Warlord-K commited on
Commit
6749ebd
1 Parent(s): c945057

Initial Commit

Browse files
.gitattributes CHANGED
@@ -33,3 +33,7 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ image_0.png filter=lfs diff=lfs merge=lfs -text
37
+ image_1.png filter=lfs diff=lfs merge=lfs -text
38
+ image_2.png filter=lfs diff=lfs merge=lfs -text
39
+ image_3.png filter=lfs diff=lfs merge=lfs -text
README.md CHANGED
@@ -1,60 +1,27 @@
1
- # LoRA training Cog model
2
 
3
- ## Use on Replicate
 
 
 
 
 
 
 
 
 
 
 
 
 
4
 
5
- Easy-to-use model pre-configured for faces, objects, and styles:
6
 
7
- [![Replicate](https://replicate.com/replicate/lora-training/badge)](https://replicate.com/replicate/lora-training)
 
 
 
8
 
9
- Advanced model with all the parameters:
10
 
11
- [![Replicate](https://replicate.com/replicate/lora-advanced-training/badge)](https://replicate.com/replicate/lora-advanced-training)
12
 
13
- Feed the trained model into this inference model to run predictions:
14
-
15
- [![Replicate](https://replicate.com/replicate/lora/badge)](https://replicate.com/replicate/lora)
16
-
17
- If you want to share your trained LoRAs, please join the `#lora` channel in the [Replicate Discord](https://discord.gg/replicate).
18
-
19
- ## Use locally
20
-
21
- First, download the pre-trained weights [with your Hugging Face auth token](https://huggingface.co/settings/tokens):
22
-
23
- ```
24
- cog run script/download-weights <your-hugging-face-auth-token>
25
- ```
26
-
27
- Then, you can run train your dreambooth:
28
-
29
- ```
30
- cog predict -i instance_data=@my-images.zip
31
- ```
32
-
33
- The resulting LoRA weights file can be used with `patch_pipe` function:
34
-
35
- ```python
36
- from diffusers import StableDiffusionPipeline
37
- from lora_diffusion import patch_pipe, tune_lora_scale, image_grid
38
- import torch
39
-
40
- model_id = "runwayml/stable-diffusion-v1-5"
41
-
42
- pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16).to(
43
- "cuda:1"
44
- )
45
-
46
- patch_pipe(pipe, "./my-images.safetensors")
47
- prompt = "detailed photo of <s1><s2>, detailed face, a brown cloak, brown steampunk corset, belt, virtual youtuber, cowboy shot, feathers in hair, feather hair ornament, white shirt, brown gloves, shooting arrows"
48
-
49
- tune_lora_scale(pipe.unet, 0.8)
50
- tune_lora_scale(pipe.text_encoder, 0.8)
51
-
52
- imgs = pipe(
53
- [prompt],
54
- num_inference_steps=50,
55
- guidance_scale=4.5,
56
- height=640,
57
- width=512,
58
- ).images
59
- ...
60
- ```
 
 
1
 
2
+ ---
3
+ license: openrail++
4
+ base_model: segmind/SSD-1B-fp32
5
+ instance_prompt: tssd tattoo
6
+ tags:
7
+ - stable-diffusion-xl
8
+ - stable-diffusion-xl-diffusers
9
+ - text-to-image
10
+ - diffusers
11
+ - lora
12
+ inference: true
13
+ ---
14
+
15
+ # LoRA DreamBooth - Warlord-K/lora-tattoo-sdxl
16
 
17
+ These are LoRA adaption weights for segmind/SSD-1B-fp32. The weights were trained on tssd tattoo using [DreamBooth](https://dreambooth.github.io/). You can find some example images in the following.
18
 
19
+ ![img_0](./image_0.png)
20
+ ![img_1](./image_1.png)
21
+ ![img_2](./image_2.png)
22
+ ![img_3](./image_3.png)
23
 
 
24
 
25
+ LoRA for the text encoder was enabled: False.
26
 
27
+ Special VAE used for training: madebyollin/sdxl-vae-fp16-fix.
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-500/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36908e927fe5c934ae766ec5668249b589780830a26422bac2b13595f7188c43
3
+ size 22117170
checkpoint-500/pytorch_lora_weights.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4610c0369bb14b35dfb2191f2368c7ce9ad2c44bacf0ab892bc34cb6dcd80bfe
3
+ size 10915240
checkpoint-500/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad21784909e1d7a8e152b13c9e3f57c7789baa52bc394285107edb2324030cb8
3
+ size 15060
checkpoint-500/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18b984273ea2d45b7ffb1d047bb359d93111e41fcad70d16a1b453fd38f72636
3
+ size 988
checkpoint-500/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81a7fe0a2983de695c44ba167520d4ce1ca01157e36e90498bee8c9d8e4b61fc
3
+ size 1000
image_0.png ADDED

Git LFS Details

  • SHA256: 3a2e9288e1a7f6dea74705ceb2a9d20be282c57e15c2dc71e753e1befa20dca7
  • Pointer size: 132 Bytes
  • Size of remote file: 1.66 MB
image_1.png ADDED

Git LFS Details

  • SHA256: bcaf4102bf5680e2e3ab65806789044df8cc6df6c534b2abacc783ae5c07a1ef
  • Pointer size: 132 Bytes
  • Size of remote file: 1.7 MB
image_2.png ADDED

Git LFS Details

  • SHA256: e7e7c4762ccffa1f08a1e18a706fecaa22f7a26e4bf81954130e30428591c87a
  • Pointer size: 132 Bytes
  • Size of remote file: 1.69 MB
image_3.png ADDED

Git LFS Details

  • SHA256: 9d352ccd095dff4eeb614442450556f3cf10bc42a334f38b77a5cd8ff6e32aff
  • Pointer size: 132 Bytes
  • Size of remote file: 1.8 MB
pytorch_lora_weights.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4610c0369bb14b35dfb2191f2368c7ce9ad2c44bacf0ab892bc34cb6dcd80bfe
3
+ size 10915240