<h2 id="h3-image-character-sheet:-one-reference-in-full-character-sheet-out">H3 Image Character Sheet: one reference in, full character sheet out</h2>Upload a picture of your character, pick a resolution, and press Run. The workflow renders 8 separate images with MiniMax H3 Image and stitches them into one character sheet.<h3 id="what-you-get">What you get</h3><ul><li>Top row (full body): front, left profile, right profile, back</li><li>Bottom row (face close-ups): front, left profile, right profile, smiling</li></ul>Each view is its own render, with its own prompt written for that angle. It works from your reference picture, so a photo stays a photo and an illustration stays an illustration. Markings, fur, hair, clothing and body proportions carry across all 8 views.<h3 id="how-to-use-it">How to use it</h3><ol><li>Upload your character picture(s) in the Reference Images box. Extra pictures should be more angles of the same character.</li><li>(Optional) Describe the character in Character Notes. This helps with details the picture doesn’t show, like the back of a costume.</li><li>Set the Render Resolution. Every one of the 8 images is rendered at this size. The full-body views use the aspect ratio you choose (2:3 portrait by default), and the face close-ups are square at the same megapixels. You can use Aspect Ratio + Megapixels, or a Custom Width x Height.</li><li>Choose the Final Sheet Size from the presets:<ul><li>1920×1280</li><li>2496×1664 (default)</li><li>3072×2048</li><li>3744×2496</li><li>5024×3360</li><li>3840×2160 (16:9)</li></ul></li><li>Press Run.</li></ol>The renders and the final sheet are set separately. You can render each image at high resolution for detail and still get a sheet of a sensible size. The renders are shrunk to fit and are never cropped or stretched.<h3 id="why-it's-easy-to-use">Why it’s easy to use</h3><ul><li>There are no Pose Studio or image-comparison parts, just upload, resolution and Run.</li><li>Almost everything is tucked inside one Character Sheet Engine node. Double-click it to edit the 8 prompts, the sampler settings, or the model file names.</li><li>The layout is organized into three panels: Upload, Resolution, Character Sheet.</li></ul><h3 id="requirements">Requirements</h3><ul><li>ComfyUI v0.45.0 or newer. The MiniMax H3 Image Conditioning node isn’t in older versions.</li><li>Custom nodes (all installable through ComfyUI-Manager):<ul><li>ComfyUI-Pixaroma</li><li>rgthree-comfy</li><li>ComfyUI-Fantastic-MiniMaxH3-PromptBuilder, which provides the reference picture loader</li></ul></li><li>Models:<ul><li>diffusion_models/minimax_h3_image_pruned_int8_convrot.safetensors (~21 GB), from <a target="_blank" rel="ugc" href="https://huggingface.co/Comfy-Org/MiniMax-H3-Image">Comfy-Org/MiniMax-H3-Image</a></li><li>text_encoders/qwen3vl_32b_minimax_h3_int8_convrot.safetensors (~27 GB), from <a target="_blank" rel="ugc" href="https://huggingface.co/Comfy-Org/MiniMax-H3">Comfy-Org/MiniMax-H3</a></li><li>vae/minimax_h3_image_vae_fp16.safetensors (~1.2 GB), from <a target="_blank" rel="ugc" href="https://huggingface.co/Comfy-Org/MiniMax-H3-Image">Comfy-Org/MiniMax-H3-Image</a></li></ul></li></ul><h3 id="tips">Tips</h3><ul><li>Drafts: render at 4 MP per image. A full run at 4 MP per image took about 6 minutes on my setup.</li><li>Final art: raise the Render Resolution for more detail. This is slower, so make a draft first.</li><li>Rendering style: the face close-up prompts mention a “100mm portrait lens”, which suits photographic characters. For flat 2D art you may want to soften that wording in the Engine.</li><li>Image content: the prompts assume one standing character with a face in the reference. Group shots, quadrupeds, or faceless designs may need the prompts adjusted.</li><li>Left and right: “left” and “right” mean the direction the character faces in the image.</li><li>Reroll: use the Seed box.</li></ul><h3 id="credits">Credits</h3><ul><li>Built on the Comfy-Org MiniMax H3 Image workflow, using the MiniMax H3 Image models.</li><li>Inspired by foxydits H3 Image workflow <a target="_blank" rel="ugc" href="https://civarchive.com/models/3045966/h3-image-w-pose-studio-other-advanced-features-foxfuressence">https://civarchive.com/models/3045966/h3-image-w-pose-studio-other-advanced-features-foxfuressence</a></li></ul><h3 id="what's-new-in-v2.0">What’s new in v2.0</h3><ul><li>Character Type dropdown: a native Custom Combo in its own pane under the uploader, with Character Notes beside it. It switches all 8 prompts to one of four sets. Each set is an editable column inside Engine › Shot Prompts.</li><li>Four-legged and vehicle subjects: the body views render landscape automatically. Vehicles get front ¾, rear ¾, top-down and a detail close-up in the bottom row instead of faces. Landscape panels leave white bands above and below on a 3:2 sheet; that’s expected.</li><li>Design first when nothing is uploaded: the workflow detects an empty upload and renders one design image, which then becomes Picture 1 for all 8 shots. With an upload, that extra render is skipped.</li><li>Native nodes only: the new logic adds no custom node packs. It uses <code>CreateList</code>/<code>GetItemFromList</code>, <code>StringFormat</code> + <code>StringCompare</code>, a lazy <code>If/Else Switch</code> and <code>RegexReplace</code>.</li></ul>

H3 Image Character Sheet Builder

What’s new in v2.0<ul><li>Character Type dropdown: a native Custom Combo in its own pane under the uploader, with Character Notes beside it. It switches all 8 prompts to one of four sets. Each set is an editable column inside Engine › Shot Prompts.</li><li>Four-legged and vehicle subjects: the body views render landscape automatically. Vehicles get front ¾, rear ¾, top-down and a detail close-up in the bottom row instead of faces. Landscape panels leave white bands above and below on a 3:2 sheet; that’s expected.</li><li>Design first when nothing is uploaded: the workflow detects an empty upload and renders one design image, which then becomes Picture 1 for all 8 shots. With an upload, that extra render is skipped.</li><li>Native nodes only: the new logic adds no custom node packs. It uses CreateList/GetItemFromList, StringFormat + StringCompare, a lazy If/Else Switch and RegexReplace.</li></ul>

Files with SHA256: d6af9007339beab01e063962e8f86f8f18aaba9ff549c1abc0a3f533e057de2b