Fer Zenth

i recreated this Ricksclip style animation completely in claude + blender it took me a week of researching polishing figuring out and becoming BETTER then the original and as promised im LEAKING the prompt for FREE he got 100M views in the past 30 days averaging 8M views per vid this style is a mix of a 2d character with a 3d background ive seen a few people try to recreate this but they dont end up like the og so how did i make this? -> Install Blender from their Website -> run the installer -> paste the prompt in claude -> generate the script -> make a voiceover using the script and the rest is fully automated chat gpt will build out the scenes in blender using a python script and sends a Windows Batch file ( .bat ) to a folder you specify u just simply double click the Render .bat file no need to even open blender blender will create the full video on your gpu , rendering times depend on your GPU cores the TI series GPU's have a faster render time 1.5-3sec per frame this video in particular was 1900 frames and took me 1.5 hours to render on my GPU anyways here is the free prompt thank me later ↓ <inputs> Ask me for my story, or pitch 3. - A good one is true and little known. Someone does something that looks ridiculous, someone laughs at them, and the reveal flips who was smart: a trick, a scheme, a bluff, a loophole, revenge. - Give each pitch with its first line, the mocker, the twist, and a title that hides the ending. Ask which voice I want: - Free, the default: Kokoro, run locally on the CPU. - Optional upgrade: ElevenLabs with a stock library voice. Tell me the credit cost before you generate anything, and make one take. Ask what GPU I have. Any GPU works: Blender EEVEE renders on all of them, just slower on older cards. Tell me everything else is free: Blender, Python, Playwright with a headless browser, FFmpeg, faster-whisper, Pixabay music and Mixkit sound effects. No image, video or 3D model generator is used anywhere. Then write the script and the beat list with seconds, and show me both before you build anything. </inputs> <direction> A 1080x1920, 30 fps, 55-70 s vertical Short in the style of narrated "true story with a twist" cartoon Shorts: flat 2D cartoon people acting inside lit, dressed 3D toon sets, one storyteller voice, captions of 1-2 words, and one camera that keeps travelling. Sets (Blender, built by a Python script): - Build every place in the story from simple shapes in code (boxes, cylinders, cones, tori, bevelled boxes), never a downloaded model. - Materials: flat toon colours with low roughness, so it reads like a cartoon, not a photo. - Ink outlines: an inverted-hull shell on every object (a Solidify modifier with flipped normals and a dark backface-only material), so the world has the same line as the characters. - Draw surfaces on a canvas and use them as textures: signs, chalkboards, brick, planks, plaques. - Put the story's words inside the world (signs, boards, counters) instead of floating titles. Palette and light: - Pick a warm key against cool shadows for each place. Balance cream, ochre and amber against blue, teal and purple. - Costumes contrast with the set. - Interiors: warm practical lamps plus a soft cool fill. Exteriors: a strong sun, a blue sky and a lighter horizon. - Render with EEVEE, the Standard view transform, a slight lowered exposure, and a soft glow added in the finish. People: - 2D characters are drawn in code (HTML canvas) and exported as transparent images, one per pose and expression. In Blender they sit on camera-facing cards that turn around the vertical axis only. - Use an emission material on the cards so faces stay clean white whatever the lighting. - The look, kept simple: - a big round white head with a thick dark brush outline - big expressive eyes and brows, a small nose, a mouth that changes shape - thin stick legs and chunky flat-colour clothes - one signature prop or accessory each (glasses, a hat, a cigar, a tool) - The face set: smug, grin, shock, laughing, worried, sweat drops. - Pose-to-pose acting: point, hold up a prop, hands on hips, arms up. Blinks and small breathing keep holds alive. - A new, original cast for every video. Show me a character sheet before building. Camera: - One camera that travels between beats. Each beat holds with a slow push, then the camera moves to the next. - Fit every camera key to what it should show: compute the distance so the named faces or props sit fully in frame. - Inserts carry the proof: a close-up on the key object while the change happens. - The payoff is the biggest frame in the video: a reveal coming at the lens. - Soft dissolves or camera moves between places, few hard cuts. Captions: - 1-2 words at a time; short words (a, the, so, to) ride with the next word. - A bold rounded font, white with a thick dark outline, centred in the lower third. - No full stops on screen. Banned: - AI images or video, downloaded 3D models, real logos - a camera that sits still - half-cut faces, legs-only or hat-only frames, empty backgrounds - a time-stretched or whispered voice - more than one or two names the viewer has to remember </direction> <structure> Length: 55-70 s, about 150-200 words. Beat map for a 62 s Short (scale it to your voice): 0-4 s, HOOK: one plain sentence about an act that makes no sense, with the reason hidden. Picture it in one frame. 4-12 s, SETUP: who, where, and what's at stake, with one exact number. 12-20 s, THE MOCKER: a quoted joke line said to the hero. Big close-up. 20-40 s, THE METHOD: it gets weirder in steps. One close-up insert per step. 40-50 s, "YOU SEE,": the trick explained through an everyday thing the viewer has done. 50-62 s, THE PAYOFF and THE TWIST: shown, not explained. The last line is the biggest reveal and calls back to the hook. </structure> <build> 1. Tools (all free): Blender (any recent version), Python 3, Node with Playwright, FFmpeg, faster-whisper, numpy. Install what's missing and tell me what you installed. 2. Script: - Tell it the way a kid tells a friend: plain words, sentences joined with "and" and "so", one funny comparison, no dates or jargon. - Join related sentences with commas, because a voice resets after every full stop and leaves a gap. - Show me the word count and the seconds per line. 3. Voice: - Free route: Kokoro on the CPU, one line per call, joined with short gaps. - Paid route: ElevenLabs, one take, cost stated first. - Only trim silence, never inside a word. Then run faster-whisper on the finished track to get word times. 4. Characters: draw the cast in code, show me a sheet, then export every pose/expression the story needs as transparent WebP. 5. Story timeline: one file that, for any frame, returns the camera (position, look-at, fov, roll), the focus distance, and each character's card, position and scale. Anchor every beat and sound to a word time, never a typed time. 6. Exporter: a headless browser page runs the timeline for every frame and writes frames.json plus the card images and sign textures. 7. Blender scene script (blender -b -P scene.py -- --data data --out frames): - builds every set, light and prop - reads frames.json, places the camera and cards each frame, animates the props - renders JPG frames, skips frames that already exist so it can resume 8. Contact sheet before the full render: stills from the middle of every shot, labelled with time and the line being spoken. I approve or ask for changes. 9. Sound: - Music: one playful bed under a free licence, about 20 dB under the voice. - Effects: real Mixkit sounds placed on the actions (whooshes on camera travels, pops on reveals, impacts, dings). - Duck music and effects under speech. Normalise to -14 LUFS. 10. Finish with FFmpeg: a soft glow (screen-blend a blurred highlight pass at about 0.4 opacity), burned-in captions, the mix, H.264. 11. Give me a one-click .bat (or .sh) that runs the export, the Blender render and the finish. It must refuse to encode if any frame is missing, and never overwrite an older video. 12. Upload text: - Title: "The [thing] That [strange act]", hiding the ending. - Cover: a clean frame of the payoff with no text. </build> <gotchas> Script: - Scripts that read like writing (names, dates, context, the twist in the hook) fall flat. Line 1 is the strange act with the reason hidden. Voice: - Short full-stop sentences make the voice stop-start. Join lines with commas. - Trimming at whisper timestamps clips words. Trim on silence only, with a small guard. Look: - Empty sets read as cheap. Dress every place with props and background detail. - Characters scaled too small look like kids next to tables. Scale them so they stand about 1.9 m against the real-size sets. Camera: - Hand-placed cameras crop faces at 9:16; the frame is narrow. Fit keys to the subjects and scan every frame for cut faces before rendering. - A camera that flies through a wall, a canopy or a post reads as a glitch. Pick another angle or cut. Render: - 3D props attached to a 2D card must follow the card's turn, or they drift off the drawn body. - A render that stops early (sleep, crash) must not be encoded into a short video. Check the frame count first. - Turn off PC sleep before a long render. Sound: - Music only a few dB under the voice makes the narrator hard to hear. Keep it low and measure. </gotchas> <start> Ask me for my story, or pitch 3. Then show me the script (word count and seconds per line) and the beat list before any voice is generated or any scene is built. </start>