Fix GPU parameter in readme, add SD style finetune config

README.md

@@ -113,7 +113,7 @@ To train, prepare a folder that contains images sized at 512x512 and execute the
                                             -t \
                                             --actual_resume ./models/ldm/stable-diffusion-v1/model.ckpt \
                                             -n my_cat \
-                                            -gpus 0, \
+                                            --gpus 0, \
                                             --data_root D:/textual-inversion/my_cat \
                                             --init_word 'cat'
 ~~~~

configs/stable-diffusion/v1-finetune_style.yaml

@@ -0,0 +1,103 @@
+model:
+  base_learning_rate: 5.0e-03
+  target: ldm.models.diffusion.ddpm.LatentDiffusion
+  params:
+    linear_start: 0.00085
+    linear_end: 0.0120
+    num_timesteps_cond: 1
+    log_every_t: 200
+    timesteps: 1000
+    first_stage_key: image
+    cond_stage_key: caption
+    image_size: 64
+    channels: 4
+    cond_stage_trainable: true   # Note: different from the one we trained before
+    conditioning_key: crossattn
+    monitor: val/loss_simple_ema
+    scale_factor: 0.18215
+    use_ema: False
+    embedding_reg_weight: 0.0
+
+    personalization_config:
+      target: ldm.modules.embedding_manager.EmbeddingManager
+      params:
+        placeholder_strings: ["*"]
+        initializer_words: ["painting"]
+        per_image_tokens: false
+        num_vectors_per_token: 1
+
+    unet_config:
+      target: ldm.modules.diffusionmodules.openaimodel.UNetModel
+      params:
+        image_size: 32 # unused
+        in_channels: 4
+        out_channels: 4
+        model_channels: 320
+        attention_resolutions: [ 4, 2, 1 ]
+        num_res_blocks: 2
+        channel_mult: [ 1, 2, 4, 4 ]
+        num_heads: 8
+        use_spatial_transformer: True
+        transformer_depth: 1
+        context_dim: 768
+        use_checkpoint: True
+        legacy: False
+
+    first_stage_config:
+      target: ldm.models.autoencoder.AutoencoderKL
+      params:
+        embed_dim: 4
+        monitor: val/rec_loss
+        ddconfig:
+          double_z: true
+          z_channels: 4
+          resolution: 256
+          in_channels: 3
+          out_ch: 3
+          ch: 128
+          ch_mult:
+          - 1
+          - 2
+          - 4
+          - 4
+          num_res_blocks: 2
+          attn_resolutions: []
+          dropout: 0.0
+        lossconfig:
+          target: torch.nn.Identity
+
+    cond_stage_config:
+      target: ldm.modules.encoders.modules.FrozenCLIPEmbedder
+
+data:
+  target: main.DataModuleFromConfig
+  params:
+    batch_size: 2
+    num_workers: 16
+    wrap: false
+    train:
+      target: ldm.data.personalized_style.PersonalizedBase
+      params:
+        size: 512
+        set: train
+        per_image_tokens: false
+        repeats: 100
+    validation:
+      target: ldm.data.personalized_style.PersonalizedBase
+      params:
+        size: 512
+        set: val
+        per_image_tokens: false
+        repeats: 10
+
+lightning:
+  callbacks:
+    image_logger:
+      target: main.ImageLogger
+      params:
+        batch_frequency: 500
+        max_images: 8
+        increase_log_steps: False
+
+  trainer:
+    benchmark: True