PAGES31
WORDS72,443
SOURCES307
READ TIME162 min
TYPEHUB
CHECKED25 AUG 26
One of the larger topics on this site. Everything here about making images and video with AI, from the vocabulary through to the models that render it.
The vocabulary
Camera grammar predates AI and does not expire when a model ships.
COMPARISON · 13 MIN · 39 SOURCESFree vs Paid AI Image, Video and Music Tools: What the Free Plan Really AllowsWhat the free plans of Midjourney, Suno, Udio, Runway, Kling, Gemini, Grok and others allow: credits, watermarks, downloads and commercial use.EXPLAINER · 13 MIN · 33 SOURCESFLUX 3: Black Forest Labs’ First Video Model, Prices and LimitsFLUX 3 makes clips of up to 20 seconds with sound. What one costs from 720p to 4K, how that compares with Veo, Omni and Grok, and what the terms allow.COMPARISON · 11 MIN · 25 SOURCESSeedance 2.5 vs 2.0: What a Clip Actually CostsOn ByteDance’s API a Seedance 2.5 clip costs about 1.5 times a 2.0 clip. Token billing explained, 5 s and 10 s prices by resolution, and the 4K question.COMPARISON · 14 MIN · 23 SOURCESWhich AI Image Model for Which Job: Vendor Claims and Prices ComparedChatGPT Images, Nano Banana, Midjourney, FLUX.2, Seedream, Grok Imagine and Muse Image compared by job, using each vendor’s own claims and per-image prices.DATED · 3 MIN · 3 SOURCESThe Sora API Shuts Down on 24 September 2026OpenAI is removing the Videos API and every Sora 2 model, and its own table names no replacement. What goes, what breaks, and where the alternatives are.COMPARISON · 4 MIN · 4 SOURCESVeo 3.1 vs Gemini Omni vs Grok Imagine VideoVeo, Gemini Omni and Grok Imagine Video, compared on what each vendor publishes about length, resolution, price and watermarking — and what none will say.EXPLAINER · 3 MIN · 3 SOURCESHow Much Does a Veo 3.1 Video Cost?Google prices Veo 3.1 per second, from 5 cents to 60, with no free tier. The full table, what one clip costs, and how to spend less.EXPLAINER · 2 MIN · 2 SOURCESWhere Whisk and ImageFX Went: Google Flow, ExplainedGoogle folded Whisk and ImageFX into Flow on 25 February 2026. Both old addresses redirect, projects can be transferred, and images are made inside Flow.THE CRAFT · 3 MINCamera GrammarTwenty-four shot types in five families — angle, distance, movement, focus, composition — what each reads as, and why naming the shot beats describing a mood.EXPLAINER · 4 MINThe Anatomy of an AI Video PromptHow to structure an AI video prompt that works. Bracket format, motion-first ordering, identity lock, camera specification — builtEXPLAINER · 4 MINColor, Light & Mood: The Visual Language of AI GenerationHow to name light sources, describe color grades, and reference visual mood in AI prompts. Director references, film stocks, namedEXPLAINER · 3 MINAspect Ratio, Resolution & Format: The Technical Decisions That Change EverythingWhen to use 16:9 vs 9:16 vs 1:1, how resolution affects AI generation quality, and the correct export format for TikTok, Instagram
Consistency and control
The hard part is not one good frame. It is the second one matching.
EXPLAINER · 6 MINCharacter Consistency in AI: Images, Video & StoryboardsEvery method for keeping AI characters consistent — seed locking, IP-Adapter, reference images, identity lock, Higgsfield Studio rEXPLAINER · 4 MINHow to Use Reference Images in AI GenerationReference images are the most powerful technique in AI generation. How to use IP-Adapter, img2img, and identity lock — and why theTHE CRAFT · 1 MIN · 6 SOURCESNegative Prompt LibraryCopy-ready negative prompts by use case — and the four major models that ignore them entirely.DATED · 4 MINThe Best Negative Prompts for Every AI Model — Copy and PasteCopy-ready negative prompts, and which models actually read them: ChatGPT Images 2.5, FLUX.2, Midjourney v8.2, Kling 3.0, Seedance 2.5, Runway and LLMs.EXPLAINER · 8 MINUltra-Detailed Upscale Prompts: 25 Variations for Every Vibe25 AI upscale and img2img prompt variations — cinematic, editorial, cyberpunk, Renaissance, documentary, old photo restoration, and video.
How the work is actually made
Process, not prompts.
EXPLAINER · 5 MINHOW AI FILMS ARE MADEAI video that looks generic is not a model problem, it is a preparation problem.EXPLAINER · 4 MINHow to Build an AI Content Pipeline: Idea to Published PostComplete end-to-end AI content workflow: concept to persona, image generation, video, voiceover, caption, and publish. Built from EXPLAINER · 5 MINThe AI Influencer Playbook: Build a Persona, Create Content, Get PaidHow to build an AI influencer from scratch — persona creation with APOB AI, video with Higgsfield Studio, audience growth on TikToDATED · 11 MINHow to Start an AI Influencer for Free (and When You Will Need to Pay)Build and launch a complete AI influencer without spending money. Persona design, free image generation, video production, voiceovDATED · 7 MINHiggsfield MCP + Claude: Make Motion Design Ads With AIHow to connect Claude to Higgsfield’s MCP server to make short motion design ads: setup, prompts, how the workflow runs, and a sober look at the income claims.
Models and platforms
Dated, because this section ages fastest.
THE CRAFT · 20 MIN · 7 SOURCESModel GuidesAround twenty models and studios with their optimal prompt format — ChatGPT Images 2.5, Seedance, Kling, FLUX, Midjourney, Suno, ElEXPLAINER · 4 MINUnderstanding AI Model Types: Image, Video, Audio & LLM ExplainedWhat each type of AI model does, what it cannot do, and how image, video, audio, and LLM models work together in a production pipeEXPLAINER · 8 MINAI Studios & Aggregators: Every Platform ExplainedComplete 2026 guide to AI studios. Higgsfield, APOB AI, Glam AI, Agent Opus, InVideo AI with Agent One, Imagine Art, OpenArt AI, aTHE CRAFT · 4 MIN · 1 SOURCESBad, Good, GreatThe same goal written three ways. The fastest way to see what actually separates an amateur prompt from a production one.EXPLAINER · 3 MINThe AI Tools Atlas: the landscape by job, not by logoThe AI tool landscape mapped by what you are trying to do: assistants, coding agents, image, video, voice, answer…
Prompts and method
Tested where a date exists, reviewed where it does not.
THE CRAFT · 34 MINThe Prompt VaultThirty-nine production prompts for image, video, LLM and pre-production work — four with a test date, the rest reviewed, all copy-ready.THE CRAFT · 13 MIN · 2 SOURCESPrompting Cheat SheetsFour reference sheets — image, video, LLM and AI studios. Lighting, cameras, formats, and the rules that survive a model release.THE CRAFT · 4 MINReverse PromptingFeed any AI output back to a model and reconstruct the prompt behind it — then improve on it. Works on images, video and text.EXPLAINER · 4 MINThe CARE Framework: Context, Anchor, Restrict, ExemplifyA four-part AI prompting framework that works first time. CARE — Context, Anchor, Restrict, Exemplify — applied to image, video, a