Update README.md
Browse files
README.md
CHANGED
@@ -8,6 +8,8 @@ Chroma1-HD is an **8.9B** parameter text-to-image foundational model based on **
|
|
8 |
|
9 |
As a **base model**, Chroma1 is intentionally designed to be an excellent starting point for **finetuning**. It provides a strong, neutral foundation for developers, researchers, and artists to create specialized models.
|
10 |
|
|
|
|
|
11 |
### Key Features
|
12 |
* **High-Performance Base:** 8.9B parameters, built on the powerful FLUX.1 architecture.
|
13 |
* **Easily Finetunable:** Designed as an ideal checkpoint for creating custom, specialized models.
|
@@ -75,7 +77,7 @@ Chroma is intended to be used as a **base model** for researchers and developers
|
|
75 |
* As a foundational component in larger AI systems.
|
76 |
|
77 |
## Limitations and Bias Statement
|
78 |
-
Chroma is trained on a broad, filtered dataset from the internet. As such, it may reflect the biases and stereotypes present in its training data. The model is released in
|
79 |
|
80 |
Users are responsible for their own use of this model. It has the potential to generate content that may be considered harmful, explicit, or offensive. I encourage developers to implement appropriate safeguards and ethical considerations in their downstream applications.
|
81 |
|
|
|
8 |
|
9 |
As a **base model**, Chroma1 is intentionally designed to be an excellent starting point for **finetuning**. It provides a strong, neutral foundation for developers, researchers, and artists to create specialized models.
|
10 |
|
11 |
+
for the fast CFG "baked" version please go to [Chroma1-Flash](https://huggingface.co/lodestones/Chroma1-Flash).
|
12 |
+
|
13 |
### Key Features
|
14 |
* **High-Performance Base:** 8.9B parameters, built on the powerful FLUX.1 architecture.
|
15 |
* **Easily Finetunable:** Designed as an ideal checkpoint for creating custom, specialized models.
|
|
|
77 |
* As a foundational component in larger AI systems.
|
78 |
|
79 |
## Limitations and Bias Statement
|
80 |
+
Chroma is trained on a broad, filtered dataset from the internet. As such, it may reflect the biases and stereotypes present in its training data. The model is released in a state as is and has not been aligned with a specific safety filter.
|
81 |
|
82 |
Users are responsible for their own use of this model. It has the potential to generate content that may be considered harmful, explicit, or offensive. I encourage developers to implement appropriate safeguards and ethical considerations in their downstream applications.
|
83 |
|