Skip to content

One-click character swap for videos: an open-source, local Higgsfield Genjutsu alternative built on ComfyUI and MiniMax H3, with FLUX.3 Klein relighting.

Add Relight to the README

D3voza75ae3523e4d
diff --git a/README.md b/README.md
index 8b2d166..c6fb443 100644
--- a/README.md
+++ b/README.md
@@ -12,6 +12,10 @@ https://github.com/user-attachments/assets/2d8d763a-1764-49a6-9116-d6d1be661ff6
| **From picture: a new look and place from one picture** | **Post-processing: fix faces** |
| ![A video frame and a picture combined into a posed picture, then a video](docs/media/from_picture.jpg) | ![A small face redrawn at close-up size](docs/media/fix_faces.jpg) |
+**From picture → Relight: new light in the same pass**
+
+![A video frame and a picture combined into a posed picture under golden backlight, then a video that keeps the light, with the nine light looks below](docs/media/relight.jpg)
+
## First visit: visual describer
The welcome page lets you choose the vision-language model that describes pictures and video frames and writes prompts. Qwen3-VL 8B INT8 remains the default; Qwen3-VL 4B FP8 and Gemma 4 E2B INT8 are smaller alternatives. Install a compatible single-file model including its vision weights in `ComfyUI/models/text_encoders`, then press **Refresh models**. Other installed models can be selected if they support image/video input and text generation through ComfyUI's CLIPLoader and Generate Text nodes. Text-only models and files requiring a different loader are unsuitable.
@@ -23,7 +27,7 @@ Choose according to available VRAM and leave room for image/video context and wo
- **Simple motion transfer**: available. One character replaces the main person (the one who fills the most of the frame). Runs `workflows/simple.api.json`, exported from `H3 One-Click Single Swap (DMAD 6 step).json`.
- **Advanced motion transfer**: available. 1–4 characters, each with an optional role; every tracked person is matched to a role per shot, and people without a character stay untouched. Runs `workflows/advanced.api.json`, exported from `H3 One-Click Advanced Swap (DMAD 6 step).json`; **One pass per person** (two characters) runs `workflows/advanced_maxq.api.json`.
- **Object swap**: available. **Change** what SAM tracks (hair, a jacket, a car) into what you describe or show in a picture; **Remove** it; or change the **Background** around it (`person` stays). Only that area is regenerated. Runs `workflows/object.api.json`, exported from `H3 One-Click Object Swap (DMAD 6 step).json`.
-- **From picture** (under Object swap): FLUX prepares the character in the raw video frame's pose and body cut while keeping the character picture's background. Review or regenerate the image, then choose **Use this image** to set the video length, video and motion-reference resolutions, models, LoRAs, steps and seed. SolarRenderer defaults to four steps with a selectable rank-384 or rank-64 four-step/control pair and supports up to 15 seconds, like the native H3 renderer. SolarRenderer clips longer than six seconds can take considerably longer to render, especially at higher resolutions; see the workflow requirements for the extended-silence node fix. Both LoRA file pickers support `models/loras` and its subfolders. **Render video** reuses the saved preview with normal-map motion guidance and the source soundtrack, in one clip without a context loop. H3 rounds the requested length down to its valid frame grid. See [the workflow requirements](workflows/picture/README.md).
+- **From picture** (under Object swap): FLUX prepares the character in the raw video frame's pose and body cut while keeping the character picture's background. Review or regenerate the image, then choose **Use this image** to set the video length, video and motion-reference resolutions, models, LoRAs, steps and seed. SolarRenderer defaults to four steps with a selectable rank-384 or rank-64 four-step/control pair and supports up to 15 seconds, like the native H3 renderer. SolarRenderer clips longer than six seconds can take considerably longer to render, especially at higher resolutions; see the workflow requirements for the extended-silence node fix. Both LoRA file pickers support `models/loras` and its subfolders. **Render video** reuses the saved preview with normal-map motion guidance and the source soundtrack, in one clip without a context loop. H3 rounds the requested length down to its valid frame grid. **Relight** (off by default) changes the light in the same FLUX pass: pick one of nine looks, each shown with an example picture, or describe your own light. FLUX then sees only your picture, and the Qwen 3.5 9B prompt upsampler reads the pose from the video frame. Magenta club and Teal lasers mostly recolour the background. See [the workflow requirements](workflows/picture/README.md).
- **Post-processing**: available, for a finished video. **Fix faces**: H3 draws faces poorly when the person is small in the frame, so this redraws the face of the person in a photo at close-up size and pastes it back. Runs `workflows/face.api.json`, written by `workflows/build/openjutsu_face_build.py`. **Fix colours** softens H3's harsh look without an H3 run: Image Detail Contrast takes some fine detail contrast out, then Orion4D's DCTL Tone Mapper grades every frame. Runs `workflows/color.api.json`.
## Requirements
diff --git a/docs/media/relight.jpg b/docs/media/relight.jpg
new file mode 100644
index 0000000..f9e573f
Binary files /dev/null and b/docs/media/relight.jpg differ