brushnet path rewrited

brushnet_nodes.py

@@ -19,7 +19,7 @@ class BrushNetLoader:
     def INPUT_TYPES(s):
         return {"required":
                     {    
-                        "brushnet": ([x[0][17:] for x in os.walk("./models/inpaint/")], ),
+                        "brushnet": (inpaint_folders(), ),
                      },
                 }
 
@@ -30,12 +30,27 @@ class BrushNetLoader:
     FUNCTION = "brushnet_loading"
 
     def brushnet_loading(self, brushnet):
-        brushnet_path = "./models/inpaint/"+brushnet
+        brushnet_path = os.path.join(folder_paths.models_dir, "inpaint", brushnet)
         print("Brushnet... ", end="")
         brush_net = BrushNetModel.from_pretrained(brushnet_path, torch_dtype=torch.float16)
         print("loaded")
         return (brush_net,)
 
+    
+def inpaint_folders():
+    inpaint_path = os.path.join(folder_paths.models_dir, 'inpaint')
+    abs_list = [x[0] for x in os.walk(inpaint_path)]
+
+    folders = []
+    for x in abs_list[1:]:
+        remain = x
+        y = ''
+        while remain != inpaint_path:
+            remain, folder = os.path.split(remain)
+            y = os.path.join(folder, y)
+        folders.append(y)        
+    return folders
+
 
 class BrushNetPipeline:
 
@@ -61,7 +76,8 @@ class BrushNetPipeline:
             model_path, 
             brushnet=brushnet, 
             torch_dtype=torch.float16, 
-            low_cpu_mem_usage=False
+            low_cpu_mem_usage=False,
+            original_config_file=os.path.join(os.path.dirname(__file__), "v1-inference.yaml"),
         )
         pipe.to("cuda")
         pipe.scheduler = UniPCMultistepScheduler.from_config(pipe.scheduler.config)

v1-inference.yaml

@@ -0,0 +1,70 @@
+model:
+  base_learning_rate: 1.0e-04
+  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: "jpg"
+    cond_stage_key: "txt"
+    image_size: 64
+    channels: 4
+    cond_stage_trainable: false   # Note: different from the one we trained before
+    conditioning_key: crossattn
+    monitor: val/loss_simple_ema
+    scale_factor: 0.18215
+    use_ema: False
+
+    scheduler_config: # 10000 warmup steps
+      target: ldm.lr_scheduler.LambdaLinearScheduler
+      params:
+        warm_up_steps: [ 10000 ]
+        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: 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