Which models are included with Maker, and which still use credits?

Hunyuan 3D V3.1 Rapid Image to 3D

Fast 3D model generation from images.

Hunyuan 3D V3.1 Rapid Text to 3D

Fast 3D model generation from text descriptions.

Hunyuan 3D V3.1 Segment Model

Split a 3D model into separate parts. Only FBX format is supported. Max 100MB, <=30,000 faces.

Hunyuan Motion

Generate 3D motion animations from text prompts using Tencent Hunyuan Motion.

Hunyuan Motion Fast

Generate 3D motion animations quickly from text prompts using Tencent Hunyuan Motion Fast.

Image to 3D

Generate a 3D model from a single image (optionally with textures).

Image to 3D

Generate a 3D model from a single image.

Multi-Image to 3D

Generate a 3D model from 1-4 images, with Meshy 6 controls for remeshing, texturing, and output options.

Multiview to 3D

Generate a 3D model from 1–4 images (front, left, back, right). Front is required.

Refine Model

Refine a draft model (for older versions; not supported for v2.0+).

Text to 3D

Generate a 3D model from text.

Text to 3D (Preview)

Generate a base mesh (no textures) from text. Useful to evaluate geometry.

Text to 3D (Refine)

Texture a preview mesh to produce a textured 3D model.

Cover Song

Create a cover of an existing song.

Extend Song

Extend an existing song.

Get Full Song

Concatenate song parts into a full track.

Kling Create Voice

Create a reusable Kling custom voice ID from a clean 5-30 second audio sample.

Lyria 2

Generate music using Google's Lyria 2 text-to-music model with high-quality 48kHz WAV output.

Lyria 3 Clip

Generate 30-second music clips using Google Lyria 3.

Lyria 3 Pro

Generate full-length songs using Google Lyria 3 Pro.

Music (Compose)

Compose a song from a prompt or a composition plan.

Pixio Music

AI Music Generator

Songcraft

Generate music using Songcraft (Suno).

Sound Effects

Turn text into sound effects for videos, voice-overs, or games.

Split Stems

Separate vocals and instrumental from a song.

Text to Dialogue

Generate dialogue from multiple speakers using ElevenLabs.

Text to Speech

Convert text to speech using ElevenLabs.

Voice Clone (IVC)

Create a voice clone and add it to your ElevenLabs voices.

Advanced Face Swap

Swap faces in images with advanced controls.

Base

Generate an image using Bria Base

Dreamina v3.1

Generate images using Bytedance's Dreamina 3.1 model.

Edit (V3)

Edit an image with a mask using Ideogram 3.0.

Face Restoration

Restore, enhance, and unblock faces in images. Fixes blur, low resolution, and censored faces using AI face reconstruction.

Fashion Photoshoot

Generate a fashion photoshoot.

Fashn Tryon v1.6

Try-on images using Fashn-s try-on model v1.6.

Fast

Generate an image using Bria Fast

Flux 2

Text-to-image generation with LoRA support for FLUX.2 [dev] from Black Forest Labs.

Flux 2 Edit

Image-to-image editing with LoRA support for FLUX.2 [dev] from Black Forest Labs.

Flux 2 Flash

Generate images with Flux 2 Flash from Black Forest Labs.

Flux 2 Flash Editing

Edit images with Flux 2 Flash from Black Forest Labs.

Flux 2 Flex

Flexible, high-quality text-to-image generation with Flux 2 Flex.

Flux 2 Flex Edit

Edit images with Flux 2 Flex from Black Forest Labs.

Flux 2 Klein 4B

Text-to-image generation with LoRA support for FLUX.2 [klein] 4B Base from Black Forest Labs.

Flux 2 Klein 4B Edit

Image-to-image editing with LoRA support for FLUX.2 [klein] 4B Base from Black Forest Labs.

Flux 2 Klein 9B

Text-to-image generation with LoRA support for FLUX.2 [klein] 9B Base from Black Forest Labs.

Flux 2 Klein 9B Edit

Image-to-image editing with LoRA support for FLUX.2 [klein] 9B Base from Black Forest Labs.

Flux 2 Max

Generate high-quality images with Flux 2 Max from Black Forest Labs.

Flux 2 Max Edit

Edit images with Flux 2 Max from Black Forest Labs.

Flux 2 Pro

Generate images with Flux 2 Pro from Black Forest Labs.

Flux 2 Pro Edit

Edit images with Flux 2 Pro from Black Forest Labs.

Flux 2 Turbo

Generate images with Flux 2 Turbo from Black Forest Labs.

Flux 2 Turbo Editing

Edit images with Flux 2 Turbo from Black Forest Labs.

Flux Dev

A fast, high-quality text-to-image model.

Flux Dev Inpainting

Inpaint an image using Flux Dev

Flux Krea

A next-generation text-to-image model.

Flux Pro

A faster, higher-quality text-to-image model.

Flux Pro Fill

Next generation inpainting/outpainting model.

Flux Pro Fill Finetuned

Flux Pro Fill with custom fine-tuned models.

Flux Pro Ultra

A next-generation text-to-image model with accelerated speeds.

Flux Pro Ultra Finetuned

Flux Pro Ultra with custom fine-tuned models.

Flux Schnell

Turbo mode for the next-generation text-to-image model FLUX.

Flux SRPO

FLUX.1 [srpo], next generation text-to-image model.

Generate (V3)

Generate an image from a prompt; supports character/style reference images.

GPT Image 1

Generate images with OpenAI GPT-Image-1.

GPT Image 1 (mini)

Faster, cheaper image generation.

GPT Image 1 (mini) Edit

Maskless image edit or composition (mini).

GPT Image 1 Edit

Edit or compose images with GPT Image 1 (multi-image, maskless).

GPT Image 1.5

Generate images with OpenAI GPT-Image-1.5.

GPT Image 1.5 Edit

Edit or compose images with GPT Image 1.5 (multi-image, maskless).

GPT Image 2

GPT Image 2 via Fal.ai — detailed images with fine typography (OpenAI's latest image stack on Fal).

GPT Image 2 Edit

Fine-grained image edits with GPT Image 2 on Fal.ai — reference images plus optional inpaint mask.

Grok Imagine Image Edit

Edit an image based on a text description using Grok Imagine.

Grok Imagine Text-to-Image

Generate an image based on a text description using Grok Imagine.

HD

Generate an image using Bria HD

Hunyuan Image V3

Generate high-quality images using Tencent Hunyuan Image V3.

Image 01

Generate images from text prompt using MiniMax API.

Image 01 Subject Reference

Generate images from text prompt with subject reference using MiniMax API.

Imagen 4

Generate images using Google's Imagen 4 model.

Imagen 4 Fast

Generate images using Google's Imagen 4 fast model.

Imagen 4 Ultra

Generate images using Google's Imagen 4 Ultra model.

Kling O1 Image

Perform precise image edits with reference images and custom elements using Kling O1 Image.

Kling O3 Image to Image

Transform reference images with Kling Omni 3 while preserving high consistency.

Kling O3 Text to Image

Generate high-consistency images from text with Kling Omni 3.

Kling V3 Image to Image

Transform images with the latest Kling Image V3 model.

Kling V3 Text to Image

Generate images with the latest Kling Image V3 model.

Kontext Max

Frontier image generation model.

Kontext Max Editing

FLUX.1 Kontext [Max] -- Frontier image editing model.

Kontext Max Editing Multi

Experimental version of FLUX.1 Kontext [Max] with multiple images.

Kontext Pro

Frontier image generation model.

Kontext Pro Editing

FLUX.1 Kontext [pro] -- Frontier image editing model.

Kontext Pro Editing Multi

Experimental version of FLUX.1 Kontext [pro] with multiple images.

Mystic

Ultra-realistic, high-resolution text-to-image generation.

Nano-Banana

Generate images using Gemini 2.5 Flash Image.

Nano-Banana 2

Generate images using Gemini 3.1 Flash Image.

Nano-Banana 2 Edit

Edit images using Gemini 3.1 Flash Image.

Nano-Banana Edit

Edit multiple images using Gemini 2.5 Flash Image.

Photo Restoration

Restore old or damaged photos with resolution, color, and scratch fixes.

PixCraft Edit (Buttons)

Execute PixCraft buttons (Upscale, Variations, Zoom, Animate, Extend, etc.) on a previous job.

PixCraft Image

Generate an image via PixCraft. Optionally include a reference image, set aspect ratio, and use Raw mode.

Pixio Image Edit

AI Image Editor

Qwen Image

LoRA inference for Qwen Image 2512 with improved text rendering and more realistic human generation.

Qwen Image 2

Generate images from text using Qwen Image 2.

Qwen Image 2 Edit

Edit images using Qwen Image 2.

Qwen Image Edit

Endpoint for Qwen's Image Editing 2511 model with LoRA support.

Qwen Image Max

Generate images from text using Qwen Image Max.

Qwen Image Max Edit

Edit images using Qwen Image Max.

Qwen-Image Edit Plus

Generate edited images with the Qwen Image Edit Plus model.

Qwen-Image Edit Plus Lora

Generate edited images with the Qwen Image Edit Plus model using multiple LoRAs.

Recraft V2

Recraft V2

Recraft V3

Recraft V3

Recraft V3 Vectorize

Recraft V3 Vectorize

Recraft V4

Recraft V4 text-to-image generation.

Reframe (V3)

Extend a square image to a chosen resolution.

Relight

Relight an image by transferring lighting from a reference or lightmap with style options.

Remix (V3)

Remix an input image guided by a prompt.

Replace Background (V3)

Replace the background of an image while keeping the foreground subject.

Restyle

Style transfer an image using AI, guided by a reference image. Portrait-focused options available.

Reve

Create images from a text description using Reve.

Reve Edit

Edit an image based on a text description using Reve.

Reve Fast Edit

Edit an image based on a text description using Reve's fast model.

Reve Fast Remix

Remix images by combining text prompts with reference images using Reve's fast model.

Reve Remix

Remix images by combining text prompts with reference images using Reve.

Riverflow 2.0 Fast

Agentic image model optimized for high-quality, fast generations supporting font control.

Runway Gen-4 (References → Image)

Generate images from references (Gen-4 Turbo).

Runway Gen-4 (Text → Image)

Generate images (Gen-4).

Sana Base

Generate an image using Sana Base

Sana Sprint

Generate an image using Sana Sprint

Sana v1.5

Generate an image using Sana v1.5

Sana v1.5 fast

Generate an image using Sana v1.5 fast

SD 1.5

Generate an image using SD 1.5

SD 3 Medium

Generate an image using SD 3 Medium

SD 3 Medium Image to Image

Generate an image from an image using SD 3 Medium

SD 3.5 Large

Generate an image using SD 3.5 Large

SD 3.5 Medium

Generate an image using SD 3.5 Medium

SDXL

Generate an image using SDXL

SDXL Image to Image

Generate an image from an image using SDXL

SDXL Inpainting

Inpaint an image using SDXL

Seedream 5

Generate images using Bytedance's Seedream 5.0 Lite model.

Seedream 5 Edit

Edit images using Bytedance's Seedream 5.0 Lite model.

Seedream v4

Generate images using Bytedance's Seedream 4 model.

Seedream v4 Edit

Edit images using Bytedance's Seedream 4 model.

Seedream v4.5

Generate images using Bytedance's Seedream 4.5 model.

Seedream v4.5 Edit

Edit images using Bytedance's Seedream 4.5 model.

Upscale

Upscale an image.

Virtual Try On

Virtually try on clothes.

WAN 2.5 Text to Image

Generate images from text using WAN 2.5 text-to-image model.

WAN 2.6 Image to Image

Edit images using 1-3 reference images with WAN 2.6.

WAN 2.6 Text to Image

Generate images from text with optional reference image guidance using WAN 2.6.

WAN 2.7 Text to Image

Generate images from text using WAN 2.7.

WAN v2.2 Text to Image

Generate an image from text prompt.

Add Audio to Video

Replace or mix an audio track onto a video (combine audio + video).

Black Bar Crop

Remove black bars and crop a video using Seedance 2 generation

Caption Video

Automatically generates burned-in captions for a video with customizable font, color, alignment, and refresh interval.

Extract First Frame

Extract the first frame from a video as an image

Extract Frame at Time

Extract a single PNG frame from a video at a chosen timestamp.

Extract Last Frame

Extract the last frame from a video as an image

Gen-4 Maker

Gen-4 image-to-video (Maker Explore queue). Requires first frame; 5s or 10s; 720p.

Gen-4 Turbo Maker

Gen-4 Turbo image-to-video (Maker Explore queue). Faster; requires first frame; 5s or 10s; 720p.

Gen-4.5 Maker

Gen-4.5 text-to-video (Maker Explore queue). 2–10s; optional reference image and end frame; up to 5000 characters.

Grok Imagine Image-to-Video

Generate a video based on an image using Grok Imagine.

Grok Imagine Text-to-Video

Generate a video based on a text description using Grok Imagine.

Grok Imagine Video Edit

Edit a video with a text prompt using Grok Imagine (up to 8 seconds). Use 480p or 720p video; larger frames are not supported.

Hunyuan Video Image to Video

Generate videos from an input image and text prompt using Tencent Hunyuan Video.

Hunyuan Video Text to Video

Generate videos from text using Tencent Hunyuan Video with LoRA support.

Hunyuan Video to Video

Transform existing videos using Tencent Hunyuan Video with LoRA support.

Kling 2.6 I2V Maker

Kling 2.6 image-to-video (Maker Explore queue). Requires one reference image; 5s or 10s.

Kling 2.6 Pro Maker

Kling 2.6 Pro text-to-video (Maker Explore queue). 5s or 10s; optional reference image.

Kling 3.0 Motion Control Maker

Kling 3.0 Motion Control (Maker Explore queue). Motion transfer: one character image and one performance video (3–30s). Resolution std/pro maps to 720p/1080p.

Kling 3.0 Pro Maker

Kling 3.0 Pro (Maker Explore queue). 5–15s; up to 2 reference images; optional end frame; multishot not exposed in this form yet.

Kling 3.0 Standard Maker

Kling 3.0 Standard (Maker Explore queue). Same limits as Pro at a lower list rate.

Kling Effects

Generate a video from an image using Kling special effects. Effects are loaded dynamically.

Lipsync 1.9

Fast legacy lipsync for simple videos. Best for quick, basic lip synchronization.

LTX 2 Fast Extend Video

Extend videos with text prompts using LTX 2 distilled model.

Merge Videos

Merge multiple videos into a single video

OmniHuman v1.5

Generate videos of humans speaking from an image and audio.

Pika v1.5 Pikaffects

Pika Pikaffects Generation.

Pika v2 Turbo Image to Video

Pika Turbo Image-to-Video Generation.

Pika v2 Turbo Text to Video

Pika Turbo Text-to-Video Generation.

Pika v2.1 Image to Video

Pika 2.1 Image-to-Video Generation.

Pika v2.1 Text to Video

Pika 2.1 Text-to-Video Generation.

Pika v2.2 Image to Video

Pika 2.2 image-to-video: animate a still image into video. Resolution 720p or 1080p; duration 5 or 10 seconds.

Pika v2.2 Pikascenes

Pika 2.2 Pikascenes Generation.

Pika v2.2 Text to Video

Pika 2.2 text-to-video: text-to-image then image-to-video. Resolution 720p or 1080p; duration 5 or 10 seconds.

PixCraft Video

Generate a short video from a starting image. Supports motion amount, looping, custom end frame, batch size, and Raw mode.

PixVerse v6 Extend

Extend an existing video using PixVerse v6 via Fal (1–15s, optional audio).

PixVerse v6 Image to Video

Animate an image into a video using PixVerse v6 via Fal (1–15s, optional audio and multi-clip).

PixVerse v6 Text to Video

Generate videos from text using PixVerse v6 via Fal (1–15s, optional audio and multi-clip).

PixVerse v6 Transition

Transition between two images using PixVerse v6 via Fal (1–15s, first frame required, optional last frame).

Ray 2 Flash Image to Video

Generate a video from an image using Luma Ray 2 Flash.

Ray 2 Flash Modify

Modify a video with Luma Ray 2 Flash.

Ray 2 Flash Reframe

Reframe a video with Luma Ray 2 Flash.

Ray 2 Flash Text to Video

Generate a video from text using Luma Ray 2 Flash.

Ray 2 Image to Video

Generate a video from an image using Luma Ray 2.

Ray 2 Modify

Modify a video with Luma Ray 2.

Ray 2 Reframe

Reframe a video with Luma Ray 2.

Ray 2 Text to Video

Generate a video from text using Luma Ray 2.

Runway Act Two (Character)

Character performance (control character only).

Runway Gen-3a Turbo

Image → Video (Gen-3a Turbo).

Runway Gen-4 Aleph

Video → Video (transform).

Runway Gen-4 Turbo

Image → Video (Gen-4 Turbo).

Seedance 2 Maker

Bytedance Seedance 2.0 for Maker. Priced at Seedance Preview VIP rates by resolution (480p / 720p). Credit Mode ON: full VIP price, no Runway explore queue. Credit Mode OFF: explore queue with 30% off VIP list. First 5 generations per 24h are free — after that, VIP credits apply. Multi-ref: up to 11 images + 3 videos, or keyframe start/end. Use @IMG_1…@IMG_11 and @VID_1…@VID_3. Up to 3500 characters.

Seedance v1 Lite Image to Video

Generate videos from an image and text using Bytedance's Seedance 1.0 Lite model.

Seedance v1 Lite Reference to Video

Generate videos from a reference image and text using Bytedance's Seedance 1.0 Lite model.

Seedance v1 Lite Text to Video

Generate a video from text using Bytedance's Seedance 1.0 Lite model.

Seedance v1 Pro Fast Image to Video

Generate videos from an image and text quickly using Bytedance's Seedance 1.0 Pro Fast model.

Seedance v1 Pro Fast Text to Video

Generate videos from text quickly using Bytedance's Seedance 1.0 Pro Fast model.

Seedance v1 Pro Image to Video

Generate videos from an image and text using Bytedance's Seedance 1.0 Pro model.

Seedance v1 Pro Text to Video

Generate a video from text using Bytedance's Seedance 1.0 Pro model.

Trim Video or Audio

Trim a video or audio file to a selected time range (FFmpeg). Output keeps the same format family.

Veo 3.1 Lite Preview (First & Last Frame)

First-to-last frame interpolation via Gemini API veo-3.1-generate-preview. Duration is fixed at 8 seconds (API requirement for interpolation). Native audio; ~1,024-token prompts; 16:9 or 9:16; 720p or 1080p. Docs: https://ai.google.dev/gemini-api/docs/video · Pricing: https://ai.google.dev/gemini-api/docs/pricing#veo-3.1

Veo 3.1 Lite Preview (Image to Video)

Animate a starting image with Veo 3.1 Lite Preview (Gemini API veo-3.1-lite-generate-preview): efficient, programmable image-to-video with native audio. Prompts up to about 1,024 tokens; 16:9 or 9:16; 720p or 1080p (1080p is 8 seconds only). No 4K, no video extension, and no reference-image workflow on Lite. Docs: https://ai.google.dev/gemini-api/docs/video · Pricing: https://ai.google.dev/gemini-api/docs/pricing#veo-3.1

Veo 3.1 Lite Preview (Text to Video)

Veo 3.1 Lite Preview is a high-efficiency, developer-friendly video model: high-fidelity clips with natively generated audio, powered by the Gemini API model veo-3.1-lite-generate-preview. Text prompts up to about 1,024 tokens; 16:9 or 9:16; 720p or 1080p (1080p is 8 seconds only). Lite does not support 4K output, video extension, or reference-image mode. Docs: https://ai.google.dev/gemini-api/docs/video · Pricing: https://ai.google.dev/gemini-api/docs/pricing#veo-3.1 · Try: https://aistudio.google.com?model=veo-3.1-lite-generate-preview

Video Background Remover

Remove the background from a video using BiRefNet v2 with multiple quality and resolution options.

Vidu Q1 Image to Video

Transform a single image into a dynamic video with motion using the Q1 model.

Vidu Q1 Reference to Video

Generate a video with consistent subjects using reference images with the Q1 model (supports up to 7 images).

Vidu Q1 Start-End to Video

Generate a smooth transition video between start and end frames using the Q1 model.

Vidu Q1 Text to Video

Generate a video from text description using the Q1 model.

Vidu Q2 Image to Video Pro

Generate a high-quality video from a single image using the Vidu Q2 Pro model.

Vidu Q2 Image to Video Turbo

Generate a faster video from an image using the Vidu Q2 Turbo model.

Vidu Q2 Text to Video

Generate a video from text using the Vidu Q2 model.

Vidu Q2 Video Extension Pro

Extend an existing video using the Vidu Q2 Pro model.

Wan 2.2 Animate Maker

Wan 2.2 Animate (Maker Explore queue). One image + one driving video; no text prompt.

WAN 2.5 Image to Video

Generate a video from an image using WAN 2.5 image-to-video model.

WAN 2.5 Text to Video

Generate a video from text using WAN 2.5 text-to-video model.

Wan 2.6 Flash Maker

Wan 2.6 Flash text-to-video (Maker Explore queue). Requires one reference image; 5–15s; 720p/1080p.

WAN Animate Move

Generate a video from a video and an image (movement mode).

WAN Animate Replace

Generate a video from a video and an image (replace mode).

WAN Effects

Generate a video from an image using WAN Effects model.

WAN v2.2 Image to Video

Generate a video from an image using WAN v2.2 image-to-video model.

WAN v2.2 Text to Video

Generate a video from text using WAN v2.2 text-to-video model.

WAN v2.2 Video to Video

Generate a video from a video using WAN v2.2 video-to-video model.

WAN VACE Video Edit

Edits a video using plain language and the Wan 2.2 VACE Fun model.

Hunyuan 3D V3 Image to 3D

Generate 3D models from a single image.

Hunyuan 3D V3 Sketch to 3D

Transform sketch or line art images into 3D models.

Hunyuan 3D V3 Text to 3D

Generate 3D models from text descriptions.

Hunyuan 3D V3.1 Optimize Model

Optimize 3D model topology. Supports GLB and OBJ formats. Max 200MB.

Hunyuan 3D V3.1 Pro Image to 3D

Generate high-quality 3D models from images with multiple view support.

Hunyuan 3D V3.1 Pro Text to 3D

Generate high-quality 3D models from text descriptions.

Image to 3D · Tripo P1

Tripo P1 (model_version P1-20260311) targets low-poly 3D: clean topology and quick meshes—well suited to games, stylized props, mobile, and AR. It is not interchangeable with v3.0, v3.1 (H3.1), or Turbo: those models expose extra controls (quad remesh, smart low poly, part generation, geometry quality). P1 only accepts its documented parameters; unsupported fields are rejected by the API. Face count must stay between 48 and 20,000. Credits: 60 without textures, 80 with standard textures, 100 with detailed textures.

Image to 3D · Tripo v3.1 (H3.1)

Tripo v3.1 H3.1 (model_version v3.1-20260211): native Tripo 3D with separate texture and geometry quality and quad FBX remesh (+10 credits). Image and multiview tasks support smart low poly and part generation; text-to-model uses the slimmer OpenAPI shape. Not interchangeable with v3.0-20250812, Turbo, or P1. Multiview: front required plus at least one other view (order: front, left, back, right). Credits: 20 without textures, 70 with standard textures, 110 with detailed textures, +40 for detailed geometry, +10 for quad mesh. Uses Tripo API model_version v3.1-20260211 (H3.1)—not the same as the v3.0-20250812 option in the other Tripo generators.

Multiview to 3D · Tripo v3.1 (H3.1)

Tripo v3.1 H3.1 (model_version v3.1-20260211): native Tripo 3D with separate texture and geometry quality and quad FBX remesh (+10 credits). Image and multiview tasks support smart low poly and part generation; text-to-model uses the slimmer OpenAPI shape. Not interchangeable with v3.0-20250812, Turbo, or P1. Multiview: front required plus at least one other view (order: front, left, back, right). Credits: 20 without textures, 70 with standard textures, 110 with detailed textures, +40 for detailed geometry, +10 for quad mesh. Uses Tripo API model_version v3.1-20260211 (H3.1)—not the same as the v3.0-20250812 option in the other Tripo generators.

Text to 3D · Tripo P1

Tripo P1 (model_version P1-20260311) targets low-poly 3D: clean topology and quick meshes—well suited to games, stylized props, mobile, and AR. It is not interchangeable with v3.0, v3.1 (H3.1), or Turbo: those models expose extra controls (quad remesh, smart low poly, part generation, geometry quality). P1 only accepts its documented parameters; unsupported fields are rejected by the API. Face count must stay between 48 and 20,000. Credits: 60 without textures, 80 with standard textures, 100 with detailed textures.

Text to 3D · Tripo v3.1 (H3.1)

Tripo v3.1 H3.1 (model_version v3.1-20260211): native Tripo 3D with separate texture and geometry quality and quad FBX remesh (+10 credits). Image and multiview tasks support smart low poly and part generation; text-to-model uses the slimmer OpenAPI shape. Not interchangeable with v3.0-20250812, Turbo, or P1. Multiview: front required plus at least one other view (order: front, left, back, right). Credits: 20 without textures, 70 with standard textures, 110 with detailed textures, +40 for detailed geometry, +10 for quad mesh. Uses Tripo API model_version v3.1-20260211 (H3.1)—not the same as the v3.0-20250812 option in the other Tripo generators.

Trellis 2 Retexture

Retexture an existing 3D mesh from a reference image using Trellis 2.

Cohere Transcribe

Turn audio into searchable text with optional language, punctuation, and token limits.

Full Stem Separation

Separate all stems (vocals, drums, bass, etc.) from a song.

Mureka Create (Advanced)

Write lyrics and style, or use a reference track—not all options at once. Dimmed fields are unavailable with your current choices.

Mureka Create (AI Lyrics)

Create a song using AI-generated lyrics based on your prompt. Average ~45s per generation, returns two versions.

Mureka Create Instrumental

Instrumental from a written description, or from one reference (library or uploaded MP3)—not both. Optional title.

Music 1.5

Generate music from structured lyrics and a style prompt using MiniMax Music 1.5.

Music 2.5

Generate complete tracks with vocals and instrumentation from a style prompt and lyrics using MiniMax Music 2.5.

Music 2.6

Generate complete tracks with singing, backing music, and arrangements from lyrics and a style description (MiniMax Music 2.6).

Music Reference

Generate music from lyrics and a reference song using MiniMax Music.

Music V2

Generate music from a style/mood prompt and lyrics using Minimax Text To Music V2.

Speech 2.5 HD

Convert text to speech using MiniMax Speech 2.5 HD.

Speech 2.6 HD

High-quality text to speech using MiniMax's Speech 2.6 HD model.

Speech 2.6 Turbo

Fast text to speech using MiniMax's Speech 2.6 Turbo model.

Speech 2.8 HD

Convert text to speech using MiniMax Speech 2.8 HD with high-quality synthesis and interjection support.

Speech 2.8 Turbo

Convert text to speech using MiniMax Speech 2.8 Turbo with fast synthesis and interjection support.

Stable Audio 2.5 - Audio to Audio

Transform audio clips with text prompts using Stable Audio 2.5.

Stable Audio 2.5 - Inpaint

Inpaint audio clips by modifying specific sections while preserving the rest.

Stable Audio 2.5 - Text to Audio

Generate high-quality audio from text prompts using Stable Audio 2.5.

Voice Clone

Clone a voice from an audio URL. Optionally, generate a TTS preview with the cloned voice.

Voice Design

Design a personalized MiniMax voice from a text description and preview text.

xAI Speech to Text

Transcribe audio with automatic language detection, speaker diarization, word timestamps, and multichannel output.

Argil Avatars Train

Train an Argil avatar from an image.

Background Removal

Remove the background from an image using BiRefNet v2.

Nano-Banana Pro

Generate high-resolution images using Gemini 3 Pro Image.

Nano-Banana Pro Edit

Edit up to 14 images using Gemini 3 Pro Image.

Phota

Generate personalized photographs from text while preserving identity traits from referenced profiles in your prompt.

Phota Edit

Edit photos while preserving identity and removing distractions with precise prompt control.

Phota Enhance

Enhance images while preserving identities using Phota.

Qwen Image 2 Pro

Generate images from text using Qwen Image 2 Pro.

Qwen Image 2 Pro Edit

Edit images using Qwen Image 2 Pro.

Recraft V4 (Vector)

Recraft V4 text-to-vector generation.

Recraft V4 Pro

Recraft V4 Pro text-to-image generation.

Recraft V4 Pro (Vector)

Recraft V4 Pro text-to-vector generation.

Riverflow 2.0 Pro

Agentic image model optimized for robust, high-precision generations supporting font control.

Upscaler (Creative)

Magnific creative upscaler. Upscale images with style-driven enhancements.

Upscaler (Precision)

Magnific precision upscaler. Enhance with sharpen, smart grain, and ultra detail.

WAN 2.7 Pro Edit

Edit images using text instructions with WAN 2.7 Pro.

WAN 2.7 Pro Text to Image

Generate premium images from text using WAN 2.7 Pro.

Argil Avatars Audio-to-Video

Generate high-quality avatar videos from audio.

Argil Avatars Text-to-Video

Generate high-quality avatar videos from text.

DaVinci MagiHuman

Expressive facial performance, natural speech-expression coordination, and accurate audio-video sync from a reference image and optional driving audio.

Fabric 1.0

Generate videos from an image and audio using VEED Fabric 1.0.

Fabric 1.0 Fast

Generate videos from an image and audio using VEED Fabric 1.0 Fast.

Grok Imagine Extend Video

Continue a Grok Imagine clip or upload your own short MP4 (2–15s). The picker lists your Grok videos; uploads must be 480p or 720p. Credits depend on extension length and the resolution tier you choose.

Grok Imagine Reference to Video

Generate videos from multiple reference images using Grok Imagine. In your prompt, use @Image1, @Image2, etc. to reference images in order (up to 7).

Happy Horse 1.0

Alibaba Happy Horse 1.0 on Replicate: generate video from text or animate a single first-frame image.

HeyGen Avatar 3 Digital Twin

Generate digital twin talking avatar videos from text with HeyGen Avatar 3.

HeyGen Avatar 4 Digital Twin

Generate digital twin talking avatar videos from text with HeyGen Avatar 4.

HeyGen Avatar 4 Image-to-Video

Animate a portrait image into a talking avatar video with HeyGen Avatar 4.

HeyGen Translate Precision

Translate spoken videos with high accuracy using HeyGen Translate Precision.

HeyGen Translate Speed

Translate spoken videos quickly using HeyGen Translate Speed.

HeyGen Video Agent

Turn a text prompt into a polished video with AI-generated script, avatar, voiceover, visuals, and editing.

Hunyuan Avatar

Generate talking avatar videos from an image and audio using Tencent Hunyuan Avatar.

Hunyuan Custom

Generate customizable videos from an input image and text prompt using Tencent Hunyuan Custom.

Kling o1 Edit Video

Modify an existing video based on the prompt, with elements and reference images, using Kling o1.

Kling o1 First/Last Frame to Video

Generate a video that smoothly transitions from a start frame to an end frame using Kling o1.

Kling o1 Reference Image to Video

Generate a video from a start frame with additional reference images and elements using Kling o1.

Kling o1 Reference Video to Video

Generate a new shot from a reference video, with optional elements and style images, using Kling o1.

Kling O1 Standard Edit Video

Edit an existing video with prompt instructions, reference images, and elements using Kling O1 Standard.

Kling O1 Standard First/Last Frame to Video

Generate a video from a start frame and optional end frame using Kling O1 Standard.

Kling O1 Standard Reference Image to Video

Generate consistent video scenes from text, reference images, and custom elements using Kling O1 Standard.

Kling O1 Standard Reference Video to Video

Generate a new shot guided by a reference video, optional images, and elements using Kling O1 Standard.

Kling O3 4K Image to Video

Generate a video from a start image with optional end image and multi-shot prompting.

Kling O3 4K Reference to Video

Generate a video with optional start/end frames, reference images, elements, and multi-shot prompting.

Kling O3 4K Text to Video

Generate a video from text with optional multi-shot prompting and aspect ratio selection.

Kling O3 Pro Image to Video

Generate a video from a start frame with optional end frame and multi-shot prompting.

Kling O3 Pro Reference to Video

Generate consistent scene videos from reference images, optional start/end frames, and elements.

Kling O3 Pro Text to Video

Generate realistic videos from text with Kling O3 Pro and optional native audio.

Kling O3 Pro Video to Video (Edit)

Edit an input video using text guidance with optional reference images and elements.

Kling O3 Pro Video to Video (Reference)

Generate new shots guided by a reference video while preserving motion and camera language.

Kling O3 Standard Image to Video

Generate a video from a start frame with optional end frame and multi-shot prompting.

Kling O3 Standard Reference to Video

Generate consistent scene videos from reference images, optional start/end frames, and elements.

Kling O3 Standard Text to Video

Generate realistic videos from text with Kling O3 Standard and optional native audio.

Kling O3 Standard Video to Video (Edit)

Edit an input video using text guidance with optional reference images and elements.

Kling O3 Standard Video to Video (Reference)

Generate new shots guided by a reference video while preserving motion and camera language.

Kling V2 Master Image to Video

Generate image-to-video clips with Kling 2.0 Master.

Kling V2 Master Text to Video

Generate text-to-video clips with Kling 2.0 Master.

Kling V2.1 Master Image to Video

Generate premium image-to-video clips with Kling 2.1 Master.

Kling V2.1 Master Text to Video

Generate premium text-to-video clips with Kling 2.1 Master.

Kling V2.1 Pro Image to Video

Generate image-to-video clips with Kling 2.1 Pro.

Kling V2.1 Standard Image to Video

Generate image-to-video clips with Kling 2.1 Standard.

Kling V2.5 Turbo Pro Image to Video

Generate image-to-video clips with Kling 2.5 Turbo Pro.

Kling V2.5 Turbo Pro Text to Video

Generate text-to-video clips with Kling 2.5 Turbo Pro.

Kling V2.5 Turbo Standard Image to Video

Generate image-to-video clips with Kling 2.5 Turbo Standard.

Kling V2.6 Pro Image to Video

Animate an input image into a video using Kling V2.6 Pro via Fal, with optional native audio.

Kling V2.6 Pro Motion Control

Generate videos where character actions match a reference video while the visual appearance is based on a reference image. Pro mode offers higher quality output.

Kling V2.6 Pro Text to Video

Generate videos from text using Kling V2.6 Pro via Fal, with optional native audio.

Kling V2.6 Standard Motion Control

Generate videos where character actions match a reference video while the visual appearance is based on a reference image. Standard mode is cost-effective.

Kling V3 4K Image to Video

Generate a video from a start image with optional end image, elements, and native audio.

Kling V3 4K Text to Video

Generate realistic videos from text with optional multi-shot prompting, aspect ratio control, and native audio.

Kling V3 Pro Image to Video

Generate videos from start/end images with Kling V3 Pro, with multi-shot, elements, and optional native audio.

Kling V3 Pro Motion Control

Transfer motion from a reference video to a character image using Kling V3 Pro.

Kling V3 Pro Text to Video

Generate high-quality videos from text with optional native audio, multi-shot prompting, and custom voices.

Kling V3 Standard Image to Video

Generate videos from start/end images with Kling V3 Standard, with multi-shot, elements, and optional native audio.

Kling V3 Standard Motion Control

Transfer motion from a reference video to a character image using Kling V3 Standard.

Kling V3 Standard Text to Video

Generate videos from text with Kling V3 Standard, including multi-shot and optional native audio.

Lipsync 2.0

Natural lipsyncing with preservation of the unique speaking style of each speaker.

Lipsync 2.0 Pro

Highest quality lipsync with diffusion-based super resolution. Enhanced detail for beards, teeth, and facial features.

Lipsync 3.0

Sync’s strongest lipsync: native visual intelligence for professional-quality video.

LTX 2 Audio to Video

Generate synchronized video from audio with optional image guidance using Lightricks Audio-to-Video.

LTX 2 Extend Video

Extend videos with text prompts using LTX 2 (full quality).

LTX 2 Fast

Fast LTX-2 generation with optional image conditioning and synchronized audio.

LTX 2 Pro

Higher-fidelity LTX-2 generation with optional image conditioning and synchronized audio.

LTX 2 Retake

Retake and regenerate a selected segment in an existing video while preserving context.

LTX 2 Video to Video

Transform videos with text prompts using LTX 2 (full quality).

LTX 2.3 22B Audio-to-Video LoRA

Generate video with audio from audio, text and images using LTX-2.3 22B and custom LoRA.

LTX 2.3 22B Distilled Audio-to-Video LoRA

Generate video with audio from audio, text and images using LTX-2.3 Distilled and custom LoRA.

LTX 2.3 22B Distilled Image-to-Video LoRA

Generate video with audio from images using LTX-2.3 Distilled and custom LoRA.

LTX 2.3 22B Distilled Reference Video-to-Video

Generate videos with audio from a required reference video and prompt using the distilled LTX 2.3 22B model. Optional audio, start image, and end image can guide the result. Keep Match Video Length on for automatic timing, or use frame count manually (121 frames is about 5 seconds at 24 FPS).

LTX 2.3 22B Distilled Text-to-Video LoRA

Generate video with audio from text using LTX-2.3 Distilled and custom LoRA.

LTX 2.3 22B Distilled Video-to-Video LoRA

Generate video with audio from videos using LTX-2.3 Distilled and custom LoRA.

LTX 2.3 22B Extend Video LoRA

Extend a video at the start or end using LTX-2.3 22B and custom LoRA.

LTX 2.3 22B Image-to-Video LoRA

Generate video with audio from images using LTX-2.3 22B and custom LoRA.

LTX 2.3 22B Reference Video-to-Video

Generate videos with audio from a required reference video and prompt using LTX 2.3 22B. Optional audio, start image, and end image can guide the result. Keep Match Video Length on for automatic timing, or use frame count manually (121 frames is about 5 seconds at 24 FPS).

LTX 2.3 22B Text-to-Video LoRA

Generate video with audio from text using LTX-2.3 22B and custom LoRA.

LTX 2.3 22B Video-to-Video LoRA

Generate video with audio from videos using LTX-2.3 22B and custom LoRA.

LTX 2.3 Audio-to-Video

Generate a video from audio with optional image conditioning using LTX 2.3.

LTX 2.3 Extend Video

Extend a video at the start or end using LTX 2.3.

LTX 2.3 Fast Image-to-Video

Generate videos from an input image and prompt with LTX 2.3 Fast.

LTX 2.3 Fast Text-to-Video

Generate videos from text prompts with LTX 2.3 Fast.

LTX 2.3 Image-to-Video

Generate high-quality videos from an input image and prompt.

LTX 2.3 Pro

High-fidelity video generation with text/image/audio, retake, and extend workflows using LTX 2.3 Pro.

LTX 2.3 Retake Video

Retake a selected segment of a video using text guidance with LTX 2.3.

LTX 2.3 Text-to-Video

Generate high-quality videos from text prompts with LTX 2.3.

MiniMax Hailuo 02 Fast Image to Video

Generate economical 512p image-to-video clips with MiniMax Hailuo 02 Fast.

MiniMax Hailuo 02 Pro Image to Video

Generate 1080p image-to-video clips with MiniMax Hailuo 02 Pro.

MiniMax Hailuo 02 Pro Text to Video

Generate 1080p text-to-video clips with MiniMax Hailuo 02 Pro.

MiniMax Hailuo 02 Standard Image to Video

Generate 512p or 768p image-to-video clips with MiniMax Hailuo 02 Standard.

MiniMax Hailuo 02 Standard Text to Video

Generate 768p text-to-video clips with MiniMax Hailuo 02 Standard.

MiniMax Hailuo 2.3 Fast Pro Image to Video

Generate fast 1080p image-to-video clips with MiniMax Hailuo 2.3 Fast Pro.

MiniMax Hailuo 2.3 Fast Standard Image to Video

Generate fast 768p image-to-video clips with MiniMax Hailuo 2.3 Fast Standard.

MiniMax Hailuo 2.3 Pro Image to Video

Generate 1080p image-to-video clips with MiniMax Hailuo 2.3 Pro.

MiniMax Hailuo 2.3 Pro Text to Video

Generate 1080p text-to-video clips with MiniMax Hailuo 2.3 Pro.

MiniMax Hailuo 2.3 Standard Image to Video

Generate 768p image-to-video clips with MiniMax Hailuo 2.3 Standard.

MiniMax Hailuo 2.3 Standard Text to Video

Generate 768p text-to-video clips with MiniMax Hailuo 2.3 Standard.

MiniMax Video 01 Director Image to Video

Generate image-to-video clips with MiniMax Video 01 Director camera-control prompts.

MiniMax Video 01 Director Text to Video

Generate text-to-video clips with MiniMax Video 01 Director camera-control prompts.

MiniMax Video 01 Image to Video

Generate video clips from images with MiniMax Video 01.

MiniMax Video 01 Live Image to Video

Animate still images with MiniMax Video 01 Live, optimized for character and illustration motion.

MiniMax Video 01 Live Text to Video

Generate lively, expressive video clips from text prompts with MiniMax Video 01 Live.

MiniMax Video 01 Subject Reference

Generate videos with consistent subject identity from a reference image.

MiniMax Video 01 Text to Video

Generate video clips from text prompts with MiniMax Video 01.

P-Video

Pruna P-Video on Replicate: text, image, or audio-conditioned video (1–20s, optional last frame, draft mode).

PixVerse C1 Image to Video

Animate a source image into cinematic video using PixVerse C1 via Fal (1-15s, up to 1080p, optional audio).

PixVerse C1 Text to Video

Generate cinematic videos from text using PixVerse C1 via Fal (1-15s, up to 1080p, optional audio).

PixVerse C1 Transition

Create seamless transitions between two images using PixVerse C1 via Fal (1-15s, up to 1080p, optional audio).

PixVerse Extend

Extend an existing video using PixVerse via Fal.

PixVerse Extend Fast

Extend an existing video using PixVerse Fast via Fal.

PixVerse Lipsync

Create a lipsync video by combining a video with audio via Fal.

PixVerse Sound Effects

Add sound effects to an existing video using PixVerse via Fal.

PixVerse v4.5 Effects

Apply PixVerse v4.5 effects to an image via Fal.

PixVerse v4.5 Image to Video

Animate an image into a video using PixVerse v4.5 via Fal.

PixVerse v4.5 Image to Video Fast

Animate an image into a video using PixVerse v4.5 Fast via Fal.

PixVerse v4.5 Text to Video

Generate videos from text using PixVerse v4.5 via Fal.

PixVerse v4.5 Text to Video Fast

Generate videos from text using PixVerse v4.5 Fast via Fal.

PixVerse v4.5 Transition

Create a transition video between two images using PixVerse v4.5.

PixVerse v5 Effects

Apply PixVerse v5 effects to an image via Fal.

PixVerse v5 Image to Video

Animate an image into a video using PixVerse v5 via Fal.

PixVerse v5 Text to Video

Generate videos from text using PixVerse v5 via Fal.

PixVerse v5 Transition

Create a transition video between two images using PixVerse v5.

PixVerse v5.5 Effects

Apply PixVerse v5.5 effects to an image to generate a stylized video via Fal.

PixVerse v5.5 Image to Video

Animate an input image into a video using PixVerse v5.5 via Fal, with optional audio and multi-clip camera motions.

PixVerse v5.5 Text to Video

Generate videos from text using PixVerse v5.5 via Fal, with optional audio and multi-clip camera motions.

PixVerse v5.5 Transition

Create a smooth transition video between two images using PixVerse v5.5 via Fal.

PixVerse v5.6 Image to Video

Animate an input image into a video using PixVerse v5.6 via Fal, with optional audio.

PixVerse v5.6 Text to Video

Generate videos from text using PixVerse v5.6 via Fal, with optional audio.

PixVerse v5.6 Transition

Create a smooth transition video between two images using PixVerse v5.6 via Fal.

PixVerse Video Swap

Swap a subject in a video using PixVerse via Fal.

React 1

Advanced emotionally reactive lip sync. Generates natural talking head movements and facial expressions based on audio and emotion prompts.

Runway Gen-4.5

Image → Video (Gen-4.5).

Seedance 2 Fast Image to Video

Animate a starting image into video with optional end-frame guidance using Seedance 2 Fast on Fal.

Seedance 2 Fast Omni

Generate faster Seedance 2 videos from text with optional image, video, and audio references on Fal. Use @Image1, @Video1, and @Audio1 in the prompt.

Seedance 2 Fast Text to Video

Generate faster Seedance 2 videos from text with Fal. Supports 480p and 720p output.

Seedance 2 Image to Video

Animate a starting image into video with optional end-frame guidance using Seedance 2 on Fal. Supports 480p, 720p, and 1080p output.

Seedance 2 Max (Image to Video)

Dreamina / UseAPI: first frame (and optional end frame). Aspect ratio is detected from images when refs are used.

Seedance 2 Max (Omni)

Dreamina / UseAPI: same behavior as Seedance 2 Max (Text to Video)—reference images, up to 3 reference videos, up to 3 audio files; tag with @image1, @video1, @audio1. 4–15s, 720p.

Seedance 2 Max (Text to Video)

Dreamina / UseAPI (US region): Seedance 2.0 text-to-video. Optional references work like Seedance Preview VIP: up to 9 images, up to 3 reference videos, up to 3 audio files—tag with @image1, @video1, @audio1. 4–15s, 720p output.

Seedance 2 Omni

Generate Seedance 2 videos from text with optional image, video, and audio references on Fal. Use @Image1, @Video1, and @Audio1 in the prompt.

Seedance 2 Preview (Image to Video)

Standard preview queue (Basic or High): up to 9 reference images, optional motion video and audio (e.g. mp3/wav, up to 15s). Use @image1, @video1, @audio1. Output 5, 10, or 15 seconds only. For the full Omni path with more references, use Seedance 2 Pro (Image to Video · Omni).

Seedance 2 Preview (Text to Video)

Standard preview: text-to-video; optional image references for subject or style. Basic vs High quality. Output 5, 10, or 15 seconds only. For full omni (more refs, longer durations), use Seedance 2 Pro · Omni.

Seedance 2 Pro (Edit Video · Preview VIP)

Preview VIP: edit a source clip with up to 9 reference images. Audio references are not supported on this queue yet. Credit estimates use VIP rates and about twice the source length when duration is known.

Seedance 2 Pro (Image to Video · Omni)

Full Seedance 2 Pro Omni: up to 12 references (images, video, mp3/wav audio up to 15s; add at least one image or video if you use audio). Output 4–15 seconds; 480p, 720p, or 1080p. Use @image1, @video1, @audio1. For the standard preview queue (5/10/15s only), use Seedance 2 Preview (Image to Video).

Seedance 2 Pro (Image to Video · Preview VIP)

Preview VIP: up to 9 reference images and optional motion video (up to 3 clips). Use @image1, @video1. Resolution 720p or 1080p for High quality. Audio references are not supported on this queue yet. With a reference video, credits reflect input plus output duration.

Seedance 2 Pro (Text to Video · Omni)

Full Seedance 2 Pro Omni: text-only or up to 12 references (images, motion video, mp3/wav audio up to 15s). Use @image1, @video1, @audio1. Output 4–15 seconds; resolutions 480p, 720p, or 1080p. For the simpler text-only preview queue (5/10/15s), use Seedance 2 Preview (Text to Video).

Seedance 2 Pro (Text to Video · Preview VIP)

Preview VIP: priority text-to-video queue (often a few minutes). Output 5, 10, or 15 seconds; 720p or 1080p when using High quality. For reference images or motion video, use Seedance 2 Pro (Image to Video · Preview VIP). Audio is not supported on Preview VIP yet.

Seedance 2 Text to Video

Generate cinematic Seedance 2 videos from text with Fal. Supports 480p, 720p, and 1080p output.

Upscale Video

Professional video upscaling with Topaz Video AI. Credits scale with output resolution tier, duration, optional 60fps interpolation, and Gaia 2 half-rate pricing.

Veo 3.1 Extend Video

Extend a video using Google's Veo 3.1 model.

Veo 3.1 Fast Extend Video

Extend a video using Google's Veo 3.1 Fast model.

Veo 3.1 Fast First–Last Frame to Video

Generate videos by animating between a first and last frame using Google's Veo 3.1 Fast model.

Veo 3.1 Fast Image to Video

Generate videos by animating an input image using Google's Veo 3.1 Fast model.

Veo 3.1 Fast Reference to Video

Generate videos from reference image(s) and text using Google's Veo 3.1 Fast model.

Veo 3.1 Fast Text to Video

Generate videos using Google's Veo 3.1 Fast model.

Veo 3.1 First–Last Frame to Video

Generate videos by animating between a first and last frame using Google's Veo 3.1 model.

Veo 3.1 Image to Video

Generate videos by animating an input image using Google's Veo 3.1 model.

Veo 3.1 Reference to Video

Generate videos from reference image(s) and text using Google's Veo 3.1 model.

Veo 3.1 Text to Video

Generate videos using Google's Veo 3.1 model.

Vidu Q3 Image to Video

Generate a video from an image using the Vidu Q3 model.

Vidu Q3 Reference to Video (Mix)

Generate a video from reference images using Vidu Q3's reference-to-video mix model.

Vidu Q3 Text to Video

Generate a video from text using the Vidu Q3 model.

WAN 2.6 Image to Video

Generate a video from an image using WAN 2.6 image-to-video model.

WAN 2.6 Reference to Video

Generate a video using reference videos for character/subject consistency.

WAN 2.6 Text to Video

Generate a video from text using WAN 2.6 text-to-video model.

WAN 2.7 Edit Video

Edit an input video with Wan 2.7 using natural-language direction, optional reference imagery, and audio controls.

WAN 2.7 Image to Video

Animate a still image or continue a clip with Wan 2.7 while preserving visual coherence.

WAN 2.7 Reference to Video

Generate a video from text while carrying appearance and motion cues from reference images and videos.

WAN 2.7 Text to Video

Generate cinematic videos from text with Wan 2.7 motion smoothness and scene coherence.