Vista4D — fp8 Release

A consumer-GPU-friendly mirror of the Vista4D inference weights, pre-quantized to fp8 (float8_e4m3fn) with per-tensor symmetric scaling. Drops the on-disk size from ~56 GiB (bf16) to ~17 GiB while staying numerically faithful enough for inference on the published Vista4D pipeline (CVPR 2026).

Vista4D reshoots a video from a new camera trajectory using a finetuned Wan 2.1-T2V-14B DiT plus a 4D point-cloud rendering pass. See the project page, paper, and upstream code for the full picture.

---

What's in this repo

Path	Contents	Size
384p49_step=30000-fp8/	DiT for the 672×384, 49-frame checkpoint, fp8 sharded safetensors + config.yaml + index	5.05 GiB
720p49_step=3000-fp8/	DiT for the 1280×720, 49-frame checkpoint (finetuned from 384p49), same layout	5.05 GiB
wan-encoders-fp8/	Wan 2.1's UMT5-XXL text encoder (fp8) + Wan VAE (bf16) + tokenizer	6.7 GiB
384p49_step=30000/dit.safetensors	The 384p49 DiT in bf16 full precision (legacy, kept for users who want the un-quantized reference)	20.1 GiB
384p49_step=30000/config.yaml	Same config as the -fp8 variant, kept alongside the bf16 file	< 1 KiB

Everything lives at the top level of https://huggingface.co/AEmotionStudio/Vista4D.

---

Quick download

# Just the fp8 release (Vista4D 384p + 720p + Wan encoders) — ~17 GiB total
hf download AEmotionStudio/Vista4D \
  --include "*-fp8/*" \
  --local-dir ./vista4d-fp8

# Single checkpoint only
hf download AEmotionStudio/Vista4D \
  --include "384p49_step=30000-fp8/*" \
  --local-dir ./vista4d-fp8
hf download AEmotionStudio/Vista4D \
  --include "wan-encoders-fp8/*" \
  --local-dir ./vista4d-fp8

# bf16 reference (only 384p49 is mirrored; 720p49 fp8 only)
hf download AEmotionStudio/Vista4D \
  --include "384p49_step=30000/dit.safetensors" \
  --local-dir ./vista4d-fp8

You'll also want the upstream Vista4D inference scripts:

git clone https://github.com/Eyeline-Labs/Vista4D

---

Quantization details

• Dtype: torch.float8_e4m3fn (max representable magnitude 448).
• Scaling: per-tensor symmetric. For each quantized weight W:
  • scale = max(|W|).float() / 448.0
  • W_fp8 = (W / scale).clamp(-448, 448).to(float8_e4m3fn)
  • The scale is saved alongside as a sibling key, e.g. blocks.0.self_attn.q.weight.scale_weight (fp32 scalar).
• What was quantized: only 2D nn.Linear weight tensors in the DiT — the QKV/output projections in self-/cross-attention and the FFN linears.
• What was kept in source dtype: patch/text/time embeddings, every *_norm.weight, modulation tensors, output head, and all biases (1D tensors are not quantized regardless of name).
• Reload pattern:

  actual_weight = fp8_tensor.to(torch.bfloat16) * scale_tensor
  

• Sharding: ≤ 5 GiB per shard, with a standard *.safetensors.index.json mapping every key to a shard. Both Vista4D DiTs ended up as single shards because each dit.pth was already ~10 GiB in fp16; the structure supports multi-shard models if you re-quantize larger weights.

This convention matches the fp8_linear path used by the WanVideoWrapper / kijai community releases and the fp8_linear matmul in diffsynth's loader (see diffsynth/core/vram/layers.py). No torchao / GPTQ wrappers — plain safetensors with sibling scales.

---

Loading example (raw safetensors)

import torch
from safetensors import safe_open

ckpt = "vista4d-fp8/384p49_step=30000-fp8/diffusion_pytorch_model-00001-of-00001.safetensors"

with safe_open(ckpt, framework="pt") as f:
    keys = list(f.keys())
    # Quantized weights have a ".scale_weight" sibling
    qk = "blocks.0.self_attn.q.weight"
    w_fp8 = f.get_tensor(qk)
    w_scale = f.get_tensor(qk + ".scale_weight")

print(w_fp8.dtype, w_fp8.shape, w_scale.dtype, w_scale.item())
# -> torch.float8_e4m3fn  torch.Size([5120, 5120])  torch.float32  ~0.000XX

# Materialize as bf16 if you want a normal tensor:
w_real = w_fp8.to(torch.bfloat16) * w_scale

---

Loading example (diffsynth fp8 path)

The fp8 layout is compatible with diffsynth-engine's native fp8 loader. Set preparing_dtype=torch.float8_e4m3fn in the config and point the model loader at the shard:

import torch
from diffsynth.core.loader.model import load_model

dit = load_model(
    "vista4d-fp8/384p49_step=30000-fp8/",  # dir containing the safetensors index
    preparing_dtype=torch.float8_e4m3fn,
)

The convert_fp8_linear helper in WanVideoWrapper (referenced above) is a near-identical drop-in if you're not using diffsynth.

---

Layout vs upstream Vista4D

The upstream pipeline expects:

checkpoints/
  vista4d/
    384p49_step=30000/
      config.yaml
      dit.pth
  wan/
    Wan2.1-T2V-14B/
      <full Wan 2.1 repo layout>

This repo ships safetensors, not .pth, and uses a flat layout instead of nested wan/Wan2.1-T2V-14B/. To wire it into the upstream code without modifications:

# Vista4D DiTs
mkdir -p checkpoints/vista4d
mv vista4d-fp8/384p49_step=30000-fp8 checkpoints/vista4d/384p49_step=30000
mv vista4d-fp8/720p49_step=3000-fp8  checkpoints/vista4d/720p49_step=3000

# Wan encoders (rename to match upstream)
mkdir -p checkpoints/wan/Wan2.1-T2V-14B
mv vista4d-fp8/wan-encoders-fp8/umt5_xxl_e4m3fn_scaled.safetensors checkpoints/wan/Wan2.1-T2V-14B/
mv vista4d-fp8/wan-encoders-fp8/Wan2.1_VAE.bf16.safetensors        checkpoints/wan/Wan2.1-T2V-14B/
mv vista4d-fp8/wan-encoders-fp8/tokenizer/umt5-xxl                 checkpoints/wan/Wan2.1-T2V-14B/google/

Most upstream loaders accept either .pth or .safetensors transparently. You may need to set the fp8-aware loader path in your config (see the diffsynth example above).

---

Source attribution

This release is a quantized derivative of:

• Vista4D — Eyeline-Labs/Vista4D (code, paper), Apache 2.0.
• Wan 2.1 — Wan-AI/Wan2.1-T2V-14B, Apache 2.0.

All weights here are derived from those releases. No new training was done.

---

License

Apache 2.0, inherited from both upstream sources. See LICENSE on Eyeline-Labs/Vista4D](https://huggingface.co/Eyeline-Labs/Vista4D/blob/main/LICENSE) and [LICENSE on Wan-AI/Wan2.1-T2V-14B.

Quantization itself is a numerical transformation; this repo redistributes the same weights under the same license.

---

Acknowledgments

• Eyeline Labs for Vista4D.
• The Wan-AI team for Wan 2.1-T2V-14B.
• kijai and the diffsynth-engine project for the fp8 linear matmul convention this release matches.

---

Citation

If you use Vista4D in your research, cite the original paper:

@inproceedings{vista4d2026,
  title     = {Vista4D: Learning to Reshoot Video with Camera Trajectories},
  author    = {Eyeline Labs},
  booktitle = {CVPR},
  year      = {2026}
}

---

Maintained by AEmotionStudio. Issues / questions: open an issue on the upstream Vista4D repo for model behavior, or here for layout / quantization questions.