Commit
·
dcaf136
1
Parent(s):
7bbfb7f
Update README.md
Browse files
README.md
CHANGED
|
@@ -8,7 +8,7 @@ This model is based on [ACertainty](https://huggingface.co/JosephusCheung/ACerta
|
|
| 8 |
|
| 9 |
You can use prompts including danbooru tags, just like other anime-style diffusion models. Use token prompt "(Nagayama_Yuunon)" (or Class:"artstyle") for better results.
|
| 10 |
|
| 11 |
-
|
| 12 |
This model can be used just like any other Stable Diffusion model. For more information, please have a look at the [Stable Diffusion](https://huggingface.co/docs/diffusers/api/pipelines/stable_diffusion).
|
| 13 |
|
| 14 |
You can also export the model to [ONNX](https://huggingface.co/docs/diffusers/optimization/onnx), [MPS](https://huggingface.co/docs/diffusers/optimization/mps) and/or FLAX/JAX.
|
|
@@ -29,19 +29,19 @@ image = pipe(prompt).images[0]
|
|
| 29 |
image.save("./pikachu.png")
|
| 30 |
```
|
| 31 |
|
| 32 |
-
|
| 33 |
****
|
| 34 |
|
| 35 |
-
|
| 36 |
* Self-collected and well-prepared class image instead of self generation, give oppotunities of training certain parts of images (eg: hands, feet, shoes).
|
| 37 |
* May use higher resolution dataset for training (eg. 768^2).
|
| 38 |
* Much proper epoches/learning speed/training steps of models.
|
| 39 |
* Can training with **rectangle** images.
|
| 40 |
|
| 41 |
-
|
| 42 |
This model is produced using Runpod RTX A5000 (24GB), with 12 vCPU, 125GB RAM and 50GB storage. The total operations costs around $15.
|
| 43 |
|
| 44 |
-
|
| 45 |
This model is open access and available to all, with a CreativeML OpenRAIL-M license further specifying rights and usage. The CreativeML OpenRAIL License specifies:
|
| 46 |
|
| 47 |
1. You can't use the model to deliberately produce nor share illegal or harmful outputs or content
|
|
|
|
| 8 |
|
| 9 |
You can use prompts including danbooru tags, just like other anime-style diffusion models. Use token prompt "(Nagayama_Yuunon)" (or Class:"artstyle") for better results.
|
| 10 |
|
| 11 |
+
## 🧨 Diffusers
|
| 12 |
This model can be used just like any other Stable Diffusion model. For more information, please have a look at the [Stable Diffusion](https://huggingface.co/docs/diffusers/api/pipelines/stable_diffusion).
|
| 13 |
|
| 14 |
You can also export the model to [ONNX](https://huggingface.co/docs/diffusers/optimization/onnx), [MPS](https://huggingface.co/docs/diffusers/optimization/mps) and/or FLAX/JAX.
|
|
|
|
| 29 |
image.save("./pikachu.png")
|
| 30 |
```
|
| 31 |
|
| 32 |
+
## 📋 Demos
|
| 33 |
****
|
| 34 |
|
| 35 |
+
## ✍️ Future Plans / Todo for V1
|
| 36 |
* Self-collected and well-prepared class image instead of self generation, give oppotunities of training certain parts of images (eg: hands, feet, shoes).
|
| 37 |
* May use higher resolution dataset for training (eg. 768^2).
|
| 38 |
* Much proper epoches/learning speed/training steps of models.
|
| 39 |
* Can training with **rectangle** images.
|
| 40 |
|
| 41 |
+
## 💻 Hardwares
|
| 42 |
This model is produced using Runpod RTX A5000 (24GB), with 12 vCPU, 125GB RAM and 50GB storage. The total operations costs around $15.
|
| 43 |
|
| 44 |
+
## License
|
| 45 |
This model is open access and available to all, with a CreativeML OpenRAIL-M license further specifying rights and usage. The CreativeML OpenRAIL License specifies:
|
| 46 |
|
| 47 |
1. You can't use the model to deliberately produce nor share illegal or harmful outputs or content
|