MiniMax H3-Image: Native 4K at 16.8MP in Six Steps - Three ComfyUI Workflows Compared A developer published three ComfyUI workflows for MiniMax's H3-Image model, which generates natively at 4K-class resolution (about 16.8 megapixels) in six sampling steps rather than upscaling. The workflows cover text-to-image (six nodes), single-image editing (48 nodes), and a 16-image reference edit (48 nodes) for character and product consistency, and ship as JSON graphs without bundled model weights. All three were tested as online workflows on RunningHub, with the open question being whether the 16-image branch preserves identity when references conflict. MiniMax H3-Image: native 4K at 16.8 megapixels in six sampling steps three ComfyUI workflows MiniMax's H3-Image is unusual for one reason: it does not upscale its way to a big picture. It generates natively at 4K-class resolution - about 16.8 megapixels - and it does it in six sampling steps. This episode tests that claim with three separate ComfyUI workflows, each built for a different job. Who this is for The three workflows, and when to use each Text to image - AIKSK H3 Image 文生图.json The simplest chain: prompt in, 6 steps of sampling, 4K image out. Six nodes total, so you can read the whole graph in a minute. Use it when the image does not exist yet. Online: https://www.runninghub.ai/zh-cn/post/2120808839725920258/?inviteCode=rh-v1111 https://www.runninghub.ai/zh-cn/post/2120808839725920258/?inviteCode=rh-v1111 Single image edit - H3 Image 单图像编辑.json 48 nodes. One reference image goes in with an instruction, and the model re-renders while keeping the parts you did not ask it to change. This is the workflow for "same photo, different weather / different light / fix this corner". Online: https://www.runninghub.ai/zh-cn/post/2120808831056293890/?inviteCode=rh-v1111 https://www.runninghub.ai/zh-cn/post/2120808831056293890/?inviteCode=rh-v1111 16-image reference edit - H3 Image 16图编辑.json Also 48 nodes, but the reference side is a bank of up to sixteen images. That is what you want for character consistency across angles, or for feeding a whole product set into one edit so the result matches all of them. Online: https://www.runninghub.ai/zh-cn/post/2120808834377023490/?inviteCode=rh-v1111 https://www.runninghub.ai/zh-cn/post/2120808834377023490/?inviteCode=rh-v1111 What is inside the JSON qwen3.8 27b w4a8 for the prompt path. minimax h3 image pruned int8 convrot , minimax h3 image vae fp16 , qwen3.5 9b w4a8 gptq , qwen3vl 32b minimax h3 int8 convrot . No model weights are bundled in the repos. You bring the weights; the workflow carries the wiring, the sampling settings and the conditioning structure. Known limits How to try it without a local install All three run as online workflows on RunningHub, which is what we used for the tests in the episode - same graph, no GPU required on your side: Episode links Where this goes next The interesting question is not whether 4K native generation looks good in a hero shot - it does. It is whether the 16-image branch holds identity when the references disagree with each other. That is the test worth running yourself.