prithivMLmods commited on
Commit
7bc7f2b
1 Parent(s): 1d78b90

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +42 -0
README.md CHANGED
@@ -22,6 +22,48 @@ license: creativeml-openrail-m
22
 
23
  <Gallery />
24
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
25
 
26
  ## Trigger words
27
 
 
22
 
23
  <Gallery />
24
 
25
+ **The model is still in the training phase. This is not the final version and may contain artifacts and perform poorly in some cases.**
26
+
27
+ ## Model description
28
+
29
+ **prithivMLmods/SD-3.5-Large-Handpainted-Sketchfab-3D-LoRA**
30
+
31
+ Image Processing Parameters
32
+
33
+ | Parameter | Value | Parameter | Value |
34
+ |---------------------------|--------|---------------------------|--------|
35
+ | LR Scheduler | constant | Noise Offset | 0.03 |
36
+ | Optimizer | AdamW | Multires Noise Discount | 0.1 |
37
+ | Network Dim | 64 | Multires Noise Iterations | 10 |
38
+ | Network Alpha | 32 | Repeat & Steps | 20 & 2K |
39
+ | Epoch | 12 | Save Every N Epochs | 1 |
40
+
41
+ Labeling: florence2-en(natural language & English)
42
+
43
+ Total Images Used for Training : 38
44
+
45
+ ## Setting up
46
+
47
+ ```python
48
+ import torch
49
+ from diffusers import StableDiffusion3Pipeline
50
+
51
+ pipe = StableDiffusion3Pipeline.from_pretrained("stabilityai/stable-diffusion-3.5-large", torch_dtype=torch.bfloat16)
52
+ pipe.load_lora_weights("prithivMLmods/SD-3.5-Large-Handpainted-Sketchfab-3D-LoRA", weight_name=" SD3.5-Large-Handpainted-Sketchfab.safetensors")
53
+ pipe.fuse_lora(lora_scale=1.0)
54
+ pipe.to("cuda")
55
+
56
+ prompt = "Handpainted, sketchfab, 3D, ured from a low-angle perspective on a gray background, a vibrant purple shotgun is seen in mid-flight. The gun has a silver body, a silver handle, and a brown leather handle. The handle is adorned with silver metal studs, adding a touch of color to the scene. The background is a solid gray, creating a stark contrast to the gun."
57
+ negative_prompt = "(lowres, low quality, worst quality)"
58
+
59
+ image = pipe(prompt=prompt,
60
+ negative_prompt=negative_prompt
61
+ num_inference_steps=24,
62
+ guidance_scale=4.0,
63
+ width=960, height=1280,
64
+ ).images[0]
65
+ image.save(f"example.jpg")
66
+ ```
67
 
68
  ## Trigger words
69