Model reference · open weights

ovie

ovie is an open-weight image model from kyutai, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.

Image kyutai 1 variants 146 downloads/mo
Request this model on EU hardware All served models Not on the shared API today — deployed on request.

About

What ovie is

OVIE — One View Is Enough! Monocular Training for In-the-Wild Novel View Generation [](https://kyutai.org/blog/2026-04-14-ovie) [](https://arxiv.org/abs/2603.23488) [](https://github.com/AdrienRR/ovie) [](https://github.com/AdrienRR/ovie/blob/main/LICENSE) OVIE is a novel view synthesis model that generates a new viewpoint of a scene from a single image and a target camera pose. Unlike most prior work, it is trained entirely on unpaired in-the-wild images — no multi-view supervision required. Model architecture OVIE is a convolutional encoder–decoder with a Vision Transformer (ViT) bottleneck conditioned on camera parameters via adaptive layer normalisation (AdaLN): - Encoder: cascaded downsampling ConvBlocks (3 scales) - Bottleneck: 12-layer ViT (hidden size 768, 12 heads) with AdaLN camera conditioning - Decoder: cascaded upsampling ConvBlocks (3 scales) - Camera conditioning: a 7-dimensional pose encoding (rotation + translation) projected into the ViT hidden space - Parameters: ~143M Usage See the repository for full installation instructions and example notebooks: - inferencehuggingface.ipynb — loads directly from this Hub page - inferencelocal.ipynb — loads from a local checkpoint Training OVIE is trained on a diverse mix of in-the-wild internet images (ImageNet, Places365, OSV5M, OpenImages) with no multi-view pairs. Training uses a combination of L2 reconstruction loss, LPIPS perceptual loss, and an adversarial loss with a DINO-based discriminator. Camera poses are sampled synthetically from a distribution of plausible viewpoint changes. Evaluation The model is evaluated on DL3DV and Real Estate 10K (RE10K) using PSNR, SSIM, and LPIPS. See the paper for full quantitative results. Citation

Summarised from the published model card. Read the full card on the HuggingFace links below.

Specifications

What it is

Makerkyutai
TypeImage models
Parameters (lead)143M
Variants1
Released2026-04-02
Popularity146 downloads / month
Likes16
LicenceOpen weights

How it works

How image models work

Text promptwhat to makeText encoderunderstands itDiffusion stepsdenoise to pixelsImagePNG / JPEGA diffusion model starts from noise and denoises it, guided by your prompt, into a finished image.

Variants

Sizes & precisions

Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.

VariantParamsPrecisionVRAMFits 16 GBWeights
ovie143MBF16~0.3 GBWeights ↗

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys ovie for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (ovie below is illustrative; you get the exact model name on deployment.)

$ curl -sS https://api.axforge.ai/v1/images/generations \
  -H "Authorization: Bearer $AXFORGE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"ovie","prompt":"a red bicycle","size":"1024x1024"}'

Details

Languages, data & research

Tags

safetensors novel-view-synthesis image-to-image computer-vision pytorch model_hub_mixin pytorch_model_hub_mixin

Papers

Licence

Open weights

Open weights under mit — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗

Sources

Weights & code

Want ovie on EU-owned hardware?

Request this model on EU hardware See what’s served now

Explore

More image models

© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms