Nodes

Rough 3D scene reconstruction from images or a camera-traverse video.

Camera tracking and sparse 3D reconstruction from a source video.

Image expansion for changing canvas or aspect ratio.

Image upscaling with alpha-preservation controls.

Background removal with partial-alpha preservation.

Upscale and enhance existing videos with target resolution, frame-rate, preset, tier, and fidelity controls.

High-quality Clarity image upscaling with 2x to 16x scale, creativity control, and output format selection.

Lightweight Claude text generation for careful drafting and summarization.

Animate a first-frame image with NVIDIA Cosmos 3 Super, using prompt expansion and optional agentic refinement.

Portrait-focused image upscaling with a simple scale-factor control.

Video upscaling with a simple scale-factor control.

Talking-human video generation from an image, prompt, and optional audio.

Reasoning-focused text generation for analytical tasks.

General-purpose DeepSeek text generation for drafting, coding, and transformations.

Prompt improvement utility for preparing text before generation.

Translation utility for text that should move into another language before use.

Text-to-sound effects for short Foley, ambience, and designed audio cues.

Fast text-to-speech for draft narration and timing work.

Expressive text-to-speech for reads where performance matters.

FLUX 2 Dev generation and editing with multi-reference image input.

Edge-guided FLUX generation for preserving structure.

Depth-guided FLUX generation for preserving spatial relationships.

FLUX inpainting and outpainting for filling or extending images.

Fast FLUX Kontext editing with exposed tuning controls.

Polished FLUX Kontext generation and editing with a simpler control surface.

Photoreal-leaning FLUX generation that avoids an overprocessed AI look.

FLUX image variation from a source image.

Fast FLUX text-to-image generation for lightweight iteration.

Generate expressive speech from text with optional multi-speaker voice configuration.

Fast text-to-video generation for short clips with audio, timing, duration, and framing controlled by the prompt.

Edit an existing video clip with a simple natural-language instruction.

Animate a single source image into a short video clip with prompt-directed motion, timing, and audio.

Generate a short video from a prompt plus one or more image references for subject, style, or composition guidance.

Fast Gemini text generation for lightweight language tasks.

Prompt-only image generation for quick visual drafts.

Fast Imagen 4 for prompt-only stills with a small control surface.

Text-to-music generation with prompt, negative prompt, and seed.

Lyria 3 music generation for 30-second ideas from text or images.

Lyria 3 Pro music generation for longer structured tracks.

Lightweight reference-guided image generation and editing.

Google image upscaling with 2x or 4x enlargement.

Instruction-following image generation for detailed briefs and text-heavy stills.

Image editing and reference-based generation for changing existing stills.

Lightweight GPT text generation for instruction following and structured text.

Grok Imagine image generation for prompt or reference-led stills.

Grok Imagine reference-to-video guided by one or more images.

Grok Imagine video generation or editing from prompt, image, or video input.

Animate a source image into a Grok Imagine 1.5 video clip.

Grok Imagine extension for continuing an existing video.

Fast Hailuo 02 video generation for low-resolution motion checks.

Hailuo 2.3 video generation for higher-fidelity text or image guided clips.

Fast Hailuo 2.3 for efficient image-to-video and text-to-video iteration.

Create a talking avatar video from text using existing avatar and voice identifiers.

High-accuracy lip sync for replacing speech in existing video.

Fast HeyGen lip sync for draft speech replacement.

Tencent Hunyuan prompt-to-image with 2K-oriented output controls.

Newer Hunyuan prompt-to-image generation with speed and quality controls.

Generate a textured 3D model from one or more reference images.

Generate a textured 3D model from a text prompt.

Ideogram character generation from a reference image.

Ideogram image generation for typography-aware graphic stills.

Prompt-driven image generation with strong typography, composition, and rendering-speed control.

Fast single-image Ideogram V4 generation for design-heavy prompts, readable text, and polished layout drafts.

Instant single-image Ideogram V4 generation for very fast design drafts with readable text and graphic composition.

Imagen prompt-only generation with structured image settings.

Kandinsky text-to-video with resolution, length, and inference-step controls.

Distilled Kandinsky text-to-video for faster simple generations.

Kling 2.5 image-to-video with duration, negative prompt, and motion scale.

Kling 2.5 text-to-video with aspect ratio and motion scale controls.

Kling 2.6 image-to-video with native audio as an option.

Kling 2.6 text-to-video with native audio support.

Kling lip-sync for matching a video to supplied speech.

Kling O1 video editing through natural-language commands.

Kling text-to-speech with voice selection and speed control.

Kling V1.6 Pro with start and end image control.

Kling V1.6 Standard for short text or image-guided clips.

Kling V2.0 text or image-to-video generation for short clips.

Kling V2.1 image-to-video with end-frame guidance and quality mode.

Kling V2.1 Master for higher-quality short video generation.

Motion transfer from a reference performance video to a character image.

Reference-heavy Kling V3 generation and video editing.

Kling V3 Turbo Pro Image To Video turns a first-frame image into a 1080p short video clip.

Kling V3 Turbo Pro Text To Video creates 1080p short video clips directly from a prompt.

Kling V3 Turbo Standard Image To Video turns a first-frame image into a 720p short video clip.

Kling V3 Turbo Standard Text To Video creates 720p short video clips directly from a prompt.

Kling V3 video generation with start/end frames, native audio, and multi-shot prompting.

Lightweight text-to-speech with simple speed and voice controls.

Higher-capacity Krea 2 text-to-image generation with optional style-reference images, aspect-ratio control, and creativity control.

Text-to-image generation with optional style-reference images, aspect-ratio control, and creativity control.

Fast text-to-image generation with optional style-reference images, aspect-ratio control, and creativity control.

Fast prompt-only Krea 2 generation with image-size presets, prompt expansion, and acceleration control.

Fast LTX 2 video generation for previews.

Higher-fidelity LTX 2 video generation from text or image.

LTX 2 retake editing for sections of existing footage.

LTX 2.3 audio-to-video with optional first-frame and prompt guidance.

LTX 2.3 extension for continuing an existing video.

Convert a source SDR image into a single HDR EXR frame, with a Rec.709 preview image returned for graph display.

LTX 2.3 image-to-video for source-image motion and optional end-frame guidance.

Fast LTX 2.3 image-to-video for early motion tests.

Generate video from an audio track with LTX 2.3 Quality, with optional first-frame image guidance.

Lift an SDR source video into an LTX 2.3 Quality HDR render.

Animate a starting image with the LTX 2.3 Quality workflow.

Transform a reference video with LTX 2.3 Quality while preserving motion or structure from the source.

LTX 2.3 generation guided by a reference video plus optional frames.

LTX 2.3 retake for replacing part of an input video.

LTX 2.3 text-to-video with timing, resolution, and audio controls.

Fast LTX 2.3 text-to-video for prompt exploration.

LTX 2.3 prompt-guided video-to-video transformation.

Luma Photon image generation with image, style, and character references.

Luma Ray 2 video generation with start/end images and concept controls.

Animate a start frame, interpolate between start and end frames, or direct a shot with timeline keyframes.

Change a video to a new aspect ratio by preserving the source footage and generating the newly exposed canvas.

Create cinematic 5- or 10-second shots from a text prompt, with resolution, looping, HDR, and EXR controls.

Restyle or reinterpret a source clip while using its motion and composition as guidance.

Generate still images with Microsoft MAI Image 2.5 using prompt, aspect ratio, and output format controls.

Edit one or more source images with Microsoft MAI Image 2.5.

Hailuo 02 video generation with first and last frame support.

MiniMax image generation with subject-reference support.

Reference-assisted music generation with lyrics, vocals, and instrumental inputs.

Full-song generation from lyrics and a style prompt.

Full-length song generation with lyrics and production-style prompting.

MiniMax song generation with optional instrumental mode and lyric optimization.

High-detail MiniMax speech generation with emotion and audio-format controls.

Fast MiniMax speech generation with the same main delivery controls as the HD node.

Generate synchronized sound effects from an input video.

Generate audio that follows video, image, or text context.

Fast image generation and editing with web-search grounding and a wide resolution range.

Efficient 1K image generation and editing from the Nano Banana 2 family.

Fast 1K image generation and editing for lightweight creative iteration.

High-control image generation and editing where text, layout, and reference composition matter.

Animate a human image from an audio track.

Ovi text-to-video with built-in audio prompting controls.

Ovi image-to-video with prompt and audio-negative-prompt guidance.

Fast Pruna image generation from text.

Fast multi-image editing from prompts and image inputs.

Pruna image upscaling with mode, target, and realism/detail controls.

Pixverse V6 video generation with optional end frame, audio, and multi-clip controls.

Pruna video generation with text, image, audio, and draft-mode controls.

Animate a reference subject image using motion and optional audio from a source video.

Create a talking-avatar video from a still image and either uploaded audio or generated speech.

Synthesize speech with Qwen3 TTS using preset voices, voice cloning, or voice design.

Camera-aware Qwen editing for angle, tilt, zoom, and wide-angle changes.

Qwen image generation with prompt expansion, guidance, and quality controls.

Qwen Image 2 generation and editing with prompt expansion and image matching.

Higher-control Qwen Image 2 for polished generation and editing.

Qwen image editing from a source image and prompt.

Qwen product or subject fusion into a new scene.

Qwen next-scene editing for continuing a visual moment.

Qwen multi-image editing and stronger single-image consistency.

Qwen relighting for changing the mood of an existing image.

Qwen detail-upscale and restoration pass for an existing image.

Fast Recraft text-to-image generation for simple design drafts.

Recraft cleanup and crisp upscaling for existing images.

Recraft V3 for styled raster and illustration generation.

Recraft V4 raster image generation for design-led stills.

Design-oriented image generation with prompt, size, color, and safety controls.

Higher-end Recraft V4.1 image generation for design-focused still images.

Generate editable SVG vector artwork with the Recraft V4.1 Pro SVG model.

Generate editable SVG vector artwork from text prompts.

Higher-resolution Recraft V4 raster generation.

Detailed Recraft V4 Pro SVG generation.

Recraft V4 SVG generation for editable vector artwork.

Fast image background removal for simple cutouts.

Expressive speech generation with optional audio prompt guidance.

Resemble speech generation with preset or custom voice selection.

Apply prompt-guided edits to a source video with optional keyframe guidance.

Runway Gen-4.5 video generation for detailed motion and camera direction.

Runway Gen-4 Aleph video-to-video transformation.

Runway Gen-4 image generation with reference tags for consistent subjects and styles.

Runway Gen-4 Turbo image-to-video for fast still-driven motion.

Seedance 1 Lite video generation for lower-resolution drafts.

Seedance 1 Pro video generation with optional first and last frames.

Fast Seedance 1 Pro for prompt or image-led motion drafts.

Quick image-to-video motion drafts in the Seedance 2.0 family.

Quick reference-guided Seedance 2.0 drafts.

Draft-speed text-to-video in the Seedance 2.0 family.

Seedance 2.0 image-led video generation with ending-frame guidance.

Lower-cost image-to-video drafts in the Seedance 2.0 family.

Lower-cost reference-guided Seedance 2.0 drafts.

Lower-cost text-to-video in the Seedance 2.0 family.

Seedance 2.0 video generation guided by images, video clips, or audio.

Seedance 2.0 text-to-video for scene ideas without reference media.

Seedream 3 prompt-only image generation with size and guidance controls.

Unified image generation and editing with high-resolution output and optional related image sets.

Reference-guided image generation for polished high-resolution stills.

Cost-efficient Seedream image generation and editing with reference images, 2K or 3K output, and optional sequential sets.

Flagship Seedream image generation and editing for polished 1K or 2K outputs guided by text and optional references.

SeedVR image upscaling with target-resolution or factor mode.

SeedVR video upscaling with output format, quality, and write-mode controls.

Generate music tracks from a text prompt with duration and sample-count controls.

Generate music that follows the pacing and mood of a source video.

Sync Lipsync 2 for matching existing video to new audio.

Higher-quality Sync Lipsync 2 for speech replacement.

Sync Lipsync V3 for high-fidelity audio-to-video lip sync.

Topaz video enhancement with model, FPS, compression, and detail controls.

Background removal with threshold, reverse, and replacement-background controls.