Hey guys, LD here, Spent months working on this. otherwise it would be free.
you don't just buy this node you buy everything i make, For future video gen models too.
i'm also in sulphur discord. if you need a hand.
Reference bank sticks to Base model methods - Allows you to add 3 photos + and mp3 for voice. My website offers a free tool to make Reference sheets perfect for H3.
My H3 Encode node is all ref/i2v/t2v in one, all handled by the Main Studio,
20 reference images and 9 mp3 vs the 9/3 stock options.
Hover over anything in the UI to get Hints of what it does
manual + other links on the website. - H3 Studio 2 – interactive tour by Lora-Daddy - new website layout. - NEW CONTENT ADDED 22:45 GMT 10/10/2026 - FX - Cinema - Many more camera and styles. <3
NEW IN 2.1.0 -
- CHAT — talk to the writer. Show it a picture, ask for ideas or dialogue, and it gives you intents with a USE AS INTENT button. It sees your tab, your rail, your frame and length — and on STEP BY STEP, the real last frame of the clip you kept.
- SHOTS dial — auto, or 1 to 20 shots a clip. 1 is one held shot; more is more action and more camera. Every clip is one continuous take: no cuts unless you ask for one.
- SHOTS form — every shot is VISUAL / DIALOGUE / SOUND. Pick who speaks from the cast, type only the words; the speaker, voice and language tag are written for you.
- SPEECH — 36 ways of talking (roadman, pirate, news anchor…), on the main characters only.
- HINTS — small preferences the writer folds in where they fit.
Updated weekly.
H3 Studio 2 – interactive tour by Lora-Daddy - new website lay out
Thanks guys.
updated weekly.
workflow is a placeholder you do need the node pack unfortunately.
Description
FAQ
Comments (9)
I feel WinAMP vibes
You are right, I have the same feeling. It Really Whips the Llama's Ass, yeah whips, not wipes.
yeahhh bro its 1 of the themes love it XD
@Lora_Daddy omg it actually is ! i just saw the drop down theme selection around 0:09 sec into the video ;)
just keep getting errors when trying to generate the prompt
1 of 1 clip(s) came back without their shot blocks - writing again…
⚠ the writer hit its token limit and was cut off - the end of the script is missing
⚠ missing field: detailed_description, overall_soundscape, non_diegetic_music
⚠ no [Shot N] blocks
My context length is set to 110K in LM studio. I have no problems when i use h3 Writer paired with ollama in other workflows....whats going on?
i had high hopes for this :/
FIXED: I had to change the Chat template of the quantized model in LM studio to {{ bos_token }}{% for message in messages %}{{ message['content'] }}{% endfor %}
Works now! Thank you!
don't need high context mines 32k what gpu you got, and what llm model?
I have a 4080, ive tried Qwen 3 12b, gemma 4 12b, gemma 4 26b, and qwen 3.8 27b. all have given that same error.
@Lora_Daddy FIXED: I had to change the Chat template of the quantized model in LM studio to {{ bos_token }}{% for message in messages %}{{ message['content'] }}{% endfor %}
Works now! Thank you!
Best workflow by far. Thanks for your work! Just three questions:
1.) Would it be possible to create an automated loop where you queue in 4 runs in advance? A fresh prompt each run for creating four unique videos.
2.) I keep having to restart ComfyUI whenever I want a new prompt generated after a video finished rendering. Otherwise it is stuck at generating a prompt. Why is that the case?
3) Which LLM model are you personally using exactly? Maybe mine is flawed resulting to 2).
Thanks!