Same moves, new faces. Open ChatGPT Desktop, paste the performer-swap prompt, drop one video and two photos, connect Higgsfield Genjutsu, hit run. Keyword SWAP unlocks this page.
Install or open the ChatGPT Desktop App. In the model picker choose Astra (GPT-6). Do not run this in a thin browser tab if you need the Apps & Connectors panel — Desktop is where Higgsfield attaches. Leave one empty chat ready before you paste anything.
02
02Prompt
Paste the exact performer-swap prompt
Copy the prompt from the code block below word for word. It maps left performer → @Image 1 and right performer → @Image 2, and locks audio, camera, cuts, set, and movement. Do not rewrite the lock lines. Paste once into the chat composer and stop.
03
03Inputs
Drop the video, then Image 1 (left) and Image 2 (right)
Attach the source clip first (any short two-person performance works — hotel lobby, mic stand, interview). Then attach two clear face photos: Image 1 = person who should land on the left, Image 2 = person on the right. Front-facing, well lit, matching the outfits you want kept. Wrong order swaps the wrong faces.
In ChatGPT Desktop go to Settings → Apps & Connectors. Add Higgsfield, paste your API key, confirm Connected. In the model / tool row pick Higgsfield Genjutsu. If Genjutsu is missing, the connector is not live — reconnect the key before you hit run.
05
05Ship
Hit run and QC: same moves, new faces only
Send the message. When Genjutsu finishes, watch once with sound on. Pass only if faces and outfits match the two photos AND every move, cut, and the original audio stay intact. Fail if the camera path drifts or a face melts. Export the keeper and post. That is the 30-minute loop — one clip, two photos, one run.
Hotel Lobby swap prompt · copy paste into ChatGPT Desktop
# Paste this exactly. Attach: source video, then Image 1 (left), Image 2 (right). Swap the two performers in the source video. The person on the left becomes the man in @Image 1, and the person on the right becomes the man in @Image 2. Keep their faces, hair and outfits exactly like the pictures. Keep the original audio, camera moves, cuts, set and every movement exactly the same. Only the characters change.
# Checklist before you hit run # 1. ChatGPT Desktop → model Astra (GPT-6) # 2. Prompt pasted once (no rewrites on the lock lines) # 3. Video attached, then Image 1 = left, Image 2 = right # 4. Apps & Connectors → Higgsfield Connected → Genjutsu selected # 5. Run → QC: same moves, new faces, original audio
Want this running for you?
Build it step by step inside AI Creative OS, with me in the thread.
