elephantmipt commited on
Commit
ed78f91
·
verified ·
1 Parent(s): 6c363f5

End of training

Browse files
Files changed (3) hide show
  1. .gitattributes +1 -0
  2. README.md +75 -0
  3. val_imgs_grid.png +3 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ 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
+ val_imgs_grid.png filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: stable-diffusion-v1-5/stable-diffusion-v1-5
3
+ library_name: diffusers
4
+ license: creativeml-openrail-m
5
+ inference: true
6
+ tags:
7
+ - stable-diffusion
8
+ - stable-diffusion-diffusers
9
+ - text-to-image
10
+ - diffusers
11
+ - diffusers-training
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the training script had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+
18
+ # Text-to-image finetuning - elephantmipt/test_tuned_sd_15
19
+
20
+ This pipeline was finetuned from **stable-diffusion-v1-5/stable-diffusion-v1-5** on the **None** dataset. Below are some example images generated with the finetuned pipeline using the following prompts: ['IMAGE_ TYPE Cocktail Photography GENRE Coktail Shooting Lowlight EMOTION I want to drink it SCENE A beautiful and refreshing glass of a drink called lychee spritz , decorated set against a dreamy background lowlight, fitting to the image ACTORS None LOCATION TYPE Studio CAMERA MODEL Nikon D850 CAMERA LENSE 60mm f 2. 8 Macro SPECIAL EFFECTS Dreamy bokeh TIME_ OF_ DAY Studio lighting INTERACTION None '
21
+ 'Gandalf, Saruman, Radagast. Blue Wizards perform a captivating magic ritual intense focus, vibrant colors swirl like airborne gas. Mystical pentagram unites them. '
22
+ 'wide shot, desert, wall, nature, fuchsia pink, brick red, ochre yellow, pale pink, chipotle orange '
23
+ 'disney pixar style character, dodge challenger srt hellcat illustration drifting under the ocean, cartoon, super detail, no text, 8k, render 3d, wide view vision '
24
+ 'wide shoot of a typical farm in rural surroundings, near a clear water lake, beautiful flowers blooming , forest, saplings, moss, beautiful, epic lighting, ultrasharp, nikon 12mm f15 '
25
+ 'dramtic sky backgraund '
26
+ 'underwater lake, dusk, scarry, blue green bright shining, deep water, nessi, lake ness'
27
+ 'Darkside Anakin Skywalker played by young Hayden Christensen with sith eyes, and a red lightsaber, hyperrealistic, cinematic, professional photo lighting, intricately detailed, cinematic lighting, 8k, ultra detailed, ultra realistic, photorealistic, camera Leica m11 quality with 30mm lens ']:
28
+
29
+ ![val_imgs_grid](./val_imgs_grid.png)
30
+
31
+
32
+ ## Pipeline usage
33
+
34
+ You can use the pipeline like so:
35
+
36
+ ```python
37
+ from diffusers import DiffusionPipeline
38
+ import torch
39
+
40
+ pipeline = DiffusionPipeline.from_pretrained("elephantmipt/test_tuned_sd_15", torch_dtype=torch.float16)
41
+ prompt = "IMAGE_ TYPE Cocktail Photography GENRE Coktail Shooting Lowlight EMOTION I want to drink it SCENE A beautiful and refreshing glass of a drink called lychee spritz , decorated set against a dreamy background lowlight, fitting to the image ACTORS None LOCATION TYPE Studio CAMERA MODEL Nikon D850 CAMERA LENSE 60mm f 2. 8 Macro SPECIAL EFFECTS Dreamy bokeh TIME_ OF_ DAY Studio lighting INTERACTION None "
42
+ image = pipeline(prompt).images[0]
43
+ image.save("my_image.png")
44
+ ```
45
+
46
+ ## Training info
47
+
48
+ These are the key hyperparameters used during training:
49
+
50
+ * Epochs: 14
51
+ * Learning rate: 8e-05
52
+ * Batch size: 20
53
+ * Gradient accumulation steps: 1
54
+ * Image resolution: 512
55
+ * Mixed-precision: bf16
56
+
57
+
58
+ More information on all the CLI arguments and the environment are available on your [`wandb` run page](https://wandb.ai/harmless_ai/alchemist/runs/qspja0u3).
59
+
60
+
61
+ ## Intended uses & limitations
62
+
63
+ #### How to use
64
+
65
+ ```python
66
+ # TODO: add an example code snippet for running this diffusion pipeline
67
+ ```
68
+
69
+ #### Limitations and bias
70
+
71
+ [TODO: provide examples of latent issues and potential remediations]
72
+
73
+ ## Training details
74
+
75
+ [TODO: describe the data used to train the model]
val_imgs_grid.png ADDED

Git LFS Details

  • SHA256: fdae31386767afefa5f0e0b8a762e1a8e501b98ad245d782a1a3ab6e2d14a1f4
  • Pointer size: 132 Bytes
  • Size of remote file: 3.87 MB