ComfyUI Node
BFS H3 Character Swap Conditioning
MiniMax H3 Character Swap conditioning. keyframe pins: the source video plus one Add Guide per edited keyframe. normal map guide / DWPose guide: the marked guide from BFS Video Segment Picker, subjects 1-4 = red, blue, green, yellow = Picture 1-4. The Pictures as references and the matching prompt.
BFS H3 Character Swap Conditioning
- clip
- vae
- guide_video
- picture_1
- picture_2
- picture_3
- picture_4
- model
- keyframes
- keyframe_1
- keyframe_2
- keyframe_3
- keyframe_4
- keyframe_5
- keyframe_6
- keyframe_7
- keyframe_8
- model
- positive
- latent
- prompt
- keyframe_video
- pictures
◄width—►
◄height—►
◄length—►
◄modekeyframe pins►
◄keyframe_until0.70►
◄keyframe_until_dropskeyframes only►
◄prompt_override►
◄keyframe_spec—►
◄time_10.00►
◄time_21.00►
◄time_32.00►
◄time_43.00►
◄time_54.00►
◄time_65.00►
◄time_76.00►
◄time_87.00►
CategoryBFS/MiniMax H3
Inputs (33)
| Name | Type | Default | Description |
|---|---|---|---|
| clip | CLIP | MiniMax H3's text encoder (Qwen3-VL). | |
| vae | VAE | — | |
| guide_video | IMAGE | keyframe pins: the prepared 24-fps source video. Guide modes: the marked guide (BFS Video Segment Picker `hybrid`). | |
| width | INT | — | |
| height | INT | — | |
| length | INT | — | |
| picture_1 | IMAGE | Subject 1 (red mark in the guide modes). | |
| mode | COMBO | keyframe pins | How the subjects to replace are marked: edited keyframes pinned at their frames, or a guide with each subject drawn as a colored normal map or DWPose skeleton (BFS Video Segment Picker). |
| keyframe_until | FLOAT | 0.700–1 | keyframe pins only, on the returned model: the guides condition every step whose sigma is at least this; below it only the Pictures remain. 0.5 = more faithful to the source, 0 = guides in every step. The guide modes keep the guide on every step. |
| keyframe_until_drops | COMBO | keyframes only | keyframe pins only: below keyframe_until drop only the keyframes (the source video keeps guiding every step) or every guide. |
| prompt_override | STRING | Non-empty: used instead of the generated prompt. | |
| picture_2opt | IMAGE | Subject 2 (blue mark in the guide modes). | |
| picture_3opt | IMAGE | Subject 3 (green mark in the guide modes). | |
| picture_4opt | IMAGE | Subject 4 (yellow mark in the guide modes). | |
| modelopt | MODEL | keyframe pins: connect to get it back with keyframe_until applied. Guide modes: passed through. | |
| keyframesopt | IMAGE | keyframe pins: edited frames, one per keyframe (BFS Keyframe Planner keyframes). | |
| keyframe_specopt | STRING | keyframe pins: BFS Keyframe Planner keyframe_spec (the frame of every keyframe). | |
| keyframe_1opt | IMAGE | keyframe pins: edited frame 1, a full frame of the RESULT (swapped person in place). | |
| time_1opt | FLOAT | 0.000–600 | keyframe pins: seconds into the guide where keyframe 1 sits. |
| keyframe_2opt | IMAGE | keyframe pins: edited frame 2, a full frame of the RESULT (swapped person in place). | |
| time_2opt | FLOAT | 1.000–600 | keyframe pins: seconds into the guide where keyframe 2 sits. |
| keyframe_3opt | IMAGE | keyframe pins: edited frame 3, a full frame of the RESULT (swapped person in place). | |
| time_3opt | FLOAT | 2.000–600 | keyframe pins: seconds into the guide where keyframe 3 sits. |
| keyframe_4opt | IMAGE | keyframe pins: edited frame 4, a full frame of the RESULT (swapped person in place). | |
| time_4opt | FLOAT | 3.000–600 | keyframe pins: seconds into the guide where keyframe 4 sits. |
| keyframe_5opt | IMAGE | keyframe pins: edited frame 5, a full frame of the RESULT (swapped person in place). | |
| time_5opt | FLOAT | 4.000–600 | keyframe pins: seconds into the guide where keyframe 5 sits. |
| keyframe_6opt | IMAGE | keyframe pins: edited frame 6, a full frame of the RESULT (swapped person in place). | |
| time_6opt | FLOAT | 5.000–600 | keyframe pins: seconds into the guide where keyframe 6 sits. |
| keyframe_7opt | IMAGE | keyframe pins: edited frame 7, a full frame of the RESULT (swapped person in place). | |
| time_7opt | FLOAT | 6.000–600 | keyframe pins: seconds into the guide where keyframe 7 sits. |
| keyframe_8opt | IMAGE | keyframe pins: edited frame 8, a full frame of the RESULT (swapped person in place). | |
| time_8opt | FLOAT | 7.000–600 | keyframe pins: seconds into the guide where keyframe 8 sits. |
Outputs (6)
| Name | Type | Description |
|---|---|---|
| model | MODEL | — |
| positive | CONDITIONING | — |
| latent | LATENT | — |
| prompt | STRING | The prompt used. |
| keyframe_video | IMAGE | keyframe pins: the keyframes at their frames on gray. Guide modes: the guide. |
| pictures | IMAGE | The Pictures in order (Picture 1..4, any sizes), e.g. for BFS Video Compare's reference. |