rromb commited on
Commit
373dc60
1 Parent(s): ee6e4db

Create README.md

Browse files
Files changed (1) hide show
  1. README.md +80 -0
README.md ADDED
@@ -0,0 +1,80 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ # For reference on model card metadata, see the spec: https://github.com/huggingface/hub-docs/blob/main/modelcard.md?plain=1
3
+ # Doc / guide: https://huggingface.co/docs/hub/model-cards
4
+ {}
5
+ ---
6
+
7
+ # SD-Turbo Model Card
8
+
9
+ <!-- Provide a quick summary of what the model is/does. -->
10
+ ![row01](output_tile.jpg)
11
+ SD-Turbo is a fast generative text-to-image model that can synthesize photorealistic images from a text prompt in a single network evaluation.
12
+
13
+ ## Model Details
14
+
15
+ ### Model Description
16
+ TODO: ADD DETAILED MODEL DESCRIPTION.
17
+
18
+
19
+
20
+ - **Developed by:** Stability AI
21
+ - **Funded by:** Stability AI
22
+ - **Model type:** Generative text-to-image model
23
+ - **Finetuned from model:** [Stable Diffusion 1.5](https://huggingface.co/runwayml/stable-diffusion-v1-5)
24
+
25
+ ### Model Sources
26
+
27
+ For research purposes, we recommend our `generative-models` Github repository (https://github.com/Stability-AI/generative-models),
28
+ which implements the most popular diffusion frameworks (both training and inference).
29
+
30
+ - **Repository:** https://github.com/Stability-AI/generative-models
31
+ - **Paper:** TODO
32
+
33
+
34
+ ## Evaluation
35
+ ![comparison](comparison.png)
36
+ The chart above evaluates user preference for SD-Turbo over TODO.
37
+ SDXL-Turbo is preferred by human voters in terms of image quality and prompt following.
38
+ For details on the user study, we refer to the [research paper](TODO)
39
+
40
+ ## Uses
41
+
42
+ ### Direct Use
43
+
44
+ The model is intended for research purposes only. Possible research areas and tasks include
45
+
46
+ - Research on generative models.
47
+ - Research on real-time applications of generative models.
48
+ - Research on the impact of real-time generative models.
49
+ - Safe deployment of models which have the potential to generate harmful content.
50
+ - Probing and understanding the limitations and biases of generative models.
51
+ - Generation of artworks and use in design and other artistic processes.
52
+ - Applications in educational or creative tools.
53
+
54
+ Excluded uses are described below.
55
+
56
+ ### Out-of-Scope Use
57
+
58
+ The model was not trained to be factual or true representations of people or events,
59
+ and therefore using the model to generate such content is out-of-scope for the abilities of this model.
60
+ The model should not be used in any way that violates Stability AI's [Acceptable Use Policy](https://stability.ai/use-policy).
61
+
62
+ ## Limitations and Bias
63
+
64
+ ### Limitations
65
+ - The generated images are of a fixed resolution (512x512 pix), and the model does not achieve perfect photorealism.
66
+ - The model cannot render legible text.
67
+ - Faces and people in general may not be generated properly.
68
+ - The autoencoding part of the model is lossy.
69
+
70
+
71
+ ### Recommendations
72
+
73
+ The model is intended for research purposes only.
74
+
75
+ ## How to Get Started with the Model
76
+
77
+ Check out https://github.com/Stability-AI/generative-models
78
+
79
+
80
+