Add link to paper, code and citation

#1
by nielsr HF Staff - opened
Files changed (1) hide show
  1. README.md +24 -8
README.md CHANGED
@@ -1,10 +1,10 @@
1
  ---
 
 
2
  license: other
3
  license_name: flux-1-dev-non-commercial-license
4
  license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md
5
- library_name: diffusers
6
  pipeline_tag: text-to-image
7
- base_model: black-forest-labs/FLUX.1-dev
8
  tags:
9
  - diffusers
10
  - flux
@@ -16,16 +16,19 @@ tags:
16
 
17
  # FLUX-RS
18
 
 
 
19
  FLUX-RS is a remote sensing text-to-image checkpoint obtained by fine-tuning `black-forest-labs/FLUX.1-dev` on a curated remote sensing corpus. It is designed to improve semantic alignment and visual realism for aerial and satellite scene synthesis, especially in settings that require dense structural details such as buildings, roads, vehicles, farmland parcels, and waterfront layouts.
20
 
21
  This model serves as the domain-specialized generative prior used in **SHARP**: *Spectrum-aware Highly-dynamic Adaptation for Resolution Promotion in Remote Sensing Synthesis*.
22
 
23
  ## Model Summary
24
 
25
- - Base model: `black-forest-labs/FLUX.1-dev`
26
- - Model type: Diffusers `FluxPipeline`
27
- - Domain: remote sensing text-to-image generation
28
- - Intended use: research, evaluation, and remote sensing synthesis experiments
 
29
 
30
  ## Usage
31
 
@@ -64,7 +67,20 @@ python run_sharp.py \
64
  --height 1024
65
  ```
66
 
67
- ## License
 
 
 
 
 
 
 
 
 
 
 
 
68
 
69
- This checkpoint is derived from `black-forest-labs/FLUX.1-dev`. Please follow the license and usage terms associated with the base model when using or redistributing FLUX-RS.
70
 
 
 
1
  ---
2
+ base_model: black-forest-labs/FLUX.1-dev
3
+ library_name: diffusers
4
  license: other
5
  license_name: flux-1-dev-non-commercial-license
6
  license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md
 
7
  pipeline_tag: text-to-image
 
8
  tags:
9
  - diffusers
10
  - flux
 
16
 
17
  # FLUX-RS
18
 
19
+ [**Paper**](https://huggingface.co/papers/2603.21783) | [**Code**](https://github.com/bxuanz/SHARP)
20
+
21
  FLUX-RS is a remote sensing text-to-image checkpoint obtained by fine-tuning `black-forest-labs/FLUX.1-dev` on a curated remote sensing corpus. It is designed to improve semantic alignment and visual realism for aerial and satellite scene synthesis, especially in settings that require dense structural details such as buildings, roads, vehicles, farmland parcels, and waterfront layouts.
22
 
23
  This model serves as the domain-specialized generative prior used in **SHARP**: *Spectrum-aware Highly-dynamic Adaptation for Resolution Promotion in Remote Sensing Synthesis*.
24
 
25
  ## Model Summary
26
 
27
+ - **Developed by:** Bingxuan Zhao, Qing Zhou, Chuang Yang, and Qi Wang
28
+ - **Base model:** `black-forest-labs/FLUX.1-dev`
29
+ - **Model type:** Diffusers `FluxPipeline`
30
+ - **Domain:** Remote sensing text-to-image generation
31
+ - **Intended use:** Research, evaluation, and remote sensing synthesis experiments
32
 
33
  ## Usage
34
 
 
67
  --height 1024
68
  ```
69
 
70
+ ## Citation
71
+
72
+ ```bibtex
73
+ @misc{zhao2026sharpspectrumawarehighlydynamicadaptation,
74
+ title={SHARP: Spectrum-aware Highly-dynamic Adaptation for Resolution Promotion in Remote Sensing Synthesis},
75
+ author={Bingxuan Zhao and Qing Zhou and Chuang Yang and Qi Wang},
76
+ year={2026},
77
+ eprint={2603.21783},
78
+ archivePrefix={arXiv},
79
+ primaryClass={cs.CV},
80
+ url={https://arxiv.org/abs/2603.21783},
81
+ }
82
+ ```
83
 
84
+ ## License
85
 
86
+ This checkpoint is derived from `black-forest-labs/FLUX.1-dev`. Please follow the license and usage terms associated with the base model when using or redistributing FLUX-RS.