arthurshow-flux-lora

README.md

@@ -0,0 +1,37 @@
+---
+tags:
+- text-to-image
+- flux
+- lora
+- diffusers
+- template:sd-lora
+widget:
+-   text: ArthurShow woman with red hair, playing chess at the park, bomb going off in the background
+    output:
+        url: 1725069952421__000004500_0.jpg
+-   text: a ArthurShow man holding a coffee cup, in a beanie, sitting at a cafe
+    output:
+        url: 1725069993317__000004500_1.jpg
+-   text: Rabbit playing the guitar, on stage, singing a song, laser lights, punk rocker ArthurShow
+    output:
+        url: 1725070034190__000004500_2.jpg
+base_model: black-forest-labs/FLUX.1-dev
+instance_prompt: ArthurShow
+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
+---
+
+# arthurshow_flux_lora
+Model trained with [AI Toolkit by Ostris](https://github.com/ostris/ai-toolkit)
+<Gallery />
+
+## Trigger words
+
+You should use `ArthurShow` to trigger the image generation.
+
+## Download model
+
+Weights for this model are available in Safetensors format.
+
+[Download](https://huggingface.co/Norod78/arthurshow-flux-lora/tree/main) them in the Files & versions tab.

arthurshow_flux_lora_000004500.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6972f61096dbe7b8b4a749de2337f222a1d1c749288c4700b50894e49687c0cc
+size 171969440

train_lora_flux_24gb.yaml

@@ -0,0 +1,90 @@
+---
+job: extension
+config:
+  # this name will be the folder and filename name
+  name: "arthurshow_flux_lora"
+  process:
+    - type: 'sd_trainer'
+      # root folder to save training sessions/samples/weights
+      training_folder: "output"
+      # uncomment to see performance stats in the terminal every N steps
+#      performance_log_every: 1000
+      device: cuda:0
+      # if a trigger word is specified, it will be added to captions of training data if it does not already exist
+      # alternatively, in your captions you can add [trigger] and it will be replaced with the trigger word
+      trigger_word: "ArthurShow"
+      network:
+        type: "lora"
+        linear: 16
+        linear_alpha: 16
+      save:
+        dtype: float16 # precision to save
+        save_every: 250 # save every this many steps
+        max_step_saves_to_keep: 2 # how many intermittent saves to keep
+        push_to_hub: false #change this to True to push your trained model to Hugging Face.
+        # You can either set up a HF_TOKEN env variable or you'll be prompted to log-in         
+        hf_repo_id: Norod78/arthurshow-flux-lora
+        hf_private: true #whether the repo is private or public
+      datasets:
+        # datasets are a folder of images. captions need to be txt files with the same name as the image
+        # for instance image2.jpg and image2.txt. Only jpg, jpeg, and png are supported currently
+        # images will automatically be resized and bucketed into the resolution specified
+        # on windows, escape back slashes with another backslash so
+        # "C:\\path\\to\\images\\folder"
+        - folder_path: "/mnt/c/Users/doron/Projects/datasets/ArthurShow_db/img"
+          caption_ext: "txt"
+          caption_dropout_rate: 0.05  # will drop out the caption 5% of time
+          shuffle_tokens: false  # shuffle caption order, split by commas
+          cache_latents_to_disk: true  # leave this true unless you know what you're doing
+          resolution: [ 512, 768, 1024]  # flux enjoys multiple resolutions
+      train:
+        batch_size: 1
+        steps: 5000  # total number of steps to train 500 - 4000 is a good range
+        gradient_accumulation_steps: 1
+        train_unet: true
+        train_text_encoder: false  # probably won't work with flux
+        gradient_checkpointing: true  # need the on unless you have a ton of vram
+        noise_scheduler: "flowmatch" # for training only
+        optimizer: "adamw8bit"
+        lr: 1e-4
+        # uncomment this to skip the pre training sample
+#        skip_first_sample: true
+        # uncomment to completely disable sampling
+#        disable_sampling: true
+        # uncomment to use new vell curved weighting. Experimental but may produce better results
+        linear_timesteps: true
+
+        # ema will smooth out learning, but could slow it down. Recommended to leave on.
+        ema_config:
+          use_ema: true
+          ema_decay: 0.99
+
+        # will probably need this if gpu supports it for flux, other dtypes may not work correctly
+        dtype: bf16
+      model:
+        # huggingface model name or path
+        name_or_path: "black-forest-labs/FLUX.1-dev"
+        is_flux: true
+        quantize: true  # run 8bit mixed precision
+#        low_vram: true  # uncomment this if the GPU is connected to your monitors. It will use less vram to quantize, but is slower.
+      sample:
+        sampler: "flowmatch" # must match train.noise_scheduler
+        sample_every: 250 # sample every this many steps
+        width: 1024
+        height: 1024
+        prompts:
+          # you can add [trigger] to the prompts here and it will be replaced with the trigger word
+#          - "[trigger] holding a sign that says 'I LOVE PROMPTS!'"\
+          - "[trigger] woman with red hair, playing chess at the park, bomb going off in the background"
+          - "a [trigger] man holding a coffee cup, in a beanie, sitting at a cafe"
+          - "Rabbit playing the guitar, on stage, singing a song, laser lights, punk rocker ArthurShow"
+          - "hipster [trigger] with a beard, building a chair, in a [trigger] wood shop"
+        neg: ""  # not used on flux
+        seed: 42
+        walk_seed: true
+        guidance_scale: 4
+        sample_steps: 20
+# you can add any additional meta info here. [name] is replaced with config name at top
+meta:
+  name: "[Arthur Show LoRA - Flux.1 DEV]"
+  version: '1.0'