Z-Image's eye for texture on MiniMax-H3's engine. Drop-in replacements for the standard H3 checkpoints: same identity, same voices, same speed, same VRAM, same workflows - but sets and surfaces render noticeably richer. Peeling paint peels harder, rust bleeds further, water carries more light.And the extra detail stays flat across chained shots - measured on the same seed, the graft ran a 0.99 texture ratio over three joins where stock drifted to 1.11. More detail, no per-shot sharpening creep from the graft.<h2 id="what-is-this-actually">What is this, actually</h2>Z-Image is a 6B image model with exceptional fine-texture rendering. Both it and MiniMax-H3 normalise attention queries per head - so the shape of how sharply each attention head commits to fine detail can be transplanted between them by rescaling those normalisation weights. That's the whole trick: no retraining, no new knowledge, H3 keeps everything it knows and attends to texture the way Z-Image does. Early blocks are deliberately left untouched (grafting them creates a weave artifact in tile-like textures - we measured, so you don't have to). This is the second marriage in this line - Joy-LTX 2.5 put JoyAI-Echo's performance on LTX-2.5's engine the same way, donor to engine. The statistics-transplant mechanism here is our own; a nod to TenStrip, whose H3 attention experiments sparked the question of what an image model could donate.<h2 id="which-file">Which file</h2><ul><li>fl2va (default) - the first/last-frame variant. Chains, lands on supplied frames, the everyday pick.</li><li>ref2va - the reference variant: reference images, voice anchoring, the identity bank. Pick it when a character must persist.</li><li><code>Q8_0</code> for 32 GB cards, <code>Q5_1</code> for 24 GB, <code>Q4_0</code> for 16 GB.</li><li>More formats (plain non-curve bakes, bf16, fp8, int8, w4a8, nvfp4 comfy-native) are on Hugging Face - links below.</li></ul><h2 id="install">Install</h2>Put the file where your H3 checkpoints live. Pick it in your loader. Done - every H3 workflow works unchanged, including the MiniMax-H3 Multishot seamless-chain canvases.<h2 id="links">Links</h2>All formats: the GGUF and comfy-native repos on Hugging Face (joeygambino). Workflows: the MiniMax-H3 Multishot page. Questions: comment here - I answer.

MiniMax-H3 x Z-Image - richer sets and textures, same identity (the spatial detail graft)

The default variant. Chains seamlessly, lands on supplied first/last frames.<ul><li><code>MiniMax-H3-fl2va-curve-zs05-Q8_0.gguf</code> - 21.5 GB - 32 GB cards.</li><li><code>MiniMax-H3-fl2va-curve-zs05-Q5_1.gguf</code> - 15.2 GB - 24 GB cards.</li><li><code>MiniMax-H3-fl2va-curve-zs05-Q4_0.gguf</code> - 11.5 GB - 16 GB cards.</li></ul>Plain (non-curve) bakes and comfy-native formats (bf16 / fp8 / int8 / w4a8 / nvfp4) are on Hugging Face.

Files with SHA256: bc9f885d30acf58ab72fa385000948fe3ad331205dbc96d04b75ddfe3d96a650