matlod/minimax-h3-turnaround

---

license: other license_name: minimax license_link: https://huggingface.co/MiniMaxAI/MiniMax-H3 base_model: MiniMaxAI/MiniMax-H3 tags:

• lora
• minimax-h3
• multi-view
• character-sheet
• turnaround
• reference-to-image

---

H3 Turnaround LoRA — character sheets from one image

The first release of Contact-Sheet diffusion: a video model's timeline repurposed as a slot axis for coordinated image sets.

One reference image + one instruction → five coherent, progressively rotated views of the same subject, jointly denoised in a single pass, each view an independently-decoded crisp still. A character turnaround from one photo in ~10 s (512²) to ~57 s (1024²) on one GPU.

A real photograph (DIV2K) the model never saw, → five views. The LoRA trained only on H3-generated subjects — real-photo identity transfer is out-of-distribution and works.

The trick

H3 is a video+audio model. Its VAE stores video as one keyframe plus bundles of four frames, and the transformer's superpower is "keep everything consistent along the timeline." This LoRA hijacks that: five standalone image latents are packed where a 5-position video latent would go, with timeline positions stretched so the model believes they span one continuous shot. The model thinks it is making a tiny video — but every "frame" is a full independent image at a different camera angle, so its temporal-consistency machinery gets repurposed into cross-view identity. The timeline becomes a slot axis.

Proof it really is "video brain, image body": apply this LoRA to a normal video generation and motion breaks — spinning windmill blades render as superimposed discrete positions, because the LoRA has learned that time = poses.

Files

file	step	character
minimax_h3_five_view_512_s1500.safetensors	1500	default — best rotation geometry
minimax_h3_five_view_512_s400_instruct.safetensors	400	better instruction following (e.g. "neutral studio background" override honored), shallower rotation
minimax_h3_five_view_1024cont_s600.safetensors	600	1024-finetuned variant — see methodology

All: rank 16, attention-only (qkv/out on 50 blocks, 100 modules), 63 MB, ref2va_pruned partition. Strength 1.0 for rotation; ~0.7 trades rotation for scene fidelity.

Checkpoint methodology — how the files differ

One dataset (90 self-generated orbit clips, 30 subjects × 3 seeds; 75 train / 15 val split by subject), one LoRA config (rank 16 α 16, attention-only), one de-distillation training adapter (ostris alpha, train-time only). The files differ only in training resolution and schedule:

• 512_s400_instruct / 512_s1500 — the same single run at 512², lr 5e-5, adamw8bit, bs 1 × grad-accum 4, flowmatch/shift, saved at steps 400 and 1500. Early = instruction-following era; late = rotation era. (~6.8 s/step; the whole 1500-step run is ~2.8 h on one card.)
• 1024cont_s600 — took the step-400 weights above and continued 200 steps at 1024², lr 1e-5 (a short calibration tail, PixArt-style). Measured against the 512 checkpoints on held-out subjects at matched seeds: image quality at 1024/2048 is comparable (512-trained weights transfer to high-res inference surprisingly well — that's the headline finding), the studio-override instruction response is weaker than s400, and the 2048 early-arc back-loading is not fixed by 1024 training (it's a resolution-dependent sampling effect, not a weights gap). Published for completeness and for users generating primarily at 1024+.
• A third arm (1024 from scratch, lr 5e-5, 400 steps) is not published yet: at its endpoint it measures comparably to the arms above at every inference size, but it's only 400 steps in (vs 1500 for the 512 run) — parked mid-experiment in favor of higher-priority work, and worth extending to 1500 at some point. Full judgment writeup in the research log.

Resolution transfer (measured)

Trained at 512 — inference transfers to 1024 and 2048:

512-trained weights, five fresh 2048² views (shown downscaled). No upscaling anywhere in the pipeline — all views generated from noise.

per sheet	512²/slot	1024²/slot	2048²/slot
time (RTX PRO 6000 @ 450 W cap, 28 steps)	~10 s	~57 s	~227 s
peak VRAM	41 GiB	42 GiB	47 GiB

Before / after

See the full description on the original page