---
license: cc-by-sa-4.0
datasets:
- sankalpsinha77/MARVEL-40M
language:
- en
base_model:
- stabilityai/stable-diffusion-3.5-large
tags:
- text-to-image
- image
---


<style>
  .nurbgen-text {
    font-family: 'Arial', sans-serif;
    font-weight: 800;
    font-size: 5rem;
    background: linear-gradient(

  90deg,
  #f59e0b, #ef4444, #ec4899, #f59e0b
);

background-size: 300% 100%;
    -webkit-background-clip: text;
    -webkit-text-fill-color: transparent;
    background-clip: text;
  }
</style>



<div align="center">

  <span class="nurbgen-text">MARVEL-FX3D</span>

         
Sankalp Sinha👨‍💻 · Mohammad Sadil Khan👨‍💻 · Muhammad Usama · Shino Sam · Didier Stricker · Sk Aziz Ali · Muhammad Zeshan Afzal

👨‍💻 Equally contributing first authors

[![Paper](
https://img.shields.io/badge/📄_Paper-ArXiv-b31b1b?style=for-the-badge)](https://openaccess.thecvf.com/content/CVPR2025/papers/Sinha_MARVEL-40M_Multi-Level_Visual_Elaboration_for_High-Fidelity_Text-to-3D_Content_Creation_CVPR_2025_paper.pdf)
[![Project Page](https://img.shields.io/badge/🌐_Project-Website-2ecc71?style=for-the-badge)](https://sankalpsinha-cmos.github.io/MARVEL/)
[![Dataset](https://img.shields.io/badge/🤗_Dataset-HuggingFace-yellow?style=for-the-badge)](https://huggingface.co/datasets/sankalpsinha77/MARVEL-40M)
[![Explorer](https://img.shields.io/badge/🔍_Explorer-Demo-blue?style=for-the-badge)](https://sadilkhan.github.io/Marvel-Explorer/)
[![Code](https://img.shields.io/badge/⚡_MARVEL--FX3D-Pipeline-purple?style=for-the-badge)](https://github.com/SadilKhan/MARVEL-FX3D)


<img src="https://readme-typing-svg.herokuapp.com?font=JetBrains+Mono&size=36&pause=1000&center=true&vCenter=true&width=1000&height=75&color=0C7C59&lines=CVPR+2025" />
</div>

---

This repo contains weights for fine-tuned Stable Diffusion 3.5 Large on [MARVEL-40M+](https://sadilkhan.github.io/Marvel-Explorer/) dataset. Given a text prompt, the model generates an image suitable for a pretrained image-to-3D model such as Sam3D, Trellis, or Stable Fast 3D.

# Inference

```python
# Generate Image from text prompts

import torch
from diffusers import StableDiffusion3Pipeline

model_id = "stabilityai/stable-diffusion-3.5-large"
lora_path = "SadilKhan/MARVEL_FX3D"  # or local path

pipe = StableDiffusion3Pipeline.from_pretrained(
    model_id,
    torch_dtype=torch.float16,
    device_map="auto"
)

# Load LoRA weights
pipe.load_lora_weights(lora_path)

pipe.to("cuda")

prompt = "An old, moss-covered wishing well. Rough stones, aged wood, rusty chains, mushrooms, fallen leaves, and twigs create an enchanting, ancient, and rustic atmosphere."

image = pipe(
    prompt=prompt,
    num_inference_steps=28,
    guidance_scale=7.0,
).images[0]

image.save("output.png")
```

# Citation

If you find MARVEL-FX3D useful, please cite

```
@inproceedings{sinha2025marvel,
  title     = {MARVEL-40M+: Multi-Level Visual Elaboration for High-Fidelity Text-to-3D Content Creation},
  author    = {Sinha, Sankalp and Khan, Mohammad Sadil and Usama, Muhammad and Sam, Shino and Stricker, Didier and Ali, Sk Aziz and Afzal, Muhammad Zeshan},
booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages={8105--8116},
  year={2025}
}
```