minimaxir commited on
Commit
b9090f5
1 Parent(s): 49f7711

README draft

Browse files
Files changed (1) hide show
  1. README.md +43 -2
README.md CHANGED
@@ -12,8 +12,49 @@ inference: true
12
 
13
  # sdxl-wrong-lora
14
 
15
- A LoRA for SDXL 1.0 Base which increases output image quality after loading it and using `wrong` as a negative prompt.
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
16
 
17
  ## Methodology
18
 
19
- The methodology for creating this LoRA is similar to the [wrong SD 2.0 textual inversion embedding](https://huggingface.co/minimaxir/wrong_embedding_sd_2_0), except trained as a LoRA since textual inversion on SDXL is complicated.
 
 
 
 
 
 
12
 
13
  # sdxl-wrong-lora
14
 
15
+ A LoRA for SDXL 1.0 Base which improves output image quality after loading it and using `wrong` as a negative prompt during inference.
16
+
17
+ Benefits of using this LoRA:
18
+
19
+ - Higher color saturation and vibrance
20
+ - Higher detail in textures/fabrics
21
+ - Higher sharpness for blurry/background objects
22
+ - Less likely to have random artifacts
23
+ - Appears to allow the model to follow the input prompt with a more expected behavior
24
+
25
+ ## Usage
26
+
27
+ The LoRA can be loaded using `load_lora_weights` like any other LoRA in `diffusers`:
28
+
29
+ ```py
30
+ import torch
31
+ from diffusers import DiffusionPipeline, AutoencoderKL
32
+
33
+ vae = AutoencoderKL.from_pretrained("madebyollin/sdxl-vae-fp16-fix", torch_dtype=torch.float16)
34
+ base = DiffusionPipeline.from_pretrained(
35
+ "stabilityai/stable-diffusion-xl-base-1.0",
36
+ vae=vae,
37
+ torch_dtype=torch.float16,
38
+ variant="fp16",
39
+ use_safetensors=True
40
+ )
41
+
42
+ base.load_lora_weights("minimaxir/sdxl-wrong-lora")
43
+
44
+ _ = base.to("cuda")
45
+ ```
46
+
47
+ During inference, use `wrong` as the sole negative prompt.
48
+
49
+ ## Examples
50
+
51
+ Left is the base model output (no LoRA) + refiner, right is base + LoRA and refiner. The generations use the same seed.
52
 
53
  ## Methodology
54
 
55
+ The methodology for creating this LoRA is similar to my [wrong SD 2.0 textual inversion embedding](https://huggingface.co/minimaxir/wrong_embedding_sd_2_0), except trained as a LoRA since textual inversion on SDXL is complicated. The base images were generated from SDXL itself.
56
+
57
+ ## Notes
58
+
59
+ - It's possible to use `not wrong` in the prompt itself but in testing it has no effect.
60
+ - You can use other negative prompts in conjunction with the `wrong` prompt but you may want to weight them.