Merge branch 'master' into controlnet-annotator

comfy/sd1_clip.py

@@ -186,7 +186,10 @@ def load_embed(embedding_name, embedding_directory):
         import safetensors.torch
         embed = safetensors.torch.load_file(embed_path, device="cpu")
     else:
-        embed = torch.load(embed_path, weights_only=True, map_location="cpu")
+        if 'weights_only' in torch.load.__code__.co_varnames:
+            embed = torch.load(embed_path, weights_only=True, map_location="cpu")
+        else:
+            embed = torch.load(embed_path, map_location="cpu")
     if 'string_to_param' in embed:
         values = embed['string_to_param'].values()
     else:

models/configs/v1-inpainting-inference.yaml

@@ -0,0 +1,71 @@
+model:
+  base_learning_rate: 7.5e-05
+  target: ldm.models.diffusion.ddpm.LatentInpaintDiffusion
+  params:
+    linear_start: 0.00085
+    linear_end: 0.0120
+    num_timesteps_cond: 1
+    log_every_t: 200
+    timesteps: 1000
+    first_stage_key: "jpg"
+    cond_stage_key: "txt"
+    image_size: 64
+    channels: 4
+    cond_stage_trainable: false   # Note: different from the one we trained before
+    conditioning_key: hybrid   # important
+    monitor: val/loss_simple_ema
+    scale_factor: 0.18215
+    finetune_keys: null
+
+    scheduler_config: # 10000 warmup steps
+      target: ldm.lr_scheduler.LambdaLinearScheduler
+      params:
+        warm_up_steps: [ 2500 ] # NOTE for resuming. use 10000 if starting from scratch
+        cycle_lengths: [ 10000000000000 ] # incredibly large number to prevent corner cases
+        f_start: [ 1.e-6 ]
+        f_max: [ 1. ]
+        f_min: [ 1. ]
+
+    unet_config:
+      target: ldm.modules.diffusionmodules.openaimodel.UNetModel
+      params:
+        image_size: 32 # unused
+        in_channels: 9  # 4 data + 4 downscaled image + 1 mask
+        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
+

nodes.py

@@ -759,8 +759,7 @@ def load_custom_nodes():
     for possible_module in possible_modules:
         module_path = os.path.join(CUSTOM_NODE_PATH, possible_module)
         if os.path.isfile(module_path) and os.path.splitext(module_path)[1] != ".py": continue
-
-        module_name = os.path.basename(module_path)
+        module_name = possible_module
         try:
             if os.path.isfile(module_path):
                 module_spec = importlib.util.spec_from_file_location(module_name, module_path)