Download this guide as Markdown (for your AI agent)

Version 1 (2026-10-15): the same steps as this page, with every download’s link and checksum. sha256 f4ac8f4d759deac3c97c338ff9259a3d1a1fd189c3a4df2fc5e0c22a7e553be3, also in the manifest.

What you need

  • A creator invitation and the extension, as for every guide.
  • ComfyUI v0.39.0, with the MiniMax H3 models and three more: the Fun ControlNet patch, the Turbo v4 LoRA and Depth Anything 3 (Set up ComfyUI).
  • A 16 GB GPU with 32 GB of system RAM and a pagefile of about 32 GB or more. Close Chrome, OBS, games and other heavy apps while it generates.
  • An image model for the design pictures (FLUX.2, Krea 2 Turbo or Qwen Image 2.1).
  1. List and cutGo to step
  2. Design picturesGo to step
  3. RunGo to step
  4. FinishGo to step
  5. CheckGo to step

1. List and cut the shots

As in Capture and mark your shot:

  • Only the shots with the thing you’re changing, picked by eye (why). Split at every cut.
  • Keep shots with on-screen text original (credits, captions, signs burned into the picture), or start your segment after the credits. A full redraw rewrites the text as garbled names.
  • Size: 1024 × 576 for 16:9, 1024 × 768 for a 4:3 show (crop, never squeeze).
  • Length: the grid value just above your shot’s frame count (124, 141 … 362). The workflow holds the last frame to fill the length.
  • A long shot: one run at 768 × 576 fitted 345 frames (about 14 seconds) in about 13 minutes.
  • Your clip needs a sound track (add a silent one if it has none).

2. Make the design pictures

The pictures decide the result more than any setting.

  1. One main picture of the new creature, ship or effect, made with FLUX.2, Krea 2 Turbo or Qwen Image 2.1. Pick the best of several.
  2. Two or three more views of the same design, made by editing the main picture (side view, close-up, from below).
  3. Cut each out on plain grey: the cut-out workflow (seamless-cutout.json, download) does it from one word, or use any background remover.
  • Color comes from the pictures. Change the picture and the color words in the prompt together; the prompt alone won’t move it.
  • One design per sequence: the same main picture for every shot of the same creature.
  • Extras and crowds, or an establishing view: pictures are optional. Describe the change in the prompt.
The main reference picture, two more views of the same creature and its cut-out on grey
The design pictures: main picture, two views, cut out on grey.

3. Run the workflow

Pick the workflow for what you change and your show’s shape
What you change16:9 show4:3 show
New design (creatures, ships, effects): seamless-upgrade-effects-fullframe.16gb.jsonDownload 1024 × 576Download 1024 × 768
Same design, the shot’s motion held exactly (extras, crowds, views): seamless-upgrade-effects-fullframe-actors.16gb.json. Your shot also goes in as a small reference video.Download 1024 × 576Download 1024 × 768
Inputs to set for each shot
NodeSet it to
Source shotYour cut shot
Pictures 1–3The main cut-out, then the extra views (load Picture 1 again if you have only one)
Prompt, size and lengthThe template below; your shot’s shape; the length
Control end0.5 (as shipped). Raise it toward 0.75–1.0 to hold the shot’s set and motion closer
SeedA new number per take

Leave the rest: 8 steps with the Turbo v4 LoRA, control strength 1.5, reference size match.

Prompt:

  • <Subject 1>: the new design as in Pictures 1–3;
  • <Subject 2>: the scene;
  • summary: “following the given motion exactly”;
  • detailed_description: what it does, as in your shot, “Where only part of it is in frame, only that part is in frame. The camera and the framing stay exactly the same.”
Rebuild a shot prompt template
subject_definitions:
<Subject 1> is the {CREATURE OR OBJECT} shown in <Picture 1>, <Picture 2> and <Picture 3>: {DESIGN: shape, skin or surface, color, distinctive marks}.
<Subject 2> is the scene: {PLACE}, with {WHAT STAYS: the set, the light}.

summary:
[reference generation] A photoreal modern visual effects shot inserted into a {YEAR} television series: <Subject 1> in <Subject 2>, following the given motion exactly.

retention_analysis:
<Subject 1>: fully_preserved design from the pictures, adapted to the scene's lighting.
<Subject 2>: fully_preserved scene geometry, lighting, exposure and camera.

detailed_description:
Realistic {YEAR} live-action television footage with natural film grain. {WHAT IT DOES, as in your shot}. Where only part of it is in frame, only that part is in frame. The camera and the framing stay exactly the same.

overall_soundscape:
{THE SHOT'S SOUND}.

non_diegetic_music:
N/A

Prompt rules from a 12-shot real-episode test (5 of 12 were right at once; the per-shot scene lines and the framing fix were confirmed in a second try):

  • Write the scene line per shot, with only what’s in that shot. One line for the whole sequence (“a rocky forest hillside, a gorge and open blue sky”) put hills, trees and a gorge into shots that showed only sky.
  • Say how many: “exactly one {CREATURE}”. Otherwise a second one can appear. Even with it, one shot in our test still got a second creature: keep the original for that shot.
  • Energy effects: say how long they last (“one short bolt, a fraction of a second”). Without it, a beam was held for about 9 frames; with it, about 6 (the original’s was 2). It helps, but doesn’t get all the way to the original’s length.
  • Describe the framing of each shot: “close-up; the man fills the left of the frame; the creature passes behind him”. In our test a fast close-up became a wide shot, and in a low-angle shot the creature took over the foreground and the actor shrank. The tested fix: a framing line plus control end 0.8, which kept the close-up and the low-angle shot with the actor in front.

Run it: about 4½ minutes for a 5-second shot at 1024 × 576 on a 16 GB card, about 6½ at 1024 × 768. Uses almost all of 32 GB RAM. Close other apps (game launchers, browsers) before you run it, or ComfyUI can be killed partway through.

  • The reference video carries the old design. With the “same design” file, a fast creature came back looking like the original in our test. For a new design, use the first file.
  • A fast creature against a dark background can come out pale or white. Try a new seed; if it’s still pale, keep the original shot (in our test, 4 of 12 shots stayed original after two tries).

4. Finish

As in Finish and conform: the finish workflow (seamless-finish.json, download) trims to your shot’s frame count, plays every frame at the episode’s rate, scales to the Start still and puts the original sound back.

  • Don’t count on prompt words for an era look. On a sky shot rendered three times with the same seed, “film grain / older TV” and “period light” lines changed nothing, by eye or by numbers. Color and brightness came out close to the original (saturation +3%, contrast +13%, brightness −9%). The real gap is sharpness: the new creature had about 2.3× the original’s fine detail; the old creature and sky were soft, with motion blur. A modern design that much sharper can look pasted on.

5. Check

  • Look at every face in the result. The automatic check compares with your source, and can pass a recast face that moves the same way.
  • The new design follows the original: the same path, size in frame and timing. Where only a wing tip was visible, only a wing tip is visible.
  • No new things: no extra animals, people, objects or text.
  • The background: a whole-frame redraw re-imagines it a little. Fine for a fast shot; for a slow one, raise the control end.
  • The flicker check (how). For a fast creature, red round it is its motion; judge red on scenery only. Then watch at full speed.

When it doesn’t work

What you see and what to do
You seeFix
Garbled names or text on screenA full redraw rewrites burned-in text: keep shots with credits or captions original, or start after the credits
A beam or bolt lasts too longSay its duration in the prompt (“one short bolt”). It shortens it (9 → 6 frames in our test), but it can stay longer than the original
The new creature looks like the old oneYou used the file with the reference video: use the new-design file
A fast creature comes out pale against a dark backgroundA new seed; if it’s still pale, keep the original shot
The background changes (different trees, sky or set)Raise the control end toward 0.75–1.0
Hills, trees or a gorge appear in a shot that showed only skyThe scene line came from another shot: write it per shot, with only what’s in that shot
A second creature appearsAdd “exactly one {CREATURE}” to the prompt
The framing changed (a close-up became a wide shot; the creature took over the foreground)Describe the shot’s framing in the prompt (“close-up; the man fills the left of the frame…”), and raise the control end to 0.8
The color is offChange the reference picture and the color words together
It looks too sharp, pasted onThe new element has far more fine detail than old, soft footage (about 2.3× in our test); prompt words don’t change it. Keep the original for shots where it shows
The design changes between shotsThe same main picture for every shot of it
Out of memoryLower the size (768 × 576) before shortening the shot; close other apps