Update README.md
Browse files
README.md
CHANGED
|
@@ -31,14 +31,14 @@ The file NetaYume_Lumina_v2_all_in_one.safetensors is an all-in-one file that co
|
|
| 31 |
|
| 32 |
---
|
| 33 |
|
| 34 |
-
|
| 35 |
- **Text Encoder**: Pre-trained **Gemma-2-2b**
|
| 36 |
- **Variational Autoencoder**: Pre-trained **Flux.1 dev's VAE**
|
| 37 |
- **Image Backbone**: Fine-tune **NetaLumina's Image Backbone**
|
| 38 |
|
| 39 |
---
|
| 40 |
|
| 41 |
-
|
| 42 |
|
| 43 |
**System Prompt:** This help you generate your desired images more easily by understanding and aligning with your prompts.
|
| 44 |
|
|
@@ -56,7 +56,7 @@ For anime-style images using Danbooru tags:
|
|
| 56 |
- res_multistep (with scheduler: linear_quadratic)
|
| 57 |
|
| 58 |
---
|
| 59 |
-
|
| 60 |
- [narugo1992](https://huggingface.co/narugo) – for the invaluable Danbooru dataset
|
| 61 |
- [Alpha-VLLM](https://huggingface.co/Alpha-VLLM) - for creating the a wonderful model!
|
| 62 |
- [Neta Lumina](https://huggingface.co/neta-art/Neta-Lumina) and his team – for openly sharing awesome model.
|
|
|
|
| 31 |
|
| 32 |
---
|
| 33 |
|
| 34 |
+
**II. Model Components & Training Details**
|
| 35 |
- **Text Encoder**: Pre-trained **Gemma-2-2b**
|
| 36 |
- **Variational Autoencoder**: Pre-trained **Flux.1 dev's VAE**
|
| 37 |
- **Image Backbone**: Fine-tune **NetaLumina's Image Backbone**
|
| 38 |
|
| 39 |
---
|
| 40 |
|
| 41 |
+
**III. Suggestion**
|
| 42 |
|
| 43 |
**System Prompt:** This help you generate your desired images more easily by understanding and aligning with your prompts.
|
| 44 |
|
|
|
|
| 56 |
- res_multistep (with scheduler: linear_quadratic)
|
| 57 |
|
| 58 |
---
|
| 59 |
+
**IV. Acknowledgments**
|
| 60 |
- [narugo1992](https://huggingface.co/narugo) – for the invaluable Danbooru dataset
|
| 61 |
- [Alpha-VLLM](https://huggingface.co/Alpha-VLLM) - for creating the a wonderful model!
|
| 62 |
- [Neta Lumina](https://huggingface.co/neta-art/Neta-Lumina) and his team – for openly sharing awesome model.
|