Kubanychbek Emil
commited on
Commit
·
7f7e464
1
Parent(s):
c90f741
Update README.md
Browse files
README.md
CHANGED
|
@@ -10,76 +10,37 @@ tags:
|
|
| 10 |
inference: true
|
| 11 |
---
|
| 12 |
|
| 13 |
-
AnyLORA is the
|
|
|
|
|
|
|
| 14 |
|
| 15 |
-
Examples:
|
| 16 |
-
|
| 17 |
-

|
| 18 |
-

|
| 19 |
-

|
| 20 |
-
|
| 21 |
-
-------
|
| 22 |
-
|
| 23 |
-
<font color="grey">Thanks to [Linaqruf](https://huggingface.co/Linaqruf) for letting me borrow his model card for reference.
|
| 24 |
|
| 25 |
-
|
| 26 |
-
|
| 27 |
-
Welcome to Anything V4 - a latent diffusion model for weebs. The newest version of Anything. This model is intended to produce high-quality, highly detailed anime style with just a few prompts. Like other anime-style Stable Diffusion models, it also supports danbooru tags to generate images.
|
| 28 |
-
|
| 29 |
-
e.g. **_1girl, white hair, golden eyes, beautiful eyes, detail, flower meadow, cumulonimbus clouds, lighting, detailed sky, garden_**
|
| 30 |
-
|
| 31 |
-
I think the V4.5 version better though, it's in this repo. feel free 2 try it.
|
| 32 |
|
| 33 |
-
|
| 34 |
|
| 35 |
|
| 36 |
-
|
| 37 |
|
| 38 |
-
We support a [Gradio](https://github.com/gradio-app/gradio) Web UI to run anything-v4.0:
|
| 39 |
-
[](https://huggingface.co/spaces/akhaliq/anything-v4.0)
|
| 40 |
|
| 41 |
## 🧨 Diffusers
|
| 42 |
|
| 43 |
This model can be used just like any other Stable Diffusion model. For more information,
|
| 44 |
please have a look at the [Stable Diffusion](https://huggingface.co/docs/diffusers/api/pipelines/stable_diffusion).
|
| 45 |
|
| 46 |
-
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]().
|
| 47 |
|
| 48 |
```python
|
| 49 |
from diffusers import StableDiffusionPipeline
|
| 50 |
import torch
|
| 51 |
|
| 52 |
-
model_id = "
|
| 53 |
pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)
|
| 54 |
pipe = pipe.to("cuda")
|
| 55 |
|
| 56 |
-
prompt = "
|
| 57 |
image = pipe(prompt).images[0]
|
| 58 |
|
| 59 |
-
image.save("./
|
| 60 |
-
```
|
| 61 |
-
|
| 62 |
-
## Examples
|
| 63 |
-
|
| 64 |
-
Below are some examples of images generated using this model:
|
| 65 |
-
|
| 66 |
-
**Anime Girl:**
|
| 67 |
-

|
| 68 |
-
```
|
| 69 |
-
masterpiece, best quality, 1girl, white hair, medium hair, cat ears, closed eyes, looking at viewer, :3, cute, scarf, jacket, outdoors, streets
|
| 70 |
-
Steps: 20, Sampler: DPM++ 2M Karras, CFG scale: 7
|
| 71 |
-
```
|
| 72 |
-
**Anime Boy:**
|
| 73 |
-

|
| 74 |
-
```
|
| 75 |
-
1boy, bishounen, casual, indoors, sitting, coffee shop, bokeh
|
| 76 |
-
Steps: 20, Sampler: DPM++ 2M Karras, CFG scale: 7
|
| 77 |
-
```
|
| 78 |
-
**Scenery:**
|
| 79 |
-

|
| 80 |
-
```
|
| 81 |
-
scenery, village, outdoors, sky, clouds
|
| 82 |
-
Steps: 50, Sampler: DPM++ 2S a Karras, CFG scale: 7
|
| 83 |
```
|
| 84 |
|
| 85 |
## License
|
|
@@ -90,8 +51,4 @@ The CreativeML OpenRAIL License specifies:
|
|
| 90 |
|
| 91 |
## Big Thanks to
|
| 92 |
|
| 93 |
-
- [
|
| 94 |
-

|
| 95 |
-

|
| 96 |
-
|
| 97 |
-

|
|
|
|
| 10 |
inference: true
|
| 11 |
---
|
| 12 |
|
| 13 |
+
**AnyLORA** is the diffuser that is highly compatible with **Civitai's** LORA weights.
|
| 14 |
+
Basically, it is just a converted version of [Lykon/AnyLORA][https://huggingface.co/Lykon/AnyLoRA/tree/main]
|
| 15 |
+
This model was created by **[Lykon](https://civitai.com/user/Lykon)** from Civitai. All credits for him. Thanks for creating this wonderful model.
|
| 16 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17 |
|
| 18 |
+
Examples:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 19 |
|
| 20 |
+

|
| 21 |
|
| 22 |
|
| 23 |
+
-------
|
| 24 |
|
|
|
|
|
|
|
| 25 |
|
| 26 |
## 🧨 Diffusers
|
| 27 |
|
| 28 |
This model can be used just like any other Stable Diffusion model. For more information,
|
| 29 |
please have a look at the [Stable Diffusion](https://huggingface.co/docs/diffusers/api/pipelines/stable_diffusion).
|
| 30 |
|
|
|
|
| 31 |
|
| 32 |
```python
|
| 33 |
from diffusers import StableDiffusionPipeline
|
| 34 |
import torch
|
| 35 |
|
| 36 |
+
model_id = "kubanemil/AnyLORA"
|
| 37 |
pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)
|
| 38 |
pipe = pipe.to("cuda")
|
| 39 |
|
| 40 |
+
prompt = "masterpiece, best quality, 1girl,"
|
| 41 |
image = pipe(prompt).images[0]
|
| 42 |
|
| 43 |
+
image.save("./anime_girl.png")
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 44 |
```
|
| 45 |
|
| 46 |
## License
|
|
|
|
| 51 |
|
| 52 |
## Big Thanks to
|
| 53 |
|
| 54 |
+
- [Lykon](https://huggingface.co/Lykon)
|
|
|
|
|
|
|
|
|
|
|
|