ell-hol commited on
Commit
1f06011
·
verified ·
1 Parent(s): 4c0da19

Upload folder using huggingface_hub

Browse files
Files changed (3) hide show
  1. README.md +46 -0
  2. config.yaml +96 -0
  3. lora.safetensors +3 -0
README.md ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: other
3
+ license_name: flux-1-dev-non-commercial-license
4
+ license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md
5
+ language:
6
+ - en
7
+ tags:
8
+ - flux
9
+ - diffusers
10
+ - lora
11
+ - replicate
12
+ base_model: "black-forest-labs/FLUX.1-dev"
13
+ pipeline_tag: text-to-image
14
+ # widget:
15
+ # - text: >-
16
+ # prompt
17
+ # output:
18
+ # url: https://...
19
+ instance_prompt: Fnac
20
+ ---
21
+
22
+ # Fx Dv Lr Fnc Frt
23
+
24
+ <Gallery />
25
+
26
+ Trained on Replicate using:
27
+
28
+ https://replicate.com/ostris/flux-dev-lora-trainer/train
29
+
30
+
31
+ ## Trigger words
32
+ You should use `Fnac` to trigger the image generation.
33
+
34
+
35
+ ## Use it with the [🧨 diffusers library](https://github.com/huggingface/diffusers)
36
+
37
+ ```py
38
+ from diffusers import AutoPipelineForText2Image
39
+ import torch
40
+
41
+ pipeline = AutoPipelineForText2Image.from_pretrained('black-forest-labs/FLUX.1-dev', torch_dtype=torch.float16).to('cuda')
42
+ pipeline.load_lora_weights('ell-hol/fx-dv-lr-fnc-frt', weight_name='lora.safetensors')
43
+ image = pipeline('your prompt').images[0]
44
+ ```
45
+
46
+ 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)
config.yaml ADDED
@@ -0,0 +1,96 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ job: custom_job
2
+ config:
3
+ name: flux_train_replicate
4
+ process:
5
+ - type: custom_sd_trainer
6
+ training_folder: output
7
+ device: cuda:0
8
+ trigger_word: Fnac
9
+ network:
10
+ type: lora
11
+ linear: 16
12
+ linear_alpha: 16
13
+ save:
14
+ dtype: float16
15
+ save_every: 100
16
+ max_step_saves_to_keep: 1
17
+ datasets:
18
+ - folder_path: input_images
19
+ caption_ext: txt
20
+ caption_dropout_rate: 0.05
21
+ shuffle_tokens: false
22
+ cache_latents_to_disk: false
23
+ cache_latents: true
24
+ resolution:
25
+ - 512
26
+ - 768
27
+ - 1024
28
+ - 1440
29
+ train:
30
+ batch_size: 1
31
+ steps: 1000
32
+ gradient_accumulation_steps: 1
33
+ train_unet: true
34
+ train_text_encoder: false
35
+ content_or_style: balanced
36
+ gradient_checkpointing: true
37
+ noise_scheduler: flowmatch
38
+ optimizer: adamw8bit
39
+ lr: 0.0004
40
+ ema_config:
41
+ use_ema: true
42
+ ema_decay: 0.99
43
+ dtype: bf16
44
+ model:
45
+ name_or_path: FLUX.1-dev
46
+ is_flux: true
47
+ quantize: true
48
+ sample:
49
+ sampler: flowmatch
50
+ sample_every: 100
51
+ width: 1024
52
+ height: 1024
53
+ prompts:
54
+ - A high-resolution daytime photograph of a Fnac store located on a bustling
55
+ urban street. The storefront features the iconic yellow Fnac logo prominently
56
+ displayed on a modern glass facade. Shoppers are casually walking by, and
57
+ the reflections of nearby buildings are visible on the large windows. A few
58
+ promotional posters are visible inside, advertising the latest tech and books.
59
+ The atmosphere is lively, with a slightly overcast sky providing soft, even
60
+ lighting.
61
+ - A nighttime photo of a Fnac store in a European city. The bright, illuminated
62
+ yellow Fnac sign contrasts against the dark sky. The store windows glow warmly,
63
+ showcasing displays of books, electronics, and entertainment products. The
64
+ street outside is wet as if it has recently rained, reflecting the store's
65
+ lights. A couple of pedestrians holding shopping bags are visible walking
66
+ past, giving a cozy and inviting atmosphere.
67
+ - A wide-angle photograph of a sleek Fnac storefront inside a bustling modern
68
+ shopping mall. The store has a clean, contemporary design with bright, inviting
69
+ lighting. The iconic yellow Fnac logo is displayed above the entrance. Shoppers
70
+ are entering and exiting the store, some holding branded bags. Visible through
71
+ the glass are shelves of books, rows of electronic gadgets, and a display
72
+ for the latest tech releases. The polished floors of the mall reflect the
73
+ store's lights.
74
+ - A vintage-style photograph of a Fnac store nestled in a historic European
75
+ city street. The building has an old-world charm with ornate architectural
76
+ details, but the bold yellow Fnac sign adds a modern touch. The store windows
77
+ are decorated with colorful displays of books, music, and electronics. Outside,
78
+ cobblestone streets and a few bicycles leaned against the building add to
79
+ the scene's character. The lighting is warm and golden, suggesting a late
80
+ afternoon ambiance.
81
+ - ''
82
+ - ''
83
+ - ''
84
+ - ''
85
+ - ''
86
+ - ''
87
+ - ''
88
+ - ''
89
+ neg: ''
90
+ seed: 42
91
+ walk_seed: true
92
+ guidance_scale: 3.5
93
+ sample_steps: 28
94
+ meta:
95
+ name: flux_train_replicate
96
+ version: '1.0'
lora.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8661db0c03308cdfd09bd8e6747a3905c6b6bbf0392d522f829b84fb6f03798
3
+ size 171969416