ModelPrésentéExterne

Text2ct Weights

Checkpoints for "From Alignment to Synthesis: Contrastive Volumetric Grounding for Text-to-CT Generation" (Molino et al., BMVC 2026).

Sourcehuggingface.co/dmolino/text2ct-weights/tree/492a1b8338e55b90f1809b798519cde9b46e3add

TypeOtherVersionBClasse

Source du modèle

Type: Other
Taille du fichier: 79,9 MB
Version: vautoencoder_epoch273
Mis à jour: 9 oct. 2026
Téléchargements: 23
Source: Hugging Face

Description de la source

Text-to-CT Model Weights

Checkpoints for "From Alignment to Synthesis: Contrastive Volumetric Grounding for Text-to-CT Generation" (Molino et al., BMVC 2026).

Note on versions. The checkpoints currently hosted here correspond to the earlier version of this work (arXiv v2). Weights for the updated model will be added alongside the code release.

Model Card

Model Description

Authors: Daniele Molino, Camillo Maria Caruso, Filippo Ruffini, Valerio Guarrasi, Paolo Soda
Model type: 3D latent diffusion (RFlow) + 3D VAE + CLIP3D text encoder for CT generation.
License: Apache 2.0 (same as code release).
Sources: Code https://github.com/cosbidev/Text2CT | Paper https://arxiv.org/abs/2506.00633
Demo: Use diff_model_demo.py from the code release for a one-off generation from text.

Intended Use

Direct use: Research/experimentation on text-conditioned 3D CT synthesis; generating synthetic data for benchmarking or augmentation.
Downstream use: Fine-tuning or integration into broader research pipelines.
Out of scope: Clinical decision-making, diagnostic use, or deployment without proper validation and approvals.

Risks & Limitations

Trained on CT-RATE; may encode dataset biases and is not validated for clinical use.
Synthetic outputs may contain artifacts; do not use for patient care.

Files included

autoencoder_epoch273.pt — 3D VAE for latent compression/decoding.
unet_rflow_200ep.pt — Diffusion UNet trained with rectified flow.
CLIP3D_Finding_Impression_30ep.pt — CLIP3D weights for encoding reports.

How to Get Started (Python)

from huggingface_hub import snapshot_download

snapshot_download(
    repo_id="dmolino/text2ct-weights",
    repo_type="model",
    local_dir="your_local_path",
)

Use these in the code release configs:

Config field	Points to
`trained_autoencoder_path`	autoencoder
`existing_ckpt_filepath` / `model_filename`	unet
`clip_weights`	clip

Training Data (for these weights)

CT-RATE dataset (public on Hugging Face) for CT volumes and reports.

Training Procedure (summary)

CLIP3D trained for vision-language alignment on CT + reports.
VAE checkpoint from https://github.com/Project-MONAI/tutorials/tree/main/generation/maisi.
Diffusion UNet trained with rectified flow (RFlow) in latent space, conditioned on text embeddings.

Evaluation

See paper for quantitative and qualitative results.

Further Information

1,000 generated CT scans are available at https://huggingface.co/datasets/dmolino/CT-RATE_Generated_Scans.

Environmental Impact

Not reported. Training used a multi-GPU setup.

Citation

If you use these weights or code, please cite:

@misc{molino2026alignment,
      title={From Alignment to Synthesis Contrastive Volumetric Grounding for Text-to-CT Generation}, 
      author={Daniele Molino and Camillo Maria Caruso and Filippo Ruffini and Paolo Soda and Valerio Guarrasi},
      year={2026},
      eprint={2506.00633},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2506.00633}, 
}

Sources

1 source

Hugging FacePrincipalVersion 492a1b8338e55b90f1809b798519cde9b46e3add

huggingface.co/dmolino/text2ct-weights/tree/492a1b8338e55b90f1809b798519cde9b46e3add

Vérifié 9 oct.

Artefacts du modèle

1 artefact

models/autoencoder_epoch273.pt

pt · 79,9 MB · SHA-256 1f8a7a056d0e…5eb3 · Hugging Face

Télécharger

Extraits de sources

3 extraits

Readme9 oct.huggingface.co/dmolino/text2ct-weights

--- license: apache-2.0 datasets: - ibrahimhamamci/CT-RATE - dmolino/CT-RATE_Generated_Scans language: - en pipeline_tag: text-to-3d tags: - medical --- # Text-to-CT Model Weights Checkpoints for **"From Alignment to Synthesis: Contrastive Volumetric Grounding for Text-to-CT Generation"** (Molino et al., BMVC 2026). > **Note on versions.** The checkpoints currently hosted here correspond to the earlier version of this work ([arXiv v2](https://arxiv.org/abs/2506.00633v2)). Weights for the updated model will be added alongside the code release. --- ## Model Card ### Model Description - **Authors:** Daniele Molino, Camillo Maria Caruso, Filippo Ruffini, Valerio Guarrasi, Paolo Soda - **Model type:** 3D latent diffusion (RFlow) + 3D VAE + CLIP3D text encoder for CT generation. - **License:** Apache 2.0 (same as code release). - **Sources:** Code https://github.com/cosbidev/Text2CT | Paper https://arxiv.org/abs/2506.00633 - **Demo:** Use `diff_model_demo.py` from the code release for a one-off generation from text. ### Intended Use - **Direct use:** Research/experimentation on text-conditioned 3D CT synthesis; generating synthetic data for benchmarking or augmentation. - **Downstream use:** Fine-tuning or integration into broader research pipelines. - **Out of scope:** Clinical decision-making, diagnostic use, or deployment without proper validation and approvals. ### Risks & Limitations - Trained on CT-RATE; may encode dataset biases and is not validated for clinical use. - Synthetic outputs may contain artifacts; do not use for patient care. ### Files included - `autoencoder_epoch273.pt` — 3D VAE for latent compression/decoding. - `unet_rflow_200ep.pt` — Diffusion UNet trained with rectified flow. - `CLIP3D_Finding_Impression_30ep.pt` — CLIP3D weights for encoding reports. ### How to Get Started (Python) ```python from huggingface_hub import snapshot_download snapshot_download( repo_id="dmolino/text2ct-weights", repo_type="model", local_dir="your_local_path", ) ``` Use these in the code release configs: | Config field | Points to | | --- | --- | | `trained_autoencoder_path` | autoencoder | | `existing_ckpt_filepath` / `model_filename` | unet | | `clip_weights` | clip | ### Training Data (for these weights) - CT-RATE dataset (public on Hugging Face) for CT volumes and reports. ### Training Procedure (summary) - CLIP3D trained for visi...

Readme1 aoûthuggingface.co/dmolino/text2ct-weights

--- license: apache-2.0 datasets: - ibrahimhamamci/CT-RATE - dmolino/CT-RATE_Generated_Scans language: - en - tr - it pipeline_tag: text-to-3d tags: - medical --- # Text-to-CT Model Weights Checkpoints for **“Text-to-CT Generation via 3D Latent Diffusion Model with Contrastive Vision-Language Pretraining”** (Molino et al., 2025). --- ## Model Card for Text-to-CT Generation via 3D Latent Diffusion Model with Contrastive Vision-Language Pretraining ### Model Description - **Authors:** Daniele Molino, Camillo Maria Caruso, Filippo Ruffini, Paolo Soda, Valerio Guarrasi - **Model type:** 3D latent diffusion (RFlow) + 3D VAE + CLIP3D text encoder for CT generation. - **License:** Apache 2.0 (same as code release). - **Sources:** Code https://github.com/cosbidev/Text2CT | Paper https://arxiv.org/abs/2506.00633 - **Demo:** Use `diff_model_demo.py` from the code release for a one-off generation from text. ### Intended Use - **Direct use:** Research/experimentation on text-conditioned 3D CT synthesis; generating synthetic data for benchmarking or augmentation. - **Downstream use:** Fine-tuning or integration into broader research pipelines. - **Out of scope:** Clinical decision-making, diagnostic use, or deployment without proper validation and approvals. ### Risks & Limitations - Trained on CT-RATE; may encode dataset biases and is not validated for clinical use. - Synthetic outputs may contain artifacts; do not use for patient care. ### Files included - `autoencoder_epoch273.pt` — 3D VAE for latent compression/decoding. - `unet_rflow_200ep.pt` — Diffusion UNet trained with rectified flow. - `CLIP3D_Finding_Impression_30ep.pt` — CLIP3D weights for encoding reports. ### How to Get Started (Python) ```python from huggingface_hub import snapshot_download repo_id = "dmolino/text2ct-weights" snapshot_download( repo_id=repo_id, repo_type="model", local_dir="your_local_path" ) ``` # Use these in the code release configs: # trained_autoencoder_path -> autoencoder_path # existing_ckpt_filepath / model_filename -> unet_path # clip_weights (for report embeddings) -> clip_path ``` ### Training Data (for these weights) - CT-RATE dataset (public on Hugging Face) for CT volumes and reports. ### Training Procedure (summary) - CLIP3D trained for vision-language alignment on CT+reports. - VAE checkpoint from https://github.com/Project-MONAI/tutorials/tree/main/genera...

Note9 oct.huggingface.co/dmolino/text2ct-weights

Source context: 23 downloads · 4 likes · Pipeline text-to-3d · Repo dmolino/text2ct-weights