Hugging Face's logo

Vijish
/
3kprompts

Text-to-Image
Diffusers
flux
lora
template:sd-lora
ai-toolkit
Model card Files
xet
 Community
Vijish commited on
Commit
dbdd795
·
verified ·
1 Parent(s): 97954e9

Upload 7 files

Browse files
Files changed (7) hide show
  1. 3kpromptsreal.safetensors +3 -0
  2. 3kpromptsreal_000000500.safetensors +3 -0
  3. 3kpromptsreal_000000750.safetensors +3 -0
  4. README (6).md +53 -0
  5. config.yaml +63 -0
  6. index.html +28 -0
  7. optimizer.pt +3 -0
3kpromptsreal.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e85bd70cd949894586d1befcd7ddb8b9a284dd4512ba6ee2620fe54306596e5e
3
+ size 171969352
3kpromptsreal_000000500.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a616eb9196b18433868b60ed53d72d3312ed853af0f1f9775efe4c2fa4f102d
3
+ size 171969352
3kpromptsreal_000000750.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b904285ddd73a42940f95435c672492fed6e51867b96bab79d8f9252adaf1b15
3
+ size 171969352
README (6).md ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - text-to-image
4
+ - flux
5
+ - lora
6
+ - diffusers
7
+ - template:sd-lora
8
+ - ai-toolkit
9
+ widget:
10
+ - text: a photo of a young asian lady
11
+ output:
12
+ url: samples/1725517929716__000001000_0.jpg
13
+ - text: a photo of a male happy ceo
14
+ output:
15
+ url: samples/1725517963797__000001000_1.jpg
16
+ - text: a photo of a black man
17
+ output:
18
+ url: samples/1725517997909__000001000_2.jpg
19
+ base_model: black-forest-labs/FLUX.1-dev
20
+
21
+ license: other
22
+ license_name: flux-1-dev-non-commercial-license
23
+ license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md
24
+ ---
25
+
26
+ # 3kpromptsreal
27
+ Model trained with [AI Toolkit by Ostris](https://github.com/ostris/ai-toolkit)
28
+ <Gallery />
29
+
30
+ ## Trigger words
31
+
32
+ No trigger words defined.
33
+
34
+ ## Download model and use it with ComfyUI, AUTOMATIC1111, SD.Next, Invoke AI, etc.
35
+
36
+ Weights for this model are available in Safetensors format.
37
+
38
+ [Download](/None/tree/main) them in the Files & versions tab.
39
+
40
+ ## Use it with the [🧨 diffusers library](https://github.com/huggingface/diffusers)
41
+
42
+ ```py
43
+ from diffusers import AutoPipelineForText2Image
44
+ import torch
45
+
46
+ pipeline = AutoPipelineForText2Image.from_pretrained('black-forest-labs/FLUX.1-dev', torch_dtype=torch.bfloat16).to('cuda')
47
+ pipeline.load_lora_weights('None', weight_name='3kpromptsreal')
48
+ image = pipeline('a photo of a young asian lady').images[0]
49
+ image.save("my_image.png")
50
+ ```
51
+
52
+ For more details, including weighting, merging and fusing LoRAs, check the [documentation on loading LoRAs in diffusers](https://huggingface.co/docs/diffusers/main/en/using-diffusers/loading_adapters)
53
+
config.yaml ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ job: extension
2
+ config:
3
+ name: 3kpromptsreal
4
+ process:
5
+ - type: sd_trainer
6
+ training_folder: output
7
+ device: cuda:0
8
+ network:
9
+ type: lora
10
+ linear: 16
11
+ linear_alpha: 16
12
+ save:
13
+ dtype: float16
14
+ save_every: 250
15
+ max_step_saves_to_keep: 4
16
+ push_to_hub: true
17
+ datasets:
18
+ - folder_path: datasets/b1767f29-6823-4154-bdf2-11808f24ccd0
19
+ caption_ext: txt
20
+ caption_dropout_rate: 0.05
21
+ shuffle_tokens: false
22
+ cache_latents_to_disk: true
23
+ resolution:
24
+ - 512
25
+ - 768
26
+ - 1024
27
+ train:
28
+ batch_size: 1
29
+ steps: 1000
30
+ gradient_accumulation_steps: 1
31
+ train_unet: true
32
+ train_text_encoder: false
33
+ gradient_checkpointing: true
34
+ noise_scheduler: flowmatch
35
+ optimizer: adamw8bit
36
+ lr: 0.0004
37
+ ema_config:
38
+ use_ema: true
39
+ ema_decay: 0.99
40
+ dtype: bf16
41
+ disable_sampling: false
42
+ model:
43
+ name_or_path: black-forest-labs/FLUX.1-dev
44
+ is_flux: true
45
+ quantize: true
46
+ low_vram: true
47
+ sample:
48
+ sampler: flowmatch
49
+ sample_every: 250
50
+ width: 1024
51
+ height: 1024
52
+ prompts:
53
+ - a photo of a young asian lady
54
+ - a photo of a male happy ceo
55
+ - a photo of a black man
56
+ neg: ''
57
+ seed: 42
58
+ walk_seed: true
59
+ guidance_scale: 4
60
+ sample_steps: 20
61
+ meta:
62
+ name: 3kpromptsreal
63
+ version: '1.0'
index.html ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ <!DOCTYPE html>
2
+ <html lang="en">
3
+ <head>
4
+ <meta charset="UTF-8">
5
+ <title>Image Upload Form</title>
6
+ <script>
7
+ function showLoading() {
8
+ document.getElementById('loading').style.display = 'block';
9
+ document.getElementById('form').style.display = 'none';
10
+ }
11
+ </script>
12
+ </head>
13
+ <body>
14
+ <h1>Upload Images for Processing</h1>
15
+ <form id="form" action="http://13.51.197.183:8000/process-image/" enctype="multipart/form-data" method="post" onsubmit="showLoading()">
16
+ <label for="api_key">API Key:</label>
17
+ <input type="text" name="api_key" required><br><br>
18
+ <label for="source_file">Source Image:</label>
19
+ <input type="file" name="source_file" accept="image/*"><br><br>
20
+ <label for="target_files">Target Images:</label>
21
+ <input type="file" name="target_files" accept="image/*" multiple><br><br>
22
+ <input type="submit" value="Process">
23
+ </form>
24
+ <div id="loading" style="display:none;">
25
+ <p>Loading, please wait...</p>
26
+ </div>
27
+ </body>
28
+ </html>
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38451ac1453947bc7ba3a25971226a2b65f80ca8f114edcf9ce5ac1703763507
3
+ size 173272836