seedream 5 Lite Edit

Efficient image editing with consistent visual references.

Edit image15 cr

Imagera Queen

2K output, best-in-class text rendering

Text to image15 cr

Imagera Queen Edit

2K edit, best-in-class text rendering

Edit image15 cr

Imagera Multilingual Dubber

Translate a clip into another language. Same faces, same footage, new voice.

Video to video80 cr

Imagera 3D Fast — From Image

Quick textured 3D models. From one picture.

Image to 3D40 cr

Z-Image

Efficient image generation with natural lighting and readable text.

Text to image15 cr

FLUX.2 Flex

Generate detailed compositions and typography with adjustable image size.

Text to image15 cr

FLUX.2 Flex Edit

Edit compositions and typography while keeping adjustable image size.

Edit image15 cr

Ideogram Character

Generate images from a character reference with consistent identity.

Edit image15 cr

Ideogram Character Remix

Remix a scene while keeping a referenced character consistent.

Edit image15 cr

Ideogram Character Edit

Edit a scene while keeping a referenced character consistent.

Edit image15 cr

Ideogram V3

Typography, graphics and poster-style image generation.

Text to image15 cr

Ideogram V3 Remix

Remix an image into new typography, graphics and layouts.

Edit image15 cr

Ideogram V3 Edit

Controlled edits for typography, graphics and poster layouts.

Edit image15 cr

Marketing Brand Studio

Paste your website. We read your brand and products, then make finished static ads — image, headline and call to action — for every product in one run.

Edit image

Marketing Studio

Pick a template or describe a shot, add your product, and get product photos, ads, posters, marketplace images and short video ads that keep your product exact.

Edit image

Playlist Video

Gather your tracks into a playlist and turn it into one continuous video — cover art and moving visuals for every song, ready for a channel or a stream.

Edit image

Cinematic Website Studio

Describe the page and drop in your photos: it builds a full cinematic website with a film in the hero, scroll animation and exportable HTML.

Edit image

Influencer Studio

Build an AI influencer from 19 kinds of choices, or start from a photo. You get a Character ID sheet that keeps the same face in every image and video.

Edit image

Long-form Video

Write the story once: it is broken into a storyboard, every shot keeps the same faces and places, and the scenes are rendered and cut into one long video.

Edit image

Music to Video

Bring a track and get a music video that runs its whole length — scenes cut to the beat, with a consistent look from the first bar to the last.

Edit image

Trend Analyzer

See what is taking off in your niche today, measured from real sources, with a ready post, campaign or article brief for each trend.

Analyze

LoRA Chaining

Combine several LoRAs in one run — your trained face with a style from the library and your product — and set how strongly each one pulls.

Edit image

Character ID

One face and body, held in every image and video. Makes one reference sheet and saves it as an ID — type its @handle in any prompt.

Edit image30 cr

Object ID

A product or prop that keeps its shape, colour and finish. Makes one reference sheet and saves it as an ID — type its @handle in any prompt.

Edit image30 cr

Location ID

A place that keeps its layout, light and mood across shots. Makes one reference sheet and saves it as an ID — type its @handle in any prompt.

Edit image30 cr

Outfit ID

A look — garments, fabric and accessories — reused on anyone. Makes one reference sheet and saves it as an ID — type its @handle in any prompt.

Edit image30 cr

ElevenLabs Music v2.5

Licensed songs and instrumentals, 3 seconds to 10 minutes.

Text to music80 cr

ChatGPT 2.5 Flare

Fast, detailed images and consistent creative edits.

Text to image15 cr

ChatGPT 2.5 Sunburst

Careful detail and precise control for polished visual work.

Text to image15 cr

ChatGPT 2.5 Flare Edit

Fast, detailed images and consistent creative edits.

Edit image15 cr

ChatGPT 2.5 Sunburst Edit

Careful detail and precise control for polished visual work.

Edit image15 cr

Mureka V9.5 Song

Full songs with vocals, written to your lyrics.

Text to music30 cr

Mureka V9.5 BGM

Instrumental background music from a short brief.

Text to music30 cr

Gemini Omni Flash 1.1

Fast video with native audio from a text prompt — now to 4K on Ultra Fast

Text to video40 cr

Gemini Omni Flash 1.1 (Reference)

Multi-reference video with native audio from your images

Reference to video40 cr

Gemini Omni Flash 1.1 Edit

Edit existing video with plain-language instructions

Video to video110 cr

Recraft V4 Styles

Instant style from your references

Text to image15 cr

Recraft V4 Styles Pro

Premium tier, same instant style

Text to image15 cr

Recraft V4 Styles Vector

Scalable SVG in your style

Text to image15 cr

Recraft V4 Styles Vector Pro

Publication-grade SVG, locked style

Text to image20 cr

FIBO Edit 1.5

Combine up to 4 images in one instruction

Edit image15 cr

Flux 3 Video

FLUX 3 super-resolution to 1080p, 2K, or 4K

Upscale video35 cr

Hi3D 3.0 — From Image

Very high-resolution textured 3D models. From one picture.

Image to 3D265 cr

MiniMax Music 3.0

Songs with vocals from a prompt, with or without your lyrics.

Text to music20 cr

Flux 3

Frontier video with native synchronized audio

Image to video110 cr

Seedance 2.5

Half-minute cinematic video with native synced audio

Text to video75 cr

Seedance 2.5 (Reference)

Up to 50 references — images, video and audio

Reference to video75 cr

A vintage television plays a felt-style owl animation beside an embroidered hoop of the same owl.

Illustration

MiniMax H3 Text→Video

Create with a compatible LoRA for MiniMax H3 Text→Video.

Generate with a LoRA85 cr

A picture frame on a stone windowsill animates a woodblock lighthouse beside its original still print.

Illustration

MiniMax H3 Image→Video

Create with a compatible LoRA for MiniMax H3 Image→Video.

Generate with a LoRA85 cr

MiniMax H3 First+Last Frame

Create with a compatible LoRA for MiniMax H3 First+Last Frame.

Generate with a LoRA85 cr

MiniMax H3 Reference→Video

Create with a compatible LoRA for MiniMax H3 Reference→Video.

Generate with a LoRA85 cr

A paper-cut heron flies over a glowing layered paper river valley in indigo and saffron tones.

Illustration

MiniMax H3 Text→Video

Text→video LoRA — train from clips, then generate straight from a prompt.

Train a LoRA

Dandelion seeds drift out of a framed meadow photograph hanging on a sage-green wall.

Illustration

MiniMax H3 Image→Video

Image→video LoRA — train from clips, then animate a still photo.

Train a LoRA

A red paper square folds step by step into an origami crane across a dark teal table.

Illustration

MiniMax H3 First+Last Frame

First/last-frame LoRA — train the motion that carries one still into another.

Train a LoRA

A beekeeper in a white veil walks through a lavender field at dusk, trailing smoke.

Illustration

MiniMax H3 Reference→Video

Reference LoRA — train on clips, then compose a shot from up to 9 reference images.

Train a LoRA

Lyria 3.5

Songs up to three minutes, with vocals or instrumental.

Text to music15 cr

HappyHorse 1.1

Cinematic video with native synchronized audio

Text to video95 cr

HappyHorse 1.1 (Reference)

Consistent video from up to 9 reference images

Reference to video95 cr

Sonilo Text to Music

Text to music

Text to music15 cr

Kling 3.0 Turbo

Multi-shot cinematic video with native audio

Text to video35 cr

Photo Humanizer

Reads the photo first, then removes the plastic AI look — skin, light and lens — in one pass.

Edit image20 cr

A hand fans out illustrated cards showing the same watercolour hedgehog in different poses.

Illustration

Ideogram 4.0

Create with a compatible LoRA for Ideogram 4.0.

Generate with a LoRA20 cr

Hands lift a fresh coral and teal emblem poster in a print studio, with matching posters behind.

Illustration

Ideogram 4.0

Poster, logo and typography trainer — the one engine that renders text properly.

Train a LoRA

Seedance 2.0 Mini

Budget multimodal video with native audio & physics

Text to video20 cr

Seedance 2.0 Mini (Reference)

Multi-reference video from images, video & audio

Reference to video20 cr

Rodin 2.5 — From Image

Production-ready textured 3D models with clean topology. From one picture.

Image to 3D55 cr

Rodin 2.5

Production-ready textured 3D models with clean topology. From a prompt.

Text to 3D55 cr

Rodin 2.5 Fast — From Image

Quick, light textured 3D models. From one picture.

Image to 3D15 cr

Rodin 2.5 Fast

Quick, light textured 3D models. From a prompt.

Text to 3D15 cr

Gemini Omni Flash

Fast video with native audio from a text prompt

Text to video40 cr

Gemini Omni Flash (Reference)

Multi-reference video with native audio from your images

Reference to video40 cr

Gemini Omni Flash Edit

Edit existing video with plain-language instructions

Video to video110 cr

Three skateboard decks against a sunny wall, each painted with the same snow leopard in different poses.

Illustration

Krea 2 Turbo

Create with a compatible LoRA for Krea 2 Turbo.

Generate with a LoRA20 cr

Close-up portrait of a weathered elderly fisherman in warm harbour light, skin detail razor sharp.

Illustration

Krea 2 Turbo

Sharp photoreal trainer — crisp skin, lighting & fine detail.

Train a LoRA

GPT Image 2

OpenAI's latest — sharper, smarter

Text to image15 cr

Precise Edit

Precise · complex briefs, clean results

Edit image15 cr

Music Video Generator

Your song and a photo — a full-length music video

Image to video15 cr

MiniMax Music

Studio-grade vocals from a reference song

Reference to music15 cr

MiniMax Music Cover

Re-sings a song in a new style.

Reference to music20 cr

Wan 2.7

Next-gen synthesis with native audio & sharper motion

Text to video25 cr

Wan 2.7 (Image)

First & last frame plus video continuation, up to 15s

Image to video25 cr

Wan 2.7 Reference

Combine up to 5 references into a new guided video

Reference to video25 cr

Wan 2.7 Video Edit

Restyle existing clips with prompt & reference image

Video to video25 cr

Lyria 3 Pro

Rich instrumentals and songs from a prompt.

Text to music15 cr

LTX-2.3 Character

Create with a compatible LoRA for LTX-2.3 Character.

Generate with a LoRA30 cr

Children in a dusk garden watch a paper-cut hummingbird animation projected onto a bedsheet between trees.

Illustration

LTX-2.3 Motion

Create with a compatible LoRA for LTX-2.3 Motion.

Generate with a LoRA30 cr

A man in a yellow raincoat leaps over a puddle on a wet cobblestone street at dusk.

Illustration

LTX-2.3 Character

Our latest & best video trainer — put your face or character into motion.

Train a LoRA

A split image shows a toy car's low tracking shot mirrored by a real car on a coastal road.

Illustration

LTX-2.3 Motion

Transfer camera moves & motion (V2V).

Train a LoRA

Kling 3.0 Animate Photo

Transfer motion from video to character image with identity

Video to video15 cr

Fast Edit

Fast · one sentence, done

Edit image15 cr

An editor compares two landscape photos, one with unnaturally repeating clouds.

Illustration

AI Image Detector

Estimates how likely a picture is to be AI-generated, with the visual signals behind the score.

Analyze15 cr

A paused interview with tracking points over the face, one cluster at the jaw glowing red.

Illustration

Deepfake Detector

Checks a face photo for swapping and manipulation, with the signals behind the score.

Analyze15 cr

A fact-checker points at one frozen, outlined news clip on a wall of screens.

Illustration

AI Video Detector

Estimates how likely a clip is to be AI-generated, from its frames and its motion.

Analyze20 cr

A young man in large headphones listens intently to a reel-to-reel tape in a dim sound booth.

Illustration

AI Voice Detector

Estimates how likely a recording is to be a synthetic voice or AI music.

Analyze20 cr

Recraft V4

Fast raster, great detail

Text to image15 cr

Recraft V4 Pro

Premium quality, up to 2048px

Text to image20 cr

Recraft V4 Vector

SVG vector output, scalable

Text to image15 cr

Recraft V4 Vector Pro

Premium SVG, max detail

Text to image20 cr

Seedance 2.0

Multimodal cinematic video with native audio & physics

Text to video60 cr

Seedance 2.0 (Reference)

Multi-reference video from images, video & audio clips

Reference to video60 cr

Real Film Grain

Adds camera sensor grain so a clean render reads as a photograph. Composition and colour stay as they are.

Edit image15 cr

Kling 3.0

Multi-shot storytelling with realistic physics & 4K

Text to video40 cr

Kling 3.0 (Image)

Multi-shot storytelling with realistic physics & 4K

Image to video40 cr

Kling O3

Omni model with native audio, multi-shot & character elements

Text to video45 cr

Kling O3 (Image)

Omni model with native audio, multi-shot & character elements

Image to video45 cr

Kling O3 Video Edit

Latest Omni model with elements & shot type

Video to video55 cr

A photo editor holds a print up to a bright window, inspecting it, with one print set aside face-down.

Illustration

Image Moderator

Flags sexual content, minors, violence, hate and harassment in a picture before you publish it.

Analyze15 cr

A film archivist in a dim projection booth carefully inspects a strip of film against a glowing lightbox.

Illustration

Video Moderator

Flags sexual content, minors, violence, hate and harassment anywhere in a clip.

Analyze15 cr

A woman in a theatre seat carefully marks passages in a printed script with a red pencil.

Illustration

Text Moderator

Flags sexual content, minors, violence, hate and harassment in a caption, comment or script.

Analyze15 cr

Three framed gouache prints of the same paper crane in one style hang on a teal café wall.

Illustration

FLUX.2 Klein 9B

Create with a compatible LoRA for FLUX.2 Klein 9B.

Generate with a LoRA20 cr

A gallery print of a tram blending woodblock, watercolour and stained-glass styles in one image.

Illustration

FLUX.2 Klein 9B

Open-weight FLUX trainer — strong style transfer, up to 3 stacked styles.

Train a LoRA

Veo 3.1 4K

Upscale a Veo 3.1 video to stunning 4K resolution

Text to video90 cr

A hand places a painted tile into a grid of tiles showing the same blue octopus.

Illustration

Qwen Image 2512

Create with a compatible LoRA for Qwen Image 2512.

Generate with a LoRA20 cr

A knitted russet fox toy sits on a mossy log in a misty forest, every stitch sharp.

Illustration

Qwen Image 2512

Strong prompt adherence & fine detail.

Train a LoRA

60fps Smoother

Fills in the frames between your frames for smooth motion, then rebuilds the clip at the size you pick.

Upscale video20 cr

Video Face Swap

Replaces the face in the clip with the face from your photo. Body, clothes, motion, framing and sound stay as they are.

Edit video15 cr

Join Clips

Joins two to ten clips into one video, in the order you add them.

Edit video20 cr

Add Audio

Lays a music, voice or sound track over a clip — mixed in, or replacing its own sound.

Edit video15 cr

Images to Reel

Turns two to twenty photos into a reel with transitions, in the order you add them. Music is optional.

Edit video20 cr

Auto Captions

Transcribes the speech in a clip and burns timed captions onto it.

Edit video25 cr

Video to GIF

Cuts a looping GIF from any stretch of a clip.

Edit video15 cr

Convert Video

Re-encodes a clip into another container — MP4, WebM, MOV, MKV or AVI.

Edit video15 cr

Denoise Video

Removes grain and sensor noise from a clip while keeping its frames and timing.

Edit video20 cr

A hand holds a phone upright showing a full-screen vertical clip of a surfer riding a turquoise wave.

Illustration

Reel Cutter

Finds the moments in a long video that stand on their own and cuts them into vertical, captioned reels.

Edit video200 cr

Kling O1

First & last frame keyframe animation, 5 or 10s

Image to video45 cr

Kling O1 Video Edit

Transform source video with character & style refs

Video to video65 cr

Chatterbox Turbo

Sub-150ms TTS with instant clone

Text to speech15 cr

Z-Image Turbo

Create with a compatible LoRA for Z-Image Turbo.

Generate with a LoRA20 cr

A hand fans out sharp photo prints showing the same corgi in five different settings.

Illustration

Z-Image Turbo

Our latest & best image trainer — fast, sharp, recommended.

Train a LoRA

Flux 2 Pro

Top-tier detail & creativity

Text to image15 cr

Magic Pose Changer

Wrong pose kills the shot. Fix it. Keep the face.

Edit image15 cr

Bytedance Video

Smart presets, SD→HD→4K

Upscale video30 cr

Image Upscaler

Rebuilds detail as it enlarges. Reaches 16K and handles photos, art and screenshots.

Upscale image15 cr

Video Enhancer

Diffusion rebuild, up to 2048p.

Upscale video20 cr

Crystal Upscaler

Portrait specialist, face detail

Upscale image35 cr

Veo 3.1

Cinematic scenes with dialogue & lip-synced audio

Text to video70 cr

Veo 3.1 (Image)

Cinematic scenes with dialogue & lip-synced audio

Image to video70 cr

Veo 3.1 Extend

Extend a Veo 3.1 video with new scenes & audio

Text to video70 cr

Veo 3.1 1080p

Upscale a Veo 3.1 video to crisp 1080p resolution

Text to video35 cr

FlashVSR

Fastest, cheapest video upscaler

Upscale video30 cr

Qwen 3 TTS

Multilingual w/ zero-shot cloning

Text to speech15 cr

A potted lemon tree split down the middle, dull overcast light on one side, warm golden sunset on the other.

Illustration

Qwen Edit 2509

Edit a photo with a compatible LoRA for Qwen Edit 2509.

Generate with a LoRA20 cr

A split photo of a green bicycle against a terracotta wall, dull overcast on the left, golden sunlight on the right.

Illustration

Qwen Edit 2509

Teach custom photo-editing operations.

Train a LoRA

Stable Audio 2.5

Sound design & instrumental beds, up to 190s

Text to music30 cr

Nano Banana 2

Reference-guided text-to-image accepting up to 14 source images, at 1K, 2K or 4K.

Text to image15 cr

Nano Banana Pro

Pro-tier reference-guided generation and image-to-image at 1K, 2K or 4K.

Text to image15 cr

Nano Banana Lite

Budget multi-reference image generation at a fixed 1K output.

Text to image15 cr

ElevenLabs Music

Premium music with section-level composition control

Text to music80 cr

Bold Create

Expressive text-to-image with crisp lettering and selectable 1K or 2K output.

Text to image15 cr

Grok Imagine Edit

Precision edits · up to 5 references

Edit image15 cr

Bold Video

Ship the clip before the idea cools

Text to video15 cr

Bold Video (Image)

Still images sit. Moving ones sell.

Image to video15 cr

An open picture book shows the same painted copper robot on both pages, resting on a sunny window seat.

Illustration

WAN 2.2 Image

Create with a compatible LoRA for WAN 2.2 Image.

Generate with a LoRA20 cr

A thumb flips a small flip book showing a clay-style blue whale leaping, pages blurred in motion.

Illustration

WAN 2.2 Video

Create with a compatible LoRA for WAN 2.2 Video.

Generate with a LoRA70 cr

A hand tilts a lenticular card showing a linocut hare leaping, above its original still print.

Illustration

WAN 2.2 Image→Video

Create with a compatible LoRA for WAN 2.2 Image→Video.

Generate with a LoRA70 cr

A woman in a yellow raincoat stands on a foggy mountain train platform at dawn.

Illustration

WAN 2.2 Image

Cinematic, high-detail look.

Train a LoRA

A flamenco dancer in a red dress spins on a lantern-lit plaza, her skirt blurred with motion.

Illustration

WAN 2.2 Video

Text→video LoRA (14B) — train from clips and/or photos. Best for cinematic motion.

Train a LoRA

A hand holds an instant photo of an ocean wave whose water spills out beyond the photo's edge.

Illustration

WAN 2.2 Image→Video

Image→video LoRA (14B) — train from video clips for animate-from-photo.

Train a LoRA

SeedVR2

Best value, high-quality 4x upscale

Upscale image30 cr

SeedVR2 Video

Upscale video

Upscale video30 cr

ElevenLabs v3

Flagship naturalness, emotion & pacing

Text to speech15 cr

Flux Kontext Pro

Edit & generate, versatile

Text to image15 cr

Flux Kontext Max

Premium edit, max quality

Text to image15 cr

Dia TTS

Multi-speaker dialogue + nonverbals

Text to speech15 cr

Google Lyria 2

Licensed training data — safest for commercial use

Text to music15 cr

MiniMax Speech 02 HD

300+ voices, 30+ languages, emotion presets

Text to speech15 cr

Topaz Image

Gold standard, specialist AI models

Upscale image40 cr

Topaz Video

Pro AI video upscale, specialist models

Upscale video30 cr

MMAudio V2

Soundtrack synced to your video

Video to music15 cr

Recraft Crisp

Best for text, logos & products

Upscale image30 cr

Hands hold up a painted print of a fox in a yellow raincoat, with matching prints behind.

Illustration

FLUX.1 Dev

Create with a compatible LoRA for FLUX.1 Dev.

Generate with a LoRA20 cr

A bearded man holds a painted portrait of himself beside his face in a sunlit loft.

Illustration

FLUX.1 Dev

Best all-rounder for faces, products & styles.

Train a LoRA

AuraSR v2

Fast 4x with tiled processing

Upscale image30 cr

Clarity Upscaler

Prompt-guided, most params

Upscale image45 cr

ESRGAN

Classic upscaler, 6 model variants

Upscale image30 cr