Add Microsoft Emoji LoRA, trained with AI-toolkit

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+optimizer.pt filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,3 +1,74 @@
----
-license: mit
----
+---
+tags:
+- text-to-image
+- flux
+- lora
+- diffusers
+- template:sd-lora
+- ai-toolkit
+widget:
+-   text: '[trigger] woman with red hair'
+    output:
+        url: samples/1726080981710__000002000_0.jpg
+-   text: '[trigger] a woman holding a coffee cup, in a beanie'
+    output:
+        url: samples/1726080985911__000002000_1.jpg
+-   text: '[trigger] a horse is a DJ at a night club'
+    output:
+        url: samples/1726080990112__000002000_2.jpg
+-   text: '[trigger] a man showing off his cool new t shirt at the beach'
+    output:
+        url: samples/1726080994314__000002000_3.jpg
+-   text: '[trigger] a bear building a log cabin'
+    output:
+        url: samples/1726080998517__000002000_4.jpg
+-   text: '[trigger] woman playing the guitar, on stage, singing a song'
+    output:
+        url: samples/1726081002722__000002000_5.jpg
+-   text: '[trigger] hipster man with a beard'
+    output:
+        url: samples/1726081006926__000002000_6.jpg
+-   text: '[trigger] a man'
+    output:
+        url: samples/1726081011130__000002000_7.jpg
+-   text: '[trigger] a man holding a sign that says, ''this is a sign'''
+    output:
+        url: samples/1726081015337__000002000_8.jpg
+-   text: '[trigger] a bulldog with a shotgun, in a leather jacket with a motorcycle'
+    output:
+        url: samples/1726081019544__000002000_9.jpg
+base_model: black-forest-labs/FLUX.1-schnell
+instance_prompt: emojy
+license: apache-2.0
+
+
+---
+
+# flux_microsoft_emoji_lora_v1
+Model trained with [AI Toolkit by Ostris](https://github.com/ostris/ai-toolkit)
+<Gallery />
+
+## Trigger words
+
+You should use `emojy` 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](/Zedge/Flux-Schnell-Emoji-Weights/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-schnell', torch_dtype=torch.bfloat16).to('cuda')
+pipeline.load_lora_weights('Zedge/Flux-Schnell-Emoji-Weights', weight_name='flux_microsoft_emoji_lora_v1')
+image = pipeline('[trigger] woman with red hair').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 +1,73 @@
+job: extension
+config:
+  name: flux_microsoft_emoji_lora_v1
+  process:
+  - type: sd_trainer
+    training_folder: output
+    performance_log_every: 1000
+    device: cuda:0
+    trigger_word: emojy
+    network:
+      type: lora
+      linear: 16
+      linear_alpha: 16
+    save:
+      dtype: float16
+      save_every: 250
+      max_step_saves_to_keep: 4
+      push_to_hub: true
+      hf_repo_id: Zedge/Flux-Schnell-Emoji-Weights
+      hf_private: true
+    datasets:
+    - folder_path: ../../datasets/Microsoft-3D-Fluent
+      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: 2000
+      gradient_accumulation_steps: 1
+      train_unet: true
+      train_text_encoder: false
+      gradient_checkpointing: false
+      noise_scheduler: flowmatch
+      optimizer: adamw8bit
+      lr: 0.0001
+      ema_config:
+        use_ema: true
+        ema_decay: 0.99
+      dtype: bf16
+    model:
+      name_or_path: black-forest-labs/FLUX.1-schnell
+      assistant_lora_path: ostris/FLUX.1-schnell-training-adapter
+      is_flux: true
+      quantize: true
+    sample:
+      sampler: flowmatch
+      sample_every: 250
+      width: 1024
+      height: 1024
+      prompts:
+      - '[trigger] woman with red hair'
+      - '[trigger] a woman holding a coffee cup, in a beanie'
+      - '[trigger] a horse is a DJ at a night club'
+      - '[trigger] a man showing off his cool new t shirt at the beach'
+      - '[trigger] a bear building a log cabin'
+      - '[trigger] woman playing the guitar, on stage, singing a song'
+      - '[trigger] hipster man with a beard'
+      - '[trigger] a man'
+      - '[trigger] a man holding a sign that says, ''this is a sign'''
+      - '[trigger] a bulldog with a shotgun, in a leather jacket with a motorcycle'
+      neg: ''
+      seed: 42
+      walk_seed: true
+      guidance_scale: 1
+      sample_steps: 4
+meta:
+  name: flux_microsoft_emoji_lora_v1
+  version: '1.0'

flux_microsoft_emoji_lora_v1.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9acbc3b5b4be5af92af84bd5185f55bf9b2e15f3c7b5f37128adcc9e3bb9403b
+size 171969432

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d31939ed302c71097bb374a94ecb6750fdf688c3e49755b7b649f05f988bf012
+size 173272836