danaevan commited on
Commit
c8ab872
1 Parent(s): 019ae01

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -4
README.md CHANGED
@@ -100,10 +100,10 @@ The following table summarizes our survey results:
100
 
101
  ## Runtime Benchmarks
102
 
103
- The following tables provide an image latency comparison between DeciDiffusion 1.0 and Stable Diffusion 1.5.
104
 
105
- DeciDiffusion 1.0 vs. Stable Diffusion 1.5 at FP16 precision
106
- |Inference Tool + Iterations| DeciDiffusion 1.0 on A10 (seconds/image) | Stable Diffusion 1.5 on A10 (seconds/image) |
107
  |:----------|:----------|:----------|
108
  | HF 50 Iterations | 2.11 | 2.95 |
109
  | Infery 50 Iterations | 1.55 |2.08 |
@@ -142,7 +142,8 @@ The model isn't designed to produce accurate or truthful depictions of people or
142
  #### Misuse and Malicious Use
143
  Misusing the model to produce content that harms or maligns individuals is strictly discouraged. Such misuses include, but aren't limited to:
144
 
145
- - Creating offensive, degrading, or damaging portrayals of individuals, their cultures, religions, or surroundings.- Intentionally promoting or propagating discriminatory content or harmful stereotypes.Deliberately endorsing or disseminating prejudiced content or harmful stereotypes.
 
146
  - Deliberately endorsing or disseminating prejudiced content or harmful stereotypes.
147
  - Posing as someone else without their agreement.
148
  - Generating explicit content without the knowledge or agreement of potential viewers.
 
100
 
101
  ## Runtime Benchmarks
102
 
103
+ The following tables provide an image latency comparison between DeciDiffusion 1.0 and Stable Diffusion v1.5.
104
 
105
+ DeciDiffusion 1.0 vs. Stable Diffusion v1.5 at FP16 precision
106
+ |Inference Tool + Iterations| DeciDiffusion 1.0 on A10 (seconds/image) | Stable Diffusion v1.5 on A10 (seconds/image) |
107
  |:----------|:----------|:----------|
108
  | HF 50 Iterations | 2.11 | 2.95 |
109
  | Infery 50 Iterations | 1.55 |2.08 |
 
142
  #### Misuse and Malicious Use
143
  Misusing the model to produce content that harms or maligns individuals is strictly discouraged. Such misuses include, but aren't limited to:
144
 
145
+ - Creating offensive, degrading, or damaging portrayals of individuals, their cultures, religions, or surroundings.
146
+ - Intentionally promoting or propagating discriminatory content or harmful stereotypes.Deliberately endorsing or disseminating prejudiced content or harmful stereotypes.
147
  - Deliberately endorsing or disseminating prejudiced content or harmful stereotypes.
148
  - Posing as someone else without their agreement.
149
  - Generating explicit content without the knowledge or agreement of potential viewers.