H3 Character Sheet Designer for ComfyUI
What’s New — v1.3
The new v1.3 workflow uses Pika H3 Flex Ref2VA LoRA.
MOSS-style presets, including 7 views with hands and feet on the right.
One shared layout guide for ON/OFF, with smaller margins and larger full-body guides.
Cleaner UI and minor clothing/13-view prompt refinements. Major quality improvements are not confirmed; human remnants and missing views can still occur.
Includes v1.3 and the previous v1.2.2 workflows. Auto sizing may increase rendering time and VRAM usage.
Models and downloads
ComponentDownload / filenameFolder under models/Diffusion / templateDaSiWa Hybrid V4 INT8 —
DasiwaMinimaxH3_dasiwaHybridV4_int8.safetensorsdiffusion_models/minimax/Native alternativeH3 Ref2VA INT8 —minimax_h3_ref2va_pruned_int8_convrot.safetensorsdiffusion_models/Text encoder / CLIPH3 Qwen3-VL INT8 —qwen3vl_32b_minimax_h3_int8_convrot.safetensorstext_encoders/Alternative encoderH3 NVFP4 AWQ —qwen3vl_32b_minimax_h3_nvfp4_awq.safetensorstext_encoders/Video VAEH3 VAE INT8 —minimax_h3_video_vae_int8_convrot.safetensorsvae/Alternative VAEH3 VAE FP16 —minimax_h3_video_vae_fp16.safetensorsvae/Pika LoRA / enabledRef2VA —pika_h3_flex_ref2va_v1_bf16.safetensorsloras/minimax/Pika LoRA / disabledFL2VA —pika_h3_flex_fl2va_v1_bf16.safetensorsloras/minimax/
v1.2
13 Views, 4 Reference Images & External Seed Control
Up to 13 views, including head, full-body, clothing, hands and footwear.
One character image + three optional references of the same character.
Fixed / randomize Seed controls outside the subgraph.
Previous nodes and workflows remain available.
Update the custom node before loading the new workflow. No character-sheet LoRA is required; the current template requires rgthree-comfy.

V1.0


Create character sheets from a reference image using MiniMax H3’s built-in reference conditioning and prompt understanding. Select the views you need, adjust the output size, and optionally add English prompts for clothing or other details.
No character-sheet LoRA is required. This Designer is the only custom node in the included workflow; generation uses ComfyUI Core nodes. You’ll need a compatible ComfyUI build and the H3 diffusion model, text encoder, and video VAE. Models are not included.
Installation
Open a terminal in your ComfyUI/custom_nodes folder and run:
git clone https://github.com/ukr8b3g-cmyk/H3-Character-Sheet-Designer.gitRestart ComfyUI and refresh the browser page. Download the official workflow, load it into ComfyUI, and select your reference image and models.
English Part prompts are recommended. Hand and footwear close-ups are optional; start without them unless needed. Results may require prompt adjustments. To generate a single view, select only that view and queue manually.
A simple, intuitive character-sheet designer using the MiniMax H3 models available through ComfyUI’s official templates. FL2VA can work well for straightforward character sheets. If you want to change clothing, colors, or other details, consider trying the official Ref2VA model from Comfy-Org. A Hybrid model is also linked in the workflow notes as an optional alternative. Results vary by model, reference image, and prompt.
For model links, examples, and full instructions, see the GitHub README.
Description
FAQ
Comments (3)
This works amazingly well, and makes using characters so much easier. It would be amazing if we could designate the reference images as character/clothing, etc. I tried manually rewriting the prompt, and it appears you can't do that.
Thanks for the suggestion! I’ve now added this to the latest Reference 13 Views node.
In Part prompts, you can assign a role to each of the three additional reference images: face, head/hair, complete outfit, front/back of outfit, hands, footwear, or another view of the same character.
For example, keep your main character in character_image, connect a clothing reference to reference_image_1, and select Complete outfit for that reference.
Please update the node pack, restart ComfyUI, and reload the browser page. The README now includes instructions. These roles guide the model through the prompt, so exact face or clothing transfer is not guaranteed.
@ukr8b3g201 oh my gosh thank you so much. That is very kind of you. I will buzz tip you when I get off of work. <3

