Text-to-Image
Diffusers
TensorBoard
Safetensors
StableDiffusionPipeline
stable-diffusion
stable-diffusion-diffusers
textual_inversion
Instructions to use hcarrion/abscess with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use hcarrion/abscess with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-2-1-base", dtype=torch.bfloat16, device_map="cuda") pipe.load_textual_inversion("hcarrion/abscess") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Improve model card: add pipeline tag, library name, paper, code and dataset links
Browse filesHi! I'm Niels, part of the community science team at Hugging Face.
This PR improves the model card for the `abscess` concept checkpoint. It:
- Adds `library_name: diffusers` and `pipeline_tag: text-to-image` to the YAML metadata to make the model easily discoverable and enable widgets.
- Links the model card to its corresponding paper page on Hugging Face: [Controllable Generation of Diverse Dermatological Imagery for Fair and Efficient Malignancy Classification](https://huggingface.co/papers/2607.12987).
- Links the model to the official GitHub repository and Hugging Face dataset.
- Adds the correct BibTeX citation from the publication.
Feel free to merge if this looks good!
README.md
CHANGED
|
@@ -1,7 +1,8 @@
|
|
| 1 |
-
|
| 2 |
---
|
| 3 |
-
license: creativeml-openrail-m
|
| 4 |
base_model: stabilityai/stable-diffusion-2-1-base
|
|
|
|
|
|
|
|
|
|
| 5 |
tags:
|
| 6 |
- stable-diffusion
|
| 7 |
- stable-diffusion-diffusers
|
|
@@ -10,8 +11,26 @@ tags:
|
|
| 10 |
- textual_inversion
|
| 11 |
inference: true
|
| 12 |
---
|
| 13 |
-
|
| 14 |
# Textual inversion text2image fine-tuning - hcarrion/abscess
|
| 15 |
-
These are textual inversion adaption weights for stabilityai/stable-diffusion-2-1-base. You can find some example images in the following.
|
| 16 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
|
|
|
| 2 |
base_model: stabilityai/stable-diffusion-2-1-base
|
| 3 |
+
library_name: diffusers
|
| 4 |
+
license: creativeml-openrail-m
|
| 5 |
+
pipeline_tag: text-to-image
|
| 6 |
tags:
|
| 7 |
- stable-diffusion
|
| 8 |
- stable-diffusion-diffusers
|
|
|
|
| 11 |
- textual_inversion
|
| 12 |
inference: true
|
| 13 |
---
|
| 14 |
+
|
| 15 |
# Textual inversion text2image fine-tuning - hcarrion/abscess
|
|
|
|
| 16 |
|
| 17 |
+
These are textual inversion adaptation weights for `stabilityai/stable-diffusion-2-1-base` to generate dermatological images representing the **abscess** class.
|
| 18 |
+
|
| 19 |
+
This model was trained as part of the paper:
|
| 20 |
+
**[Controllable Generation of Diverse Dermatological Imagery for Fair and Efficient Malignancy Classification](https://huggingface.co/papers/2607.12987)** (MICCAI 2026).
|
| 21 |
+
|
| 22 |
+
- **Code:** [hectorcarrion/ControllableGenDDI](https://github.com/hectorcarrion/ControllableGenDDI)
|
| 23 |
+
- **Dataset:** [hcarrion/ControllableGenDDI](https://huggingface.co/datasets/hcarrion/ControllableGenDDI)
|
| 24 |
+
|
| 25 |
+
## Citation
|
| 26 |
|
| 27 |
+
```bibtex
|
| 28 |
+
@inproceedings{carrion2026cgddi,
|
| 29 |
+
title = {Controllable Generation of Diverse Dermatological Imagery for Fair and Efficient Malignancy Classification},
|
| 30 |
+
author = {Carri{\'o}n, H{\'e}ctor and Norouzi, Narges},
|
| 31 |
+
booktitle = {Medical Image Computing and Computer-Assisted Intervention (MICCAI)},
|
| 32 |
+
year = {2026},
|
| 33 |
+
publisher = {Springer},
|
| 34 |
+
series = {Lecture Notes in Computer Science}
|
| 35 |
+
}
|
| 36 |
+
```
|