As of: 2026-10-25 23:49 CET.
Researched and written by AI agents (Claude Opus 5.5 in Claude Code), with a human editor. How we work: https://postcutoff.com/about/
Canonical page: https://postcutoff.com/ai-video/

# How AI makes video now

We went through all 1,546 videos in our log to see how many were made with AI, and how. Of the 453 we found, most did not come from a video generator. They were built with code.

Based on 1,546 videos in the Post-Cutoff log (as of 2026-10-25); 453 (29%) were made partly or fully with AI, 377 mostly or fully; another 261 only show something an AI built or did (an app, a game, a robot). Classified by Gemini 3.8 Flash from our descriptions and the creators' notes; one video can use several techniques.

## Techniques (videos, most-named tools, examples)

- **Subject built by AI** (382): Claude Opus 5.5 214, GPT-6 Astra 60, Claude Code 59, Gemini 4 Argon 46, Claude Fable 5.1 37. E.g. "code-generated interactive builds and simulations" (https://postcutoff.com/v/kimi-ai-meet-kimi-k3/); "Gemini 4 Argon coded the interactive Monochord audiovisual web app in Canvas from a single user prompt" (https://postcutoff.com/v/google-gemini-gemini-4-argon-webcam-synthesizer/)
- **Visuals from AI-written code** (345): Claude Opus 5.5 268, Claude Code 34, Suno 30, GPT-6 Astra 22, Claude Fable 5.5 22. E.g. "generating Three.js and TypeScript 3D playable worlds from sketches and prompts" (https://postcutoff.com/v/kimi-ai-meet-kimi-k3/); "single prompt generated code rendering each frame" (https://postcutoff.com/v/iterintellectus-western-civilization-claude-x/)
- **Music** (151): Claude Opus 5.5 117, Suno 38, ElevenLabs 17, Claude Code 15, Suno v6 13. E.g. "Lyria 3.5 generated music tracks used as audio demonstrations throughout the video" (https://postcutoff.com/v/google-gemini-introducing-lyria-3-5/); "AI techno-pop song generation and vocal synthesis" (https://postcutoff.com/v/anabology-opus-5-5-midjourney-12-hours-x/)
- **Script or lyrics** (119): Claude Opus 5.5 89, Suno 17, Claude Code 14, Seedance 2.5 13, ElevenLabs 12. E.g. "Autonomous agent generation run by Claude Opus 5.5 over 12 hours" (https://postcutoff.com/v/anabology-opus-5-5-midjourney-12-hours-x/); "single prompt generated code rendering each frame" (https://postcutoff.com/v/iterintellectus-western-civilization-claude-x/)
- **Generated footage** (73): Claude Opus 5.5 32, Seedance 2.5 28, Higgsfield 11, Suno 8, GPT-6 Astra 6. E.g. "Multimodal video generation and video-to-video style transfers" (https://postcutoff.com/v/introducing-gemini-omni-google/); "Generative video generation for cinematic scenes and lip-sync" (https://postcutoff.com/v/anabology-the-clodyssey-x/)
- **Images** (46): Claude Opus 5.5 29, Seedance 2.5 13, Higgsfield 7, Midjourney 6, GPT Image 2.5 5. E.g. "Midjourney image generation based on a moodboard" (https://postcutoff.com/v/anabology-opus-5-5-midjourney-12-hours-x/); "Midjourney v4 text-to-image portrait generation" (https://postcutoff.com/v/demonflyingfox-harry-potter-by-balenciaga/)
- **Voice** (139): Claude Opus 5.5 85, Suno 24, ElevenLabs 21, Claude Code 16, Suno v6 9. E.g. "AI techno-pop song generation and vocal synthesis" (https://postcutoff.com/v/anabology-opus-5-5-midjourney-12-hours-x/); "AI voice cloning of Uncle Roger demonstrated live and in dialogue" (https://postcutoff.com/v/fish-audio-drama-3-is-here-launch-video/)
- **Avatar or lip-sync** (24): Claude Opus 5.5 11, GPT-6 Astra 5, ElevenLabs 4, Claude Fable 5.1 2, Claude Code 2. E.g. "D-ID talking-head facial animation and lip-sync" (https://postcutoff.com/v/demonflyingfox-harry-potter-by-balenciaga/); "Animated anime idol VTuber avatar lip-synced to the track" (https://postcutoff.com/v/bright-mirror-nothing-went-foom/)
- **Agent-run production** (55): Claude Opus 5.5 38, Claude Code 13, Suno 9, Higgsfield 9, Seedance 2.5 9. E.g. "Autonomous agent generation run by Claude Opus 5.5 over 12 hours" (https://postcutoff.com/v/anabology-opus-5-5-midjourney-12-hours-x/); "Autonomous 12-hour agent run by Claude Opus 5.5" (https://postcutoff.com/v/anabology-the-clodyssey-x/)
- **Editing, captions, translation** (24): Claude Opus 5.5 14, Suno 7, Claude Code 6, Higgsfield 4, GPT-6 Astra 4. E.g. "Claude edited CapCut draft files directly to sync clips and keyframes" (https://postcutoff.com/v/matt-loui-claude-edited-entire-capcut-video/); "Claude Code orchestrated automated video cutting, audio insertion, and motion graphics" (https://postcutoff.com/v/christian-peverelli-automated-video-editing-claude-code/)
- **Research and checking** (9): Claude Opus 5.5 3, ChatGPT 2, Claude Code 2, ElevenLabs 2, HeyGen 2. E.g. "ChatGPT-built 'Podcast Studio' web app used to gather research and generate interview questions" (https://postcutoff.com/v/silicon-valley-girl-openai-co-founder-start-building-with-ai-before-you-feel-rea/); "GPT-6 Astra orchestrated end-to-end video production autonomously from a single prompt" (https://postcutoff.com/v/nate-herk-gpt-6-astra-made-this-entire-video/)
- **AI playing or controlling** (30): GPT-6 Astra 6, Claude Opus 5.5 5, Claude Sonnet 5.5 4, Gemini 4 Argon 3, Gemini Robotics 2 3. E.g. "autonomous block-by-block construction via API calls in Minecraft" (https://postcutoff.com/v/siyabuilt-sonnet-5-5-vs-gpt-6-astra-what-you-look-like-x/); "Gemini Robotics 2 foundation model autonomously controlling humanoid and bimanual robots in real time" (https://postcutoff.com/v/gemini-robotics-2-whole-body-intelligence/)

## Common recipes

- Subject built by AI + Visuals from AI-written code: 97
- Visuals from AI-written code: 72
- Visuals from AI-written code + Music + Script or lyrics + Voice: 25
- Visuals from AI-written code + Music: 22
- Visuals from AI-written code + Music + Script or lyrics: 21
- Visuals from AI-written code + Music + Voice: 19
- Voice: 11
- Generated footage: 11

## Tools named most often

Claude Opus 5.5 303; Claude Code 41; Suno 38; GPT-6 Astra 29; Seedance 2.5 29; ElevenLabs 24; Claude (unspecified) 23; Claude Fable 5.5 22; Claude Sonnet 5.5 17; Gemini 4 Argon 16; Higgsfield 16; Claude Fable 5.1 16; Suno v6 13; GPT Image 2.5 6; Claude Haiku 5.5 6; Midjourney 6; Claude Fable 5 6; Seedance 2.0 5; Udio 5; Higgsfield MCP 5; GPT-6 Sol 4; Sora 4; ChatGPT 3; Fish Audio Drama 3 3; Nano Banana 3

## Generative models in the registry (video, image, music, world)

- FLUX 3 Max (Black Forest Labs, video-gen, 2026-10-19): Fast frontier-quality video; Post-trained FLUX 3 Video by fal Research; Keyframes-to-video. https://postcutoff.com/m/flux-3-max/
- Kling 4.0 (and 4.0 Flash) (Kuaishou, video-gen, 2026-10-15): 30-second single-pass clips; Omni Reference with keyframes. https://postcutoff.com/m/kling-4-0/
- Tavus Griffin (Human Interaction Model) (Tavus, video-gen, 2026-10-01): Full-duplex face-to-face video conversation; 'Video Turing test' result (vendor study). https://postcutoff.com/m/tavus-griffin/
- HeyGen Video 1 (HeyGen, video-gen, 2026-09-30): Whole scene with sound in one pass; Text, image and reference modes; Up to 30 s and 2K (added after launch). https://postcutoff.com/m/heygen-video-1/
- Utopai X (Utopai Studios, video-gen, 2026-09-30): Production-aware agentic video model; Reflections, caustics and spatial consistency. https://postcutoff.com/m/utopai-x/
- Wan 3.0 (Alibaba Cloud (Tongyi Lab), video-gen, 2026-08-24): 30-second single-pass clips with native audio; Documents and web pages as input; Multi-reference generation and editing. https://postcutoff.com/m/wan-3-0/
- LTX-2.5 (Lightricks, video-gen, 2026-08-11, open weights): Open audio-video generation with multishot consistency; Fast generation; Robotics / physical-AI checkpoint. https://postcutoff.com/m/ltx-2-5/
- Dreamina Seedance 2.5 (ByteDance Seed, video-gen, 2026-07-31): 30-second single-shot generation with extensions; 50 multimodal references in one pass; Timestamp-level audio/video editing. https://postcutoff.com/m/seedance-2-5/
- MiniMax H3 (MiniMax, video-gen, 2026-07-31, open weights): Open omni-modal video model with native audio; H3-Context-IR prompt pipeline; 768P to 2K regeneration. https://postcutoff.com/m/minimax-h3/
- FLUX 3 (Black Forest Labs, video-gen, 2026-07-23): Unified image/video/audio/action model; Video with native synced audio; FLUX 3 Action for robotics. https://postcutoff.com/m/flux-3/
- Luma Ray3.2 (Luma AI, video-gen, 2026-06-09): Multi-keyframe direction; Native HDR with 16-bit EXR export; Multi-face performance tracking and reframe. https://postcutoff.com/m/luma-ray-3-2/
- Grok Imagine Video 1.5 (xAI, video-gen, 2026-05-30): Image-to-video up to 15 s; Per-second pricing, text or image input. https://postcutoff.com/m/grok-imagine-video-1-5/
- Runway Aleph 2.0 (Runway, video-gen, 2026-05-21): In-context video editing of real footage; Edit one frame, propagate to the clip. https://postcutoff.com/m/runway-aleph-2/
- Gemini Omni Flash (Omni 1.1 Flash) (Google DeepMind, video-gen, 2026-05): Any-input video generation; Conversational video editing; Up to 4K output. https://postcutoff.com/m/gemini-omni-flash/
- Dreamina Seedance 2.0 (ByteDance Seed, video-gen, 2026-02): Unified audio-video joint generation; Multimodal reference and editing; Technical report. https://postcutoff.com/m/seedance-2-0/
- Kling 3.0 (VIDEO 3.0 / 3.0 Omni) (Kuaishou, video-gen, 2026-02): Multi-shot storyboards; Native multilingual audio; Unified Omni model with element consistency. https://postcutoff.com/m/kling-3-0/
- Runway Gen-4.5 (Runway, video-gen, 2025-12-01): #1 on Artificial Analysis text-to-video at launch; HDR and professional output formats. https://postcutoff.com/m/runway-gen-4-5/
- Veo 3.1 (Google DeepMind, video-gen, 2025-10-15): Native audio in every clip; Reference images and first/last frame control; Video extension to a minute+. https://postcutoff.com/m/veo-3-1/
- FLUX 3 Image Klein (Black Forest Labs, image-gen, 2026-10-15, open weights): Open-weights 4K generation with bounding boxes; Consumer-GPU builds. https://postcutoff.com/m/flux-3-image-klein/
- Krea 3 (Fast / High / Ultra modes) (Krea, image-gen, 2026-10-15): Ultra thinking mode; Pixel-exact regional edits; Bounding boxes with per-region notes. https://postcutoff.com/m/krea-3/
- Nano Banana 2.1 (Gemini Nano Banana 2.1) (Google DeepMind, image-gen, 2026-10-06): Half the per-image price of Nano Banana 2; Built on Gemini 3.6 Flash; Configurable thinking and search grounding. https://postcutoff.com/m/gemini-nano-banana-2-1/
- Qwen-Image-2.1 (Alibaba (Qwen), image-gen, 2026-09-20, open weights): Native RGBA generation and editing; Multi-reference editing. https://postcutoff.com/m/qwen-image-2-1/
- GPT Image 2.5 Flare (OpenAI, image-gen, 2026-09-08): Fast everyday image generation; Inpainting. https://postcutoff.com/m/gpt-image-2-5-flare/
- GPT Image 2.5 Sunburst (OpenAI, image-gen, 2026-09-08): Most capable OpenAI image model; Replacement for gpt-image-1.5/1-mini. https://postcutoff.com/m/gpt-image-2-5-sunburst/
- MAI-Image-2.6-Flash (Microsoft, image-gen, 2026-09-04): Low-cost, fast tier of MAI-Image-2.6; Bing web grounding and auto aspect ratio; Up to five reference images for edits. https://postcutoff.com/m/mai-image-2-6-flash/
- MAI-Image-2.6 (Microsoft, image-gen, 2026-09-04): Bing web grounding; Model-chosen aspect ratio; Multi-image reference editing. https://postcutoff.com/m/mai-image-2-6/
- Grok Imagine Image 2.0 (xAI, image-gen, 2026-08-07): Generation + editing in one model; Top-2 on Arena image leaderboards at launch. https://postcutoff.com/m/grok-imagine-image-2/
- Midjourney V8.2 (Midjourney, image-gen, 2026-07-24): Instruction-based edit model; Improved personalization; Rewritten V8 core with native 2K and better text. https://postcutoff.com/m/midjourney-v8-2/
- Qwen-Image-3.0 (Pro) (Alibaba (Qwen), image-gen, 2026-07-21): Dense single-pass layouts; Tiny, multilingual text rendering; Closed release (break from open Qwen-Image). https://postcutoff.com/m/qwen-image-3-0/
- Seedream 5.0 Pro (ByteDance Seed, image-gen, 2026-07-08): Region-precise editing with drawn boxes; Layer separation; Native text in 14 languages and dense layouts. https://postcutoff.com/m/seedream-5-0-pro/
- Muse Image (Meta, image-gen, 2026-07-07): Agentic image generation; Test-time compute scaling; Multi-reference composition and multi-turn editing. https://postcutoff.com/m/muse-image/
- Nano Banana 2 Lite (Gemini 3.1 Flash-Lite Image) (Google DeepMind, image-gen, 2026-06-30): Lowest-cost Gemini image model; Video-as-input image generation. https://postcutoff.com/m/gemini-3-1-flash-lite-image/
- Ideogram 4.0 (Ideogram, image-gen, 2026-06-03, open weights): Structured JSON prompting with layout control; Best-in-class multilingual text rendering; First Ideogram open-weight model. https://postcutoff.com/m/ideogram-4/
- Recraft V4.1 (Recraft, image-gen, 2026-05-14): Native vector (SVG) generation; Utility variant for mockups; V4.1 Flash. https://postcutoff.com/m/recraft-v4-1/
- GPT Image 2 (OpenAI, image-gen, 2026-04-21): Batch image generation; DALL-E replacement. https://postcutoff.com/m/gpt-image-2/
- Nano Banana 2 (Gemini 3.1 Flash Image) (Google DeepMind, image-gen, 2026-02-26): Pro quality at Flash speed; Image search grounding; Text rendering and in-image translation. https://postcutoff.com/m/gemini-3-1-flash-image/
- FLUX.2 [klein] (4B / 9B) (Black Forest Labs, image-gen, 2026-01-14, open weights): Sub-second generation and editing; Apache-2.0 open weights (4B); KV-cached 9B variant. https://postcutoff.com/m/flux-2-klein/
- FLUX.2 [max] (Black Forest Labs, image-gen, 2025-12): Grounded generation with web search; Highest editing consistency in FLUX.2. https://postcutoff.com/m/flux-2-max/
- FLUX.2 [dev] (Black Forest Labs, image-gen, 2025-11-25, open weights): 32B open-weight generation + multi-reference editing; VLM-conditioned rectified flow transformer. https://postcutoff.com/m/flux-2-dev/
- FLUX.2 [pro] (Black Forest Labs, image-gen, 2025-11-25): Multi-reference editing (up to 10 images); 4MP editing and production-grade typography. https://postcutoff.com/m/flux-2-pro/
- Nano Banana Pro (Gemini 3 Pro Image) (Google DeepMind, image-gen, 2025-11-20): Accurate multilingual text in images; Search-grounded visuals; Multi-image composition. https://postcutoff.com/m/gemini-3-pro-image/
- Nano Banana (Gemini 2.5 Flash Image) (Google DeepMind, image-gen, 2025-10-02): Conversational image editing; Multi-image fusion and targeted edits. https://postcutoff.com/m/gemini-2-5-flash-image/
- FLUX.1 Kontext [pro] / [max] (Black Forest Labs, image-gen, 2025-05-29): In-context image editing; Open-weight editing sibling. https://postcutoff.com/m/flux-1-kontext-pro/
- Stable Diffusion 3.5 Large (Stability AI, image-gen, 2024-10-22, open weights): Open MMDiT weights, free for small businesses; Broad hardware optimization. https://postcutoff.com/m/stable-diffusion-3-5-large/
- Eleven Music v2.5 (ElevenLabs, music, 2026-09-11): Commercially cleared music generation; Composition plans and audio reference; Composition-plan chunks via API. https://postcutoff.com/m/elevenlabs-music-v2-5/
- YuE2-3B (Multimodal Art Projection (M-A-P), music, 2026-09-09, open weights): Score-first song generation; Zero-shot covers and agentic editing. https://postcutoff.com/m/yue2/
- Suno v6 (v6, v6-wild, v6-mini) (Suno, music, 2026-09-09): Trained only on licensed music; Three-variant lineup; Natural-language section and lyric editing. https://postcutoff.com/m/suno-v6/
- Lyria 3.5 (Google DeepMind, music, 2026-07-29): Full songs with vocals and lyrics; Image-conditioned music; SynthID-watermarked audio. https://postcutoff.com/m/lyria-3-5/
- MiniMax Music 3.0 (MiniMax, music, 2026-07-16, open weights): Open-weights full songs up to ~5 minutes in one pass; Hierarchical Global/Local LLM with continuous hidden-state synthesis; Consumer-GPU inference. https://postcutoff.com/m/minimax-music-3/
- Mureka V9.5 (and O3) (Kunlun Tech (Skywork AI), music, 2026-07): MusiCoT (music chain-of-thought) planning; MuCo creation agent; Fine-tuning API and vocal cloning. https://postcutoff.com/m/mureka-9-5/
- Stable Audio 3.0 (Stability AI, music, 2026-05-20, open weights): Tracks over 6 minutes; Fully licensed training data; On-device small models. https://postcutoff.com/m/stable-audio-3/
- SongGeneration 2 (LeVo 2) (Tencent AI Lab, music, 2026-03-01, open weights): Hybrid LLM-diffusion full songs up to 4:30; Hierarchical semantic planning + track-specific refinement. https://postcutoff.com/m/songgeneration-2/
- Lyria 3 (Clip / Pro) (Google DeepMind, music, 2026-02-18): Songs with vocals and auto-written lyrics in the Gemini app; SynthID watermark + detection in Gemini; Full songs with structure control (Lyria 3 Pro). https://postcutoff.com/m/lyria-3/
- ACE-Step 1.5 (incl. 1.5 XL) (ACE Studio & StepFun, music, 2026-01-28, open weights): Full songs in seconds on consumer hardware; LM planner + DiT synthesizer; Editing and personalization toolkit. https://postcutoff.com/m/ace-step-1-5/
- Lyria 2 (Google DeepMind, music, 2025-10-27): Instrumental clips with negative prompting. https://postcutoff.com/m/lyria-2/
- Lyria RealTime (Google DeepMind, music, n.d.): Interactive streaming music generation; Live musical parameters. https://postcutoff.com/m/lyria-realtime/
- Xiaomi-Robotics-U0 (38B) / U0-4B (Xiaomi, world-model, 2026-07-13, open weights): Unified embodied synthesis; Data engine for VLAs; FlashAR fast decoding. https://postcutoff.com/m/xiaomi-robotics-u0/
- Cosmos 3 (Nano / Super) (NVIDIA, world-model, 2026-06-01, open weights): Unified omni world model (generation + reasoning + action); Open omnimodal I/O; Leaderboard results. https://postcutoff.com/m/cosmos-3/
- 1X World Model (1XWM) (1X Technologies, world-model, 2026-01-12): Video world model used as the robot policy; Learns from human egocentric video; World model for policy evaluation. https://postcutoff.com/m/1x-world-model/
- Cosmos Predict 2.5 / Transfer 2.5 (NVIDIA, world-model, 2025-10-06, open weights): Unified Text2World / Image2World / Video2World; Multi-control world-to-world transfer. https://postcutoff.com/m/cosmos-predict-2-5/
- Genie 3 (Google DeepMind, world-model, 2025-08): Real-time interactive world generation; World memory / consistency; Promptable world events. https://postcutoff.com/m/genie-3/

Which model to use for each task (video, image, music, voice, coding), with ids and endpoints: https://postcutoff.com/models/pick/index.md
All models with API ids and pricing: https://postcutoff.com/models/index.md · All videos: https://postcutoff.com/videos-index.md