Upload README (5).md

README (5).md

@@ -0,0 +1,138 @@
+---
+license: minimax-h3-community-license
+pipeline_tag: video-to-video
+tags:
+  - minimax-h3
+  - comfyui
+  - workflow
+  - ref2v
+  - prompt-enhancer
+  - character-replacement
+  - v2v
+---
+
+# Nugget H3 EasyR2V — Prompt Enhancer & Full Workflow
+
+Why spend 30 minutes doing something when you can spend 2 weeks making a tool to automate it. That's basically the whole reason this exists.
+
+I wanted an easy to use workflow for us simple folk who want to do **Ref2V** on MiniMax H3 but keep running into trouble replacing characters. A good prompt does 80–90% of the work with H3 R2V — so instead of writing them by hand every time, this workflow writes them for you.
+
+Think of it as **"Ref2Video for dummies"**. But it's not just limited to that.
+
+![full workflow view](https://huggingface.co/datasets/PoopMan333/Examples/resolve/main/Prompt_Enhancer/full%20wf%20view%20image.PNG)
+
+---
+
+## What it does
+
+- **Scans your video** (if you're using one) to caption it and transcribe the audio
+- **Captions all your images** — so it also works as a pure image-to-video workflow
+- **Loads a small LLM of your choice** and writes your H3 R2V prompt in the correct format
+- **If you're on the Full workflow**, it generates the video too
+
+### The clever part
+
+- If your video doesn't change, a second run doesn't trigger a new transcription
+- If your images and user prompt don't change, it doesn't write a new prompt — so you can re-run on a new seed to test without paying the LLM cost every time
+
+---
+
+## Two workflows
+
+| File | What it does |
+|---|---|
+| `Nugget_H3_EasyR2V_Full_WF_v03.json` | The full thing — transcribe + prompt + generate video |
+| `Nugget_H3_EasyR2V_Prompter_Only_v03.json` | Just writes the H3 prompt. Copy it out, or wire it into your own H3 graph |
+
+Prompter-only is handy if you've already got your own H3 setup dialled in and just want a better prompt without ripping your workflow apart.
+
+![prompter only view](https://huggingface.co/datasets/PoopMan333/Examples/resolve/main/Prompt_Enhancer/prompt%20enhancer%20only%20view.PNG)
+
+---
+
+## Examples
+
+**Character replacement** — swap the person in a clip for one from your reference images:
+
+<video controls src="https://huggingface.co/datasets/PoopMan333/Examples/resolve/main/Prompt_Enhancer/Character_replacement_example.mp4"></video>
+
+Side by side, original vs replaced:
+
+<video controls src="https://huggingface.co/datasets/PoopMan333/Examples/resolve/main/Prompt_Enhancer/example%20side%20by%20side.mp4"></video>
+<video controls src="https://huggingface.co/datasets/PoopMan333/Examples/resolve/main/Prompt_Enhancer/example%20side%20by%20side%202.mp4"></video>
+
+**Background + character replacement** — swap both in one go:
+
+<video controls src="https://huggingface.co/datasets/PoopMan333/Examples/resolve/main/Prompt_Enhancer/BG_and_Char_Replacement_Example.mp4"></video>
+
+**Voice line + character replacement** — new person, new dialogue:
+
+<video controls src="https://huggingface.co/datasets/PoopMan333/Examples/resolve/main/Prompt_Enhancer/Voice_Line_and_Char_Replacement_Example.mp4"></video>
+
+![example char replacement setup](https://huggingface.co/datasets/PoopMan333/Examples/resolve/main/Prompt_Enhancer/example%20char%20replacement.PNG)
+
+---
+
+## Setup
+
+Both workflow files have a big **START HERE — Downloads & Setup** markdown note pinned inside them, with every model link, folder path and install step. Rather than duplicate it all here, just open the workflow and read the note — it's more accurate than a copy of it would be.
+
+The short version:
+
+- **Custom nodes**: ComfyUI-Nugget, ComfyUI-KJNodes, and (Full workflow only) ComfyUI-PlagueKind-Nodes
+- **Run the Nugget install script** if you want dialogue transcribed — it installs `faster-whisper` into ComfyUI's own Python. A normal `pip install` goes into the wrong interpreter and it will still say the package is missing
+- **H3 models** from [🤗 Comfy-Org/MiniMax-H3](https://huggingface.co/Comfy-Org/MiniMax-H3)
+- **Prompt enhancer model** — start with Qwen3-VL 8B fp8_scaled. Drop to nvfp4 on 12 GB cards
+
+If the file won't open in ComfyUI, a node pack is missing. Install it, restart, reopen. Bypassing won't help.
+
+---
+
+## Tips for good character replacement
+
+- **If the video is easy, replacement should be easy too.** H3 has a quirk though — if the original person and the new person look too similar, it sometimes converges back to the original. A prompt won't always fix that. If you hit it, look into the **Greenman method** or the **Sam3 noise method** as alternatives *(links to be added)*
+- **More than one person in the scene?** Describe the scene properly. `replace the man wearing white shorts with the man in <picture 1>` beats `replace the man with <picture 1>` every time
+- **Give the LLM some context.** A one-liner in the user prompt like `<video 1> is a video of two girls eating a cup of chocolate ice cream` really helps the LLM understand what it's looking at. Especially useful with multiple scenes
+- **H3 is a tool, you're the one using it.** If you don't specify something, expect expressionless results. **Slop prompt in, slop video out**
+- **Don't expect miracles.** Sometimes less is more, sometimes more is more. You'll get a feel for it
+- **Limit the resolution and length.** There seems to be an arbitrary token limit that's affected by higher res/longer time. Keep it smaller and your success rate goes up
+
+---
+
+## Caveats (being honest here)
+
+- This is still working within the limits of H3, so sometimes it'll go funny. Not much I can do about that from a workflow
+- Clips run best around **8–20 seconds**. Longer than that and the transcriber gets memory-hungry — a minute of 1080p is more RAM than most machines want to spend. Trim first
+- I'm still testing more challenging v2v scenarios. If you hit something weird, let me know
+
+---
+
+## Re-running cheaply
+
+Keep both `seed` widgets on **fixed**. If nothing upstream has changed, ComfyUI skips the transcriber and the prompt enhancer entirely — only the sampler re-runs. Change the sampler seed for a new take, don't touch the others.
+
+Set the transcriber or enhancer seed to `randomize` and you'll re-transcribe the whole video every queue for nothing.
+
+To skip the video entirely, bypass **Load source video** (Ctrl+B). Prompt is written from the images and your text alone.
+
+---
+
+## Credit
+
+Workflow build, tuning and prompt-enhancer chain by **C_Nugget**.
+
+Original single-image workflow by **mackyb** (H3 Basic prompt enhancer v2). This is a modified variant, not their release.
+
+---
+
+## Licence stuff
+
+The workflow files are mine, do what you like with them.
+
+**The model isn't.** MiniMax H3 has a community licence that excludes the EU, UK, South Korea and the USA, and it covers **outputs** as well as the weights. If you're planning anything commercial, go read [the actual licence](https://huggingface.co/MiniMaxAI/MiniMax-H3/blob/main/LICENSE) rather than taking my word for it. I'm not a lawyer.
+
+---
+
+**[If this has helped you, consider chucking a few dollars my way. Any tips help with the power bills. Thank you.](https://ko-fi.com/c_nugget)**
+
+By C_Nugget