Every AI model and tool you can use in CNAPS Studio — 80+ models and 80+ tools — each with its own page. Hosted models run on CNAPS servers, no outside account or API key needed. External models run on the provider's servers with your own API key. Use Ctrl/Cmd + F to find a model by name, or start from the quick picks below.
🎯 Quick Picks
Not sure where to start? These are good first choices for common tasks.
I want to… | Start with | Also try |
Upscale a photo | PiSA-SR (sharpest) | SMFANet+, FideSR, or CoDSR for large (2K+) inputs |
Remove a background | BiRefNet (Subject) | SAM3.1 (Scene) to pick objects by text |
Remove an object | Moebius (fast, mask-based) | PowerPaint, LatentDiffusion |
Edit an image with words | QWEN-2511 | FireRed-1.1 to keep a person's identity |
Generate an image | Z-Image-Turbo | FLUX Schnell, SANA-Sprint; GLM-Image for posters with text |
Detect objects | RF-DETR Medium | YOLO-S, DETR |
Read documents (OCR) | GLM-OCR | DeepSeekOCR; PaddleOCR for fast CJK; Sarashina2.2-OCR for Japanese |
Upscale a video | SeedVR2 7B (highest quality) | SeedVR2 3B, FlashVSR-v1.1 (fast) |
Generate a video | Helios-Base | Helios-Distilled (faster), LTX-2.5 (with sound) |
Transcribe speech | Speech Recognition (Video) | Transcribe (Gemini) |
Turn text into speech | Qwen3-TTS | Qwen3 Voice Design, Gemini TTS |
🖥️ Hosted Models
Open-weights models that run on CNAPS Studio's own servers — no outside account or API key needed. Licenses vary by model; see each model's page.
🎙️ Audio Understanding
Transcribe Every Clip in a Video List — Timed Transcripts
🔧 Image Restoration
Fix Motion Blur — Handles Uneven Blur Across the Frame
🧠 Multimodal Language Models
Compact Vision-Language Model — Spatial Reasoning, Charts & Documents
👁️ Object Detection
Find License Plates — Chain with Blur for Anonymization
🎬 Video Generation
Omni-Reference Video Generation with Native Stereo Audio — 5–15 s @ 24 fps
🌐 External Models
Run on the provider's servers with your own API key — add it under your avatar → Workspace Settings → Integrations. They don't use your CNAPS capacity.
🎙️ Audio Understanding
One-Shot Summary of an Audio File — Speech, Language, Setting & Key Events
🎙️ Audio Understanding
Detect 100+ Sound Events with Timestamps — Sirens, Glass Breaks, Applause & More
🎙️ Audio Understanding
Speaker-Separated Transcripts in 100 Languages via Cochl
🛠️ Tools
Image, Video & Audio Processing Tools
Category | Tool | What It Does |
Annotation | Turn any image into a clean white-edges-on-black edge map | |
Blur & Effects | Quick blur with minimal processing for fast results | |
Blur & Effects | The safest and simplest form of Blur in the family | |
Blur & Effects | Apply blur effects to images for various intensity levels | |
Blur & Effects | Camera-Style Bokeh - Circular Disc Blur, Not Gaussian | |
Blur & Effects | Apply a clean, region-specific blur to any part of an image | |
Color Adjustments | Convert color images to grayscale | |
Color Adjustments | Invert colors in images for creative effects | |
Color Adjustments | Merge brightness and color information at the pixel level. | |
Comparison | Compare up to 4 images side-by-side for quality or differences | |
Comparison | Compare up to 4 texts side-by-side for quality or differences | |
Comparison | Compare up to 4 videos side-by-side for quality or differences | |
Image Blending | Blend images by adding pixel values together | |
Image Blending | Blend images by multiplying pixel values for overlay effects | |
Image Blending | Paste a processed crop back into the original image by its detected class | |
Image Blending | Paste a processed crop back into the original image at a given box | |
Image Blending | Paste multiple images back into their original positions using coordinates. | |
Image Masking | Write a mask into the alpha channel for a transparent PNG cutout | |
Image Masking | Create masks by selecting its assigned class from Object Detection | |
Image Masking | Create masks by selecting its bounding box coordinates from Object Detection | |
Image Masking | Turn Written Coordinates into a Black-and-White Mask | |
Image Masking | Create masks and select regions for targeted processing | |
Image Masking | Grow or shrink a mask's edge by a set number of pixels | |
Image Masking | Select objects for targeted processing | |
Image Resizing | Auto-upscale small images to the next standard resolution tier | |
Image Resizing | Resize images to specific dimensions or aspect ratios | |
Image Resizing | Resize one image to match another's exact dimensions | |
Layered Tools | Stack Multiple Images Into One - Photoshop-Style Layer Compositing | |
Repeat | Start a loop — run the next nodes once for every item in a list | |
Repeat | End a loop — gather each item's result back into one list, in order | |
Selection & Extraction | Extract segmented region by selecting its assigned class from Segmentation | |
Selection & Extraction | Extract segmented region by RGB color match | |
Selection & Extraction | Extract segmented region by selecting its color from Segmentation | |
Selection & Extraction | Combine up to 8 separate images into one image list | |
Selection & Extraction | Crop detected objects by class for batch processing | |
Selection & Extraction | Crop an image by selecting its assigned class from Object Detection | |
Selection & Extraction | Crop an image by its bounding box coordinates from Object Detection | |
Selection & Extraction | Pass through the input image only when specified text matches | |
Selection & Extraction | Select the first available image from multiple inputs for downstream | |
Selection & Extraction | Pick One Image Out of an Image List — By Index | |
Selection & Extraction | Put One Image Back Into a List — Replace by Index | |
Selection & Extraction | Manually crop any image by drawing the keep-region directly on it | |
Selection & Extraction | Combine up to 8 separate sounds into one sound list | |
Selection & Extraction | Pick One Sound Out of a Sound List — By Index | |
Selection & Extraction | Put One Sound Back Into a List — Replace by Index | |
Selection & Extraction | Select the best take from a batch using evaluation results. | |
Selection & Extraction | Combine up to 8 separate videos into one video list | |
Selection & Extraction | Pull a Single Frame Out of a Video as an Image | |
Selection & Extraction | Turn an Image List Back Into a Video | |
Selection & Extraction | Pick One Video Out of a Video List — By Index | |
Selection & Extraction | Put One Video Back Into a List — Replace by Index | |
Selection & Extraction | Turn a Video Into an Image List — with Sampling and Frame-Count Controls | |
Selection & Extraction | Cut a video into highlight clips driven by a Video Analysis JSON | |
Text | Place text anywhere on an image | |
Text | Strip OCR Output Down to Just the Coordinates | |
Text | Merge Up to 4 Text Inputs Into One | |
Text | Reusable prompt templates — fill the blank with incoming text | |
Video Editing | Cut audio, apply fades, and adjust levels before playback or mixing | |
Video Editing | Broadcast-standard loudness normalization (EBU R128, -14 LUFS / -1.5 dBTP) + true-peak limiter — publish-ready audio in one node | |
Video Editing | Combine audio tracks into a mixed output | |
Video Editing | Replace or mix a video's audio, with voice ducking to keep speech clear over background audio | |
Video Editing | Composite green- or blue-screen footage with automatic left/right flipping and corner placement | |
Video Editing | Prepend a short preview of each clip's best moment to the front — the classic cold-open attention trick | |
Video Editing | Animate a still image with zooms, pans, or multiple keyframes, including a 3:4 canvas option | |
Video Editing | Freeze the first frame while a narration audio plays over it, then join to the front of the clip — raw voiceover cold-open muxer | |
Video Editing | Auto jump-cut editor — trim silent gaps out of every clip for snappy talking-head pacing | |
Video Editing | One Whole-Video Transcript, Sliced Onto Each Clip — Automatically | |
Video Editing | Nudge Video Analysis segment cuts to the nearest word boundary — no more mid-word clips | |
Video Editing | Evaluate takes in a batch to support automatic selection | |
Video Editing | Extract a video's audio for transcription, editing, or reuse in another flow | |
Video Editing | Burn a static Title or Hook overlay onto each clip — six named look presets, three positions | |
Video Editing | Trim each clip to its longest continuous shot — removes mid-clip scene jumps automatically | |
Video Editing | Glue every clip in a list into a single continuous video, auto-normalizing resolution and frame rate | |
Video Editing | Measure a Video's Framing & Caption Constraints — Data for a Downstream Shorts Planner | |
Video Editing | Turn a Shorts Edit Plan into a Renderable EDL — The Bridge from Planning to Rendering | |
Video Editing | Choose the Exact Cut and Framing Inside Each Candidate Take — The Shorts Planner | |
Video Editing | Create a simple two-frame animation for emphasis moments | |
Video Editing | Extract timing cues for placing sound effects on visual beats | |
Video Editing | AI-voiced cold-open narration for every clip — reads the clip's Hook or Title via Qwen3 TTS (EN / KO / auto) | |
Video Editing | Reframe every clip to 9:16 vertical (1080×1920) — four strategies incl. Subject-Aware punch-in for Reels / TikTok / Shorts | |
Video Editing | Auto-mix emotion-matched sound effects timed to each clip's peak moment — reads Video Analysis EDL metadata or falls back to keyword scan | |
Video Editing | Retime every clip in a batch by a single speed factor — audio pitch preserved (no chipmunk voices) | |
Video Editing | Burn karaoke-style word-synced subtitles onto every clip — seven presets, five fonts (CJK-ready), optional bounce animation | |
Video Editing | Cut one time range out of a video — frame-accurate, returns a single clip | |
Video Editing | One-word-at-a-time pop captions burned onto a video, TikTok/Reels ad style |
Last updated: Oct 23rd, 2026
‣