Quick answer
"Beans, greens, potatoes, tomatoes, lamb, rams, hogs, dogs, chicken, turkeys, rabbits, you name it!" is a line from gospel singer Pastor Shirley Caesar's song "Hold My Mule", where she rattles off a whole Thanksgiving spread. A remix made it the #UNameItChallenge in 2016, and it goes viral again every November as the Thanksgiving meme. Starrd's Beans Greens Potatoes Tomatoes template puts you on the mic: photo 1 preaches the menu, lip-synced word by word to the original voice, photo 2 laughs in the crowd and photo 3 nods along behind you. Only photo 1 is required, and pets work in any part. 1 to 3 photos, 18 seconds, vertical 9:16, 200 credits (about $10).
"Beans, greens, potatoes, tomatoes, lamb, rams, hogs, dogs, chicken, turkeys, rabbits, you name it!" is a line from Pastor Shirley Caesar that reads a Thanksgiving menu like scripture, and every November it's the Thanksgiving meme again. Here's where it comes from, and how to put yourself on the mic from one photo:
Where "Beans, Greens, Potatoes, Tomatoes" Comes From
The line is from Pastor Shirley Caesar's gospel song "Hold My Mule". In the middle of the story she lists everything on the table, dish after dish, dead serious: "beans, greens, potatoes, tomatoes, lamb, rams, hogs, dogs, chicken, turkeys, rabbits, you name it!"
In 2016 a remix turned it into the #UNameItChallenge. Since then it comes back every Thanksgiving: posted before dinner, laid over a shot of the spread, or acted out by the family.
The clip most people share is live church footage: the speaker on the mic with a man right behind her, cut against a woman in the crowd laughing and a man shading his eyes to look. This template follows the version posted on TikTok by @80sbabybut90sraisedme on November 1, 2023, tagged #thankgivingdinner, all 17.6 seconds of it.
Why it works with you in it: the joke is the delivery, not the person. Anyone at the microphone, in their own outfit, preaching a menu like scripture, is funny, and the cutaways need nothing but a laugh.
Star in It
Eighteen seconds, eleven shots, one sacred menu. One photo puts you on the mic; up to two friends take the crowd.
Beans Greens Potatoes Tomatoes
You preach the whole Thanksgiving menu into the mic while friends laugh and nod along. 1 to 3 photos, 18 seconds.
What You Get
- The whole meme in 18 seconds: "Beans, greens, potatoes, tomatoes, lamb, rams, hogs, dogs, chicken, turkeys, rabbits, you name it!", twice through.
- You on the mic, from photo 1, preaching dead serious.
- Up to two friends: photo 2 laughs out loud in the crowd, photo 3 stands behind you nodding along. Skip them and AI strangers fill in.
- Word-by-word lip sync in the original voice, mouth shut between the dishes.
- Your own faces and outfits in every shot.
- Every cut where the clip cuts. Ten hard cuts, cropped to vertical on whoever is on screen.
- Pets in any part.
- The original sound.
The 18 Seconds
| Time | Shot | Who is on screen |
|---|---|---|
| 0.0s | "Beans, greens, potatoes, tomatoes, lamb, rams..." into the mic | You, with photo 3 behind you |
| 3.6s | Head tipped back, laughing out loud | Photo 2 |
| 5.5s | Leaning in: "...rabbits, you name it!" | You |
| 6.9s | Shading the eyes to look out over the crowd | A stranger |
| 7.5s | "Look!" then a turn to the side | You |
| 8.4s | "I got beans, greens, potatoes, tomatoes, lamb, rams, hogs..." | You, with photo 3 behind you |
| 13.0s | Still laughing | Photo 2 |
| 14.4s | "...greens, potatoes, tomatoes, chicken..." | You, with photo 3 behind you |
| 15.9s | Still laughing | Photo 2 |
| 16.7s | "...rabbits..." | You |
| 17.1s | Close: "you name it!", hand on the chest | You |
Your Look
Everyone's face and clothes come from their own photo: the same hair, glasses, facial hair and outfit in every shot. Nobody gets the original speaker's burgundy blazer.
The roles go by photo order, not by who you are: photo 1 is always on the mic, photo 2 always laughs, photo 3 always stands behind. Swap the photos to swap the parts.
Pets: a pet on the mic holds it in its front paws and barks out the menu with its own mouth. A pet in the crowd throws its head back in an open-mouthed grin. If every photo is a pet, the AI strangers are animals too.
Use a clear, front-facing photo for the one on the mic. Most shots are chest-up close-ups, so that face fills the screen for more than half the video.
The Fastest Way
Beans Greens Potatoes Tomatoes
One photo on the mic, up to two friends in the crowd. 'You name it!', lip-synced. 18 seconds.
One to three photos, 200 credits (about $10), no prompt. Vertical 9:16, 480p, 18 seconds, with the original sound. People or pets. Find it in Comedy & Viral.
Build It Yourself
1. Time every word. The menu is delivered in short bursts, one dish at a time. Write down when each word starts and stops by frame, and which face is on screen for every range. The voice keeps going over the cutaways, so note that nobody on screen says it there.
2. Make one reference sheet. A single image with the empty church on top, then a front, three-quarter, side and back view of each person, keeps the faces and outfits steady across the cuts.
Image 1, Image 2 and Image 3 are photos of three subjects. Make a photoreal vertical character reference sheet in four bands separated by thin black lines. Top band: a packed church with wooden pews and a standing congregation, nobody close to the camera. Then one band per subject, full length, from the front, three-quarter, side and back, each in their own outfit from their photo. Same faces and hair in every panel. The church softly out of focus behind them. No text.
3. Drive a video model with the clip. Feed the sheet, your photos and the clip to a model that copies motion from a reference video, say who is on screen in each shot, and give every word its start and stop time. Starrd's Character Swap does the swap on your own clip.
Common Mistakes
The one laughing mouths the menu. The voice plays over the crowd shots. If the model hears it there, the laugher lip-syncs it. Mute the voice in the reference clip for those shots and keep it in the final sound.
A landscape clip in a vertical video. The original is a wide strip inside a tall frame. Crop each shot to vertical on whoever is on screen, or everyone ends up tiny.
A pet that turns into a person. Every shot is a chest-up human close-up, and a pet copies the head and hands. Soften the heads and hands in a separate reference clip for pets.
The original speaker's blazer. The clothes in the clip carry over unless you say that everyone wears their own outfit.
Related Reading
- How to Make the 'I Be Thinking Bout My Bills' AI Video: another meme for you and up to two friends, with AI strangers in empty seats
- How to Make the 'Deep Down In My Heart' AI Video: a two-photo meme, lip-synced
- How to Make the 'Cardo, Your Dinner Is Ready' AI Video: another dinner-table meme
- How to Make 'The Hot Chick' Ice Cream Scene AI Video: a two-photo movie scene, people or pets
- How to Put Yourself in Any Video With AI: character swap on your own clip
- Viral AI Video Trends 2026: every trend we've turned into a template this year
