jbilcke-hf HF staff commited on
Commit
d69ec89
1 Parent(s): e004c9c

saving checkpoint-300

Browse files
README.md ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ ---
3
+ base_model: stabilityai/stable-diffusion-xl-base-1.0
4
+ instance_prompt: cyberpunk-2077
5
+ tags:
6
+ - stable-diffusion-xl
7
+ - stable-diffusion-xl-diffusers
8
+ - text-to-image
9
+ - diffusers
10
+ - lora
11
+ inference: false
12
+ datasets:
13
+ - jbilcke-hf/cyberpunk-2077
14
+ ---
15
+
16
+ # LoRA DreamBooth - jbilcke-hf/sdxl-cyberpunk-2077
17
+ ## MODEL IS CURRENTLY TRAINING ...
18
+ Last checkpoint saved: checkpoint-300
19
+ These are LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0 trained on @fffiloni's SD-XL trainer.
20
+ The weights were trained on the concept prompt:
21
+ ```
22
+ cyberpunk-2077
23
+ ```
24
+ Use this keyword to trigger your custom model in your prompts.
25
+ LoRA for the text encoder was enabled: False.
26
+ Special VAE used for training: madebyollin/sdxl-vae-fp16-fix.
27
+ ## Usage
28
+ Make sure to upgrade diffusers to >= 0.19.0:
29
+ ```
30
+ pip install diffusers --upgrade
31
+ ```
32
+ In addition make sure to install transformers, safetensors, accelerate as well as the invisible watermark:
33
+ ```
34
+ pip install invisible_watermark transformers accelerate safetensors
35
+ ```
36
+ To just use the base model, you can run:
37
+ ```python
38
+ import torch
39
+ from diffusers import DiffusionPipeline, AutoencoderKL
40
+ device = "cuda" if torch.cuda.is_available() else "cpu"
41
+ vae = AutoencoderKL.from_pretrained('madebyollin/sdxl-vae-fp16-fix', torch_dtype=torch.float16)
42
+ pipe = DiffusionPipeline.from_pretrained(
43
+ "stabilityai/stable-diffusion-xl-base-1.0",
44
+ vae=vae, torch_dtype=torch.float16, variant="fp16",
45
+ use_safetensors=True
46
+ )
47
+ pipe.to(device)
48
+ # This is where you load your trained weights
49
+ specific_safetensors = "pytorch_lora_weights.safetensors"
50
+ lora_scale = 0.9
51
+ pipe.load_lora_weights(
52
+ 'jbilcke-hf/sdxl-cyberpunk-2077',
53
+ weight_name = specific_safetensors,
54
+ # use_auth_token = True
55
+ )
56
+ prompt = "A majestic cyberpunk-2077 jumping from a big stone at night"
57
+ image = pipe(
58
+ prompt=prompt,
59
+ num_inference_steps=50,
60
+ cross_attention_kwargs={"scale": lora_scale}
61
+ ).images[0]
62
+ ```
checkpoint-300/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93553e9bfe9d319ebd823194a926915cf68d95a636a9477c8f53513d0ba9d899
3
+ size 14990599
checkpoint-300/pytorch_lora_weights.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:755ee98c411eb6efd6b983b3861ebbeaa70cc70498c69197898435f44afe5d16
3
+ size 23401064
checkpoint-300/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:765b436265c72cd3365381511f9932339c0bc4fc23069af3538d01da7409d3be
3
+ size 14599
checkpoint-300/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:efafd90182e3d39d1b7c4a686f86e5913f5abc094dc3e2f827a6d479c6cef247
3
+ size 557
checkpoint-300/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a84fb1fc02dc9adb8c44beeab2c46fbc41e10a07e99dad3fcd85350ca2bda9d5
3
+ size 563