Load one photo of a person, and MiniMax H3 draws a character sheet: the same person from the front, the three-quarter view, the side and the back, side by side in one picture. If your photo leaves something out, like the legs in a half-body photo, a box lets you name it, and the views show it. Switches make it faster, make it twice as big with SeedVR2, save each view as its own picture, put your photo beside the sheet, add a row of head close-ups or four expressions under it, or redraw each view at twice the size.

It's in my new video: I threw a ton of edits at Qwen Image 2.1, FLUX 3 Klein and FIBO 2

How to use it

1. Load your picture: one person, clearly in view.

2. Optional: type a background, like "a neon city street at night". Left empty, it is plain white.

3. Optional: name what your photo doesn't show, like "blue jeans and white sneakers" for a half-body photo.

4. Run. The first run takes a few minutes, because about 42 GB of models load once.

What you get

• One picture, 3072 × 1536: four views in a row, each 768 × 1536.

• The views are framed like your photo. A half-body photo gives half-body views, a full-body photo full-body views.

• To see more than your photo shows, name it in What the photo doesn't show. "Blue jeans and white sneakers" turned a chest-up photo into head-to-toe views in that outfit. Words like "full body" alone changed nothing.

• The back is H3's guess from what your photo shows.

• With Close-ups under the sheet on, the same picture gets a row of four head close-ups under the sheet: the front, the three-quarter view, the side and the back of the head. The picture is then 3072 × 2304.

The switches

• Fast: 10 steps instead of 18. The sheets looked just as good in my tests.

• Upscale 2x: SeedVR2 makes the sheet twice as big on each side, 6144 × 3072, and sharpens it. About 25 seconds more.

• Save each view too: the four views are also saved as pictures of their own, 768 × 1536 each (1536 × 3072 with Upscale 2x or Redraw each view).

• Your photo on the left: your photo goes on the left of the sheet, at the same height, with a thin white line between. The views from Save each view too stay without it.

• Close-ups under the sheet: H3 runs a second time, from your photo and the finished sheet, and draws the four close-ups. About 70 seconds more. Fast works on them too. With Upscale 2x on they are made twice as big as well, so the picture is 6144 × 4608. Save each view too still saves the four views of the sheet only.

• Expressions instead of head turns: the four close-ups face the camera and show the expressions in the four boxes under the switches. Those boxes light up when this is on. They run left to right, like the close-ups. It needs Close-ups under the sheet on too.

• Redraw each view: H3 redraws each of the four views at twice the size, so faces, hair and clothes come out sharp. About 3 minutes more. The sheet comes out 6144 × 3072.

What you need

• ComfyUI 0.30.0 or newer.

• AusBoss nodes 2.24.0 or newer. In ComfyUI-Manager, search "AusBoss". Already have them? Update first.

• The models:

  • minimax_h3_ref2va_pruned_int8_convrot.safetensors → models/diffusion_models · 20.97 GB (the Ref2VA model, not FL2VA)

  • qwen3vl_32b_minimax_h3_nvfp4_awq.safetensors → models/text_encoders · 15.69 GB (every H3 workflow uses it, so you may have it already)

  • minimax_h3_video_vae_fp16.safetensors → models/vae · 5.21 GB

• Card older than the RTX 50 series? Get qwen3vl_32b_minimax_h3_int8_convrot.safetensors (27.14 GB) and pick it in Text encoder.

• Only for Upscale 2x, SeedVR2:

  • seedvr2_3b_int8_convrot.safetensors → models/diffusion_models · 3.46 GB

  • seedvr2_ema_vae_fp16.safetensors → models/vae · 501 MB

• Optional, an uncensored text encoder (a community-made "Heretic" file; the regular one stays picked, see the second note in the workflow): qwen3vl_32b_heretic_minimax_h3_nvfp4.safetensors → models/text_encoders · 15.68 GB

Tips

• A view came out wrong? Run again. The seed changes after every run.

• It is set up for photos. The prompt asks for a live-action photograph, and I only tested photos.

• A phone or a camera in front of the face is fine. In my tests H3 left it out and drew the face.

• Strong coloured light, like orange or red neon, becomes plain studio light, and in one test the skin came out lighter than in the photo. A photo in plain light keeps the person closest.

• Each view's own picture is an exact quarter of the sheet, so a wide sleeve at the edge of a view can get cut off there. The sheet keeps it whole.

• Going from half-body to full body can lose small things, like a shirt under a jacket. Name those in What the photo doesn't show too.

• To change the views or the wording, open the box Write the sheet prompt. The prompt is plain text.

• Times on an RTX 5090: about 45 seconds a sheet once the models are loaded, about 28 with Fast on. The close-ups add about 70 seconds, Redraw each view about 3 minutes.

• LoRAs made for H3's Ref2VA model go in LoRA Loader.

Credits

MiniMax H3 is by MiniMax, under the MiniMax H3 Community License, and the files are Comfy-Org's repackage. The license only covers its "Applicable Territory", which leaves out the European Union, the United Kingdom, South Korea and the United States, and the same limit applies to what you make with it. Commercial products above US$20M a year in revenue need MiniMax's written OK and must show "MiniMax H3". SeedVR2 is by ByteDance Seed. The Heretic text encoder is Momoking's NVFP4 version of ethanfel's Heretic file, under Apache 2.0.

v1.0 (2026-10-26): first release.

v1.0 fix (2026-10-27): an empty background box now gives plain white instead of light grey.

v1.1 (2026-11-01): three new switches: Close-ups under the sheet, Expressions instead of head turns and Redraw the faces.

v1.2 (2026-11-12): Redraw each view replaces Redraw the faces. Each view is redrawn whole at twice the size, and the body edge no longer blurs at the chest.

Questions or bugs: GitHub issues or the comments here. Videos on YouTube @ausbossdev. More from me on X @Zanzibased and GitHub.