Update README.md

README.md

@@ -7,80 +7,80 @@ tags:
 - template:sd-lora
 - ai-toolkit
 widget:
--   text: HST style autochrome photo of a drugged God Christ-insect in wooden pillbox
+-   text: /@step 4000 weights:/ HST style autochrome photo of a drugged God Christ-insect in wooden pillbox
         being pinned needle-poked by a giant Marina Tsvetaeva in a long
         red gown, arcane symbolism, colorful HD realistic film in Yury Annenkov &
         David Lynch styles, detailed face worrying, full-height red-robed woman roams
         European city circa 1930
     output:
         url: samples/1729711624663__000004000_4.jpg
--   text: HST style autochrome photo of a drugged God Christ-insect in wooden pillbox
+-   text: /@step 1600 weights:/HST style autochrome photo of a drugged God Christ-insect in wooden pillbox
         being pinned needle-poked by a giant Marina Tsvetaeva in a long
         red gown, arcane symbolism, colorful HD realistic film in Yury Annenkov &
         David Lynch styles, detailed face worrying, full-height red-robed woman roams
         European city circa 1930
     output:
         url: samples/1729700659095__000001600_4.jpg 
--   text: HST style autochrome photo of a drugged God Christ-insect in wooden pillbox
+-   text: /@step 1800 weights:/HST style autochrome photo of a drugged God Christ-insect in wooden pillbox
         being pinned needle-poked by a giant Marina Tsvetaeva in a long
         red gown, arcane symbolism, colorful HD realistic film in Yury Annenkov &
         David Lynch styles, detailed face worrying, full-height red-robed woman roams
         European city circa 1930
     output:
         url: samples/1729701571749__000001800_4.jpg 
--   text: HST style autochrome photo of a drugged God Christ-insect in wooden pillbox
+-   text: /@step 800 weights:/HHST style autochrome photo of a drugged God Christ-insect in wooden pillbox
         being pinned needle-poked by a giant Marina Tsvetaeva in a long
         red gown, arcane symbolism, colorful HD realistic film in Yury Annenkov &
         David Lynch styles, detailed face worrying, full-height red-robed woman roams
         European city circa 1930
     output:
         url: samples/1729696985671__000000800_4.jpg
-- text: 'HST style communist poster with text "JOIN RCA!", over autochrome color photo of Vladimir Lenin at a Dada cabaret in 1916 Zurich, 
+- text: '/@step 1800 weights:/HST style communist poster with text "JOIN RCA!", over autochrome color photo of Vladimir Lenin at a Dada cabaret in 1916 Zurich, 
 dancing with red feathered drunken dinosaur, an early conceptual artist. Lenin is full of contageous awe, his blemished skin flushing 
 with anxious excitement, his famous bald spot sweatily glistening under warm lights. In the back, Krupskaya and Inessa Armand laugh. '
   output:
     url: samples/1729701488064__000001800_0.jpg
-- text: 'HST style communist poster with text "JOIN RCA!", over autochrome color photo of Vladimir Lenin at a Dada cabaret in 1916 Zurich, 
+- text: '/@step 4000 weights:/HHST style communist poster with text "JOIN RCA!", over autochrome color photo of Vladimir Lenin at a Dada cabaret in 1916 Zurich, 
 dancing with red feathered drunken dinosaur, an early conceptual artist. Lenin is full of contageous awe, his blemished skin flushing 
 with anxious excitement, his famous bald spot sweatily glistening under warm lights. In the back, Krupskaya and Inessa Armand laugh. '
   output:
     url: samples/1729711540947__000004000_0.jpg
-- text: 'HST style communist poster with text "JOIN RCA!", over autochrome color photo of Vladimir Lenin at a Dada cabaret in 1916 Zurich, 
+- text: '/@step 1600 weights:/ HST style communist poster with text "JOIN RCA!", over autochrome color photo of Vladimir Lenin at a Dada cabaret in 1916 Zurich, 
 dancing with red feathered drunken dinosaur, an early conceptual artist. Lenin is full of contageous awe, his blemished skin flushing 
 with anxious excitement, his famous bald spot sweatily glistening under warm lights. In the back, Krupskaya and Inessa Armand laugh. '
   output:
     url: samples/1729700575417__000001600_0.jpg
--   text: 'HST autochrome style analog dslr award-winning 8k art photo showing a nurse
+-   text: '/@step 1600 weights:/ HST autochrome style analog dslr award-winning 8k art photo showing a nurse
         battling a giant cell phone, above text caption of \ONCE WE WERE ALL HARRY
         GARDNER!\, in a highly realistic modern American medical hospital '
     output:
         url: samples/1729700596338__000001600_1.jpg
--   text: 'HST autochrome style analog dslr award-winning 8k art photo showing a nurse
+-   text: '/@step 1000 weights:/ HST autochrome style analog dslr award-winning 8k art photo showing a nurse
         battling a giant cell phone, above text caption of \ONCE WE WERE ALL HARRY
         GARDNER!\, in a highly realistic modern American medical hospital '
     output:
         url: samples/1729697845170__000001000_1.jpg
--   text: HST style autochrome photograph of a dark CIA agent Koala leaping at the
+-   text: /@step 3600 weights:/ HST style autochrome photograph of a dark CIA agent Koala leaping at the
         throat of goth freedom-fighter Julian Assange, tragic atmosphere, award-winning
         art photo
     output:
         url: samples/1729709764758__000003600_2.jpg
--   text: HST style autochrome photograph of a dark CIA agent Koala leaping at the
+-   text: /@step 1200 weights:/ HST style autochrome photograph of a dark CIA agent Koala leaping at the
         throat of goth freedom-fighter Julian Assange, tragic atmosphere, award-winning
         art photo
     output:
         url: samples/1729698783304__000001200_2.jpg
--   text: HST style autochrome photograph of a dark CIA agent Koala leaping at the
+-   text: /@step 1000 weights:/ HST style autochrome photograph of a dark CIA agent Koala leaping at the
         throat of goth freedom-fighter Julian Assange, tragic atmosphere, award-winning
         art photo
     output:
         url: samples/1729697866093__000001000_2.jpg
--   text: HST style autochrome photo of realistic green-eyed black cat, with prominent
+-   text: /@step 4000 weights:/ HST style autochrome photo of realistic green-eyed black cat, with prominent
         regions of white fur, playing a piano and singing, amateur 2004 photograph
         shot on a cell phone in a Los Angeles apartment kitchen
     output:
         url: samples/1729711603742__000004000_3.jpg
--   text: HST style autochrome photo of realistic green-eyed black cat, with prominent
+-   text: /@step 1800 weights:/ HST style autochrome photo of realistic green-eyed black cat, with prominent
         regions of white fur, playing a piano and singing, amateur 2004 photograph
         shot on a cell phone in a Los Angeles apartment kitchen
     output:
@@ -100,6 +100,63 @@ Model trained with [AI Toolkit by Ostris](https://github.com/ostris/ai-toolkit)
 
 'HST style autochrome photo'
 
+## Config Parameters 
+Using the Google Colab Notebook Version of #ai-toolkit#. 
+I've used A100 via Colab Pro.
+But training SD3.5 may potentially work with Free Colab or lower Vram in general, especially if one used lower rank (try 4 or 8), dataset size (in terms of caching/bucketing/pre-loading impacts), 1 batch size, Adamw8bit optimizer, 512 resolution, maybe adding the "lowvram, true" argument, and plausibly specifying alternate quantization variants! 
+Generally, VRAM expenditures tend to be lower than for Flux during training. So, try it! I certainly will.
+To use on Colab, modify a Flux template Notebook from [here](https://github.com/ostris/ai-toolkit/tree/main/notebooks) with parameters from Ostris' example config for SD3.5 [here](https://github.com/ostris/ai-toolkit/blob/main/config/examples/train_lora_sd35_large_24gb.yaml)!
+```
+job: extension
+config:
+  name: HSTsd3ii
+  process:
+  - type: sd_trainer
+    training_folder: /content/drive/MyDrive/HSTsd3ii
+    performance_log_every: 600
+    device: cuda:0
+    network:
+      type: lora
+      linear: 16
+      linear_alpha: 32
+    save:
+      dtype: float16
+      save_every: 250
+      push_to_hub: true
+      hf_repo_id: AlekseyCalvin/HSTsd3iii
+      hf_private: true
+      max_step_saves_to_keep: 16
+    datasets:
+    - folder_path: /content/dataset
+      caption_ext: txt
+      caption_dropout_rate: 0.0
+      shuffle_tokens: false
+      cache_latents_to_disk: true
+      resolution:
+      - 1024
+    train:
+      batch_size: 4
+      steps: 4000
+      gradient_accumulation_steps: 1
+      train_unet: true
+      train_text_encoder: false
+      gradient_checkpointing: true
+      noise_scheduler: flowmatch
+      timestep_type: linear
+      optimizer: ademamix8bit
+      lr: 0.0002
+      skip_first_sample: true
+      ema_config:
+        use_ema: true
+        ema_decay: 0.8
+      dtype: bf16
+    model:
+      name_or_path: stabilityai/stable-diffusion-3.5-large
+      is_v3: true
+      quantize: true
+```
+Plus validation settings: Prompts like the above, at 1024, guidance scale 4, 25 steps, seed 42, no negatives.
+
 ## Download model and use it with ComfyUI, AUTOMATIC1111, SD.Next, Invoke AI, etc.
 
 Weights for this model are available in Safetensors format.