Initial Commit

.gitattributes

@@ -33,3 +33,7 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+image_0.png filter=lfs diff=lfs merge=lfs -text
+image_1.png filter=lfs diff=lfs merge=lfs -text
+image_2.png filter=lfs diff=lfs merge=lfs -text
+image_3.png filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,60 +1,27 @@
-# LoRA training Cog model
 
-## Use on Replicate
+---
+license: openrail++
+base_model: segmind/SSD-1B-fp32
+instance_prompt: tssd tattoo
+tags:
+- stable-diffusion-xl
+- stable-diffusion-xl-diffusers
+- text-to-image
+- diffusers
+- lora
+inference: true
+---
+    
+# LoRA DreamBooth - Warlord-K/lora-tattoo-sdxl
 
-Easy-to-use model pre-configured for faces, objects, and styles:
+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. 
 
-[![Replicate](https://replicate.com/replicate/lora-training/badge)](https://replicate.com/replicate/lora-training)
+![img_0](./image_0.png)
+![img_1](./image_1.png)
+![img_2](./image_2.png)
+![img_3](./image_3.png)
 
-Advanced model with all the parameters:
 
-[![Replicate](https://replicate.com/replicate/lora-advanced-training/badge)](https://replicate.com/replicate/lora-advanced-training)
+LoRA for the text encoder was enabled: False.
 
-Feed the trained model into this inference model to run predictions:
-
-[![Replicate](https://replicate.com/replicate/lora/badge)](https://replicate.com/replicate/lora)
-
-If you want to share your trained LoRAs, please join the `#lora` channel in the [Replicate Discord](https://discord.gg/replicate).
-
-## Use locally
-
-First, download the pre-trained weights [with your Hugging Face auth token](https://huggingface.co/settings/tokens):
-
-```
-cog run script/download-weights <your-hugging-face-auth-token>
-```
-
-Then, you can run train your dreambooth:
-
-```
-cog predict -i instance_data=@my-images.zip
-```
-
-The resulting LoRA weights file can be used with `patch_pipe` function:
-
-```python
-from diffusers import StableDiffusionPipeline
-from lora_diffusion import patch_pipe, tune_lora_scale, image_grid
-import torch
-
-model_id = "runwayml/stable-diffusion-v1-5"
-
-pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16).to(
-    "cuda:1"
-)
-
-patch_pipe(pipe, "./my-images.safetensors")
-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"
-
-tune_lora_scale(pipe.unet, 0.8)
-tune_lora_scale(pipe.text_encoder, 0.8)
-
-imgs = pipe(
-    [prompt],
-    num_inference_steps=50,
-    guidance_scale=4.5,
-    height=640,
-    width=512,
-).images
-...
-```
+Special VAE used for training: madebyollin/sdxl-vae-fp16-fix.

checkpoint-500/optimizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36908e927fe5c934ae766ec5668249b589780830a26422bac2b13595f7188c43
+size 22117170

checkpoint-500/pytorch_lora_weights.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4610c0369bb14b35dfb2191f2368c7ce9ad2c44bacf0ab892bc34cb6dcd80bfe
+size 10915240

checkpoint-500/random_states_0.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad21784909e1d7a8e152b13c9e3f57c7789baa52bc394285107edb2324030cb8
+size 15060

checkpoint-500/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18b984273ea2d45b7ffb1d047bb359d93111e41fcad70d16a1b453fd38f72636
+size 988

checkpoint-500/scheduler.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81a7fe0a2983de695c44ba167520d4ce1ca01157e36e90498bee8c9d8e4b61fc
+size 1000

pytorch_lora_weights.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4610c0369bb14b35dfb2191f2368c7ce9ad2c44bacf0ab892bc34cb6dcd80bfe
+size 10915240