Ricardouchub commited on
Commit
c6939ae
·
verified ·
1 Parent(s): 7ec4d5d

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -4
README.md CHANGED
@@ -3,8 +3,6 @@ license: mit
3
  base_model:
4
  - stabilityai/stable-diffusion-xl-base-1.0
5
  pipeline_tag: text-to-image
6
- datasets:
7
- - neuralcatcher/hateful_memes
8
  ---
9
  # SarcasmDiffusion — SDXL Fused Meme Generator
10
 
@@ -54,7 +52,7 @@ SarcasmDiffusion is a diffusion-based generative model focused on producing **cl
54
  - **Frozen:** VAE, text_encoder, text_encoder_2
55
 
56
  ### Data
57
- - Source: *Hateful Memes* (Facebook AI).
58
  - We **excluded** labeled hateful samples and applied **NLP enrichment**:
59
  - Emotion scoring (GoEmotions distilled) and irony scoring (RoBERTa‑irony).
60
  - Heuristics + percentiles → tones: `humor / irony / neutral`.
@@ -137,7 +135,7 @@ pip install "diffusers==0.35.1" "transformers==4.45.2" "accelerate==1.10.1
137
 
138
  ## License
139
 
140
- - **Code:** MIT (project-level).
141
  - **Model weights:** follow the base model’s license (Stability AI / SDXL Base 1.0).
142
  - **Data:** Users must obtain *Hateful Memes* from its source and agree to its terms.
143
 
 
3
  base_model:
4
  - stabilityai/stable-diffusion-xl-base-1.0
5
  pipeline_tag: text-to-image
 
 
6
  ---
7
  # SarcasmDiffusion — SDXL Fused Meme Generator
8
 
 
52
  - **Frozen:** VAE, text_encoder, text_encoder_2
53
 
54
  ### Data
55
+ - Source: *Hateful Memes* (Facebook AI).
56
  - We **excluded** labeled hateful samples and applied **NLP enrichment**:
57
  - Emotion scoring (GoEmotions distilled) and irony scoring (RoBERTa‑irony).
58
  - Heuristics + percentiles → tones: `humor / irony / neutral`.
 
135
 
136
  ## License
137
 
138
+ - **Code:** MIT
139
  - **Model weights:** follow the base model’s license (Stability AI / SDXL Base 1.0).
140
  - **Data:** Users must obtain *Hateful Memes* from its source and agree to its terms.
141