Upload 8 files

README.md

@@ -1,3 +1,67 @@
----
-license: apache-2.0
----
+---
+tags:
+- text-to-image
+- flux
+- lora
+- diffusers
+- template:sd-lora
+- ai-toolkit
+widget:
+-   text: a green aluminum can of 'NOCCO BCAA+ Apple' energy drink on a rock in a
+        foggy forest
+    output:
+        url: samples/1727181393674__000002500_0.jpg
+-   text: a green aluminum can of 'NOCCO BCAA+ Apple' energy drink can in a hand of
+        a person
+    output:
+        url: samples/1727181430166__000002500_1.jpg
+-   text: a green aluminum can of 'NOCCO BCAA+ Apple' can on a sandy beach at sunset,
+        surrounded by seashells and gentle ocean waves
+    output:
+        url: samples/1727181466660__000002500_2.jpg
+-   text: Taylor swift holding a green aluminum can NOCCO BCAA+ Apple energy drink
+        can
+    output:
+        url: samples/1727181503160__000002500_3.jpg
+-   text: '''NOCCO BCAA+ Apple'' can, green aluminum can dropping into crystal-clear
+        water, apple taste, commercial-style, the water should create dramatic splashes
+        and bubbles,  surrounding the can in all directions,  capturing the moment
+        of impact, high-resolution,  colorful,  (from above:1.2),  photo by Gregory
+        Colbert'
+    output:
+        url: samples/1727181539672__000002500_4.jpg
+base_model: black-forest-labs/FLUX.1-dev
+instance_prompt: XN0APBCX
+license: other
+license_name: flux-1-dev-non-commercial-license
+license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md
+---
+
+# nocco_apple_v6
+Model trained with [AI Toolkit by Ostris](https://github.com/ostris/ai-toolkit)
+<Gallery />
+
+## Trigger words
+
+You should use `XN0APBCX` to trigger the image generation.
+
+## Download model and use it with ComfyUI, AUTOMATIC1111, SD.Next, Invoke AI, etc.
+
+Weights for this model are available in Safetensors format.
+
+[Download](/None/tree/main) them in the Files & versions tab.
+
+## Use it with the [🧨 diffusers library](https://github.com/huggingface/diffusers)
+
+```py
+from diffusers import AutoPipelineForText2Image
+import torch
+
+pipeline = AutoPipelineForText2Image.from_pretrained('black-forest-labs/FLUX.1-dev', torch_dtype=torch.bfloat16).to('cuda')
+pipeline.load_lora_weights('None', weight_name='nocco_apple_v6.safetensors')
+image = pipeline('a green aluminum can of 'NOCCO BCAA+ Apple' energy drink on a rock in a foggy forest').images[0]
+image.save("my_image.png")
+```
+
+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

@@ -0,0 +1,72 @@
+job: extension
+config:
+  name: nocco_apple_v6
+  process:
+  - type: sd_trainer
+    training_folder: ./output/flux_lora_nocco
+    device: cuda:0
+    trigger_word: XN0APBCX
+    network:
+      type: lora
+      linear: 16
+      linear_alpha: 16
+    save:
+      dtype: float16
+      save_every: 250
+      max_step_saves_to_keep: 4
+      push_to_hub: true
+    datasets:
+    - folder_path: ./nocco_me
+      caption_ext: txt
+      caption_dropout_rate: 0.05
+      shuffle_tokens: false
+      cache_latents_to_disk: true
+      resolution:
+      - 512
+      - 768
+      - 1024
+    train:
+      batch_size: 1
+      steps: 2500
+      gradient_accumulation_steps: 1
+      train_unet: true
+      train_text_encoder: false
+      gradient_checkpointing: true
+      noise_scheduler: flowmatch
+      optimizer: adamw8bit
+      lr: 0.0001
+      skip_first_sample: true
+      ema_config:
+        use_ema: true
+        ema_decay: 0.99
+      dtype: bf16
+    model:
+      name_or_path: black-forest-labs/FLUX.1-dev
+      is_flux: true
+      quantize: true
+    sample:
+      sampler: flowmatch
+      sample_every: 250
+      width: 1024
+      height: 1024
+      prompts:
+      - a green aluminum can of 'NOCCO BCAA+ Apple' energy drink on a rock in a foggy
+        forest
+      - a green aluminum can of 'NOCCO BCAA+ Apple' energy drink can in a hand of
+        a person
+      - a green aluminum can of 'NOCCO BCAA+ Apple' can on a sandy beach at sunset,
+        surrounded by seashells and gentle ocean waves
+      - Taylor swift holding a green aluminum can NOCCO BCAA+ Apple energy drink can
+      - '''NOCCO BCAA+ Apple'' can, green aluminum can dropping into crystal-clear
+        water, apple taste, commercial-style, the water should create dramatic splashes
+        and bubbles,  surrounding the can in all directions,  capturing the moment
+        of impact, high-resolution,  colorful,  (from above:1.2),  photo by Gregory
+        Colbert'
+      neg: ''
+      seed: 42
+      walk_seed: true
+      guidance_scale: 4
+      sample_steps: 20
+meta:
+  name: nocco_apple_v6
+  version: '1.0'

nocco_apple_v6.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:264b742860b0a1efdca6c0787a7d046d388383b332b964f9c74ceae06d32ee94
+size 171969408

nocco_apple_v6_000001500.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79a3fc8cdb0a74360c49240c3edca286d790e366acb91b67ed1cd16581ff93f2
+size 171969408

nocco_apple_v6_000001750.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76fcaef5788f408200a9dcb3fd00104ccbb5353def3e6d54dc61aebe4b34f459
+size 171969408

nocco_apple_v6_000002000.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71bbfbb7a5b0f92709a0436ebd86cac4040210b3371dff93aeb482a853f61d77
+size 171969408

nocco_apple_v6_000002250.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e376480b017be65dcabe07a3f83e907a11944442ab9e6b967e5715f6a7e0c627
+size 171969408

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f7742aa24596fbb50df7b5c0da69641074fbe57b3d387bddc973c3728343424
+size 175676612