correct diffusers

feature_extractor/preprocessor_config.json

@@ -14,7 +14,7 @@
     0.4578275,
     0.40821073
   ],
-  "image_processor_type": "CLIPFeatureExtractor",
+  "image_processor_type": "CLIPImageProcessor",
   "image_std": [
     0.26862954,
     0.26130258,

model_index.json

@@ -3,7 +3,7 @@
   "_diffusers_version": "0.12.0.dev0",
   "feature_extractor": [
     "transformers",
-    "CLIPFeatureExtractor"
+    "CLIPImageProcessor"
   ],
   "requires_safety_checker": true,
   "safety_checker": [

safety_checker/config.json

@@ -80,7 +80,7 @@
     "top_p": 1.0,
     "torch_dtype": null,
     "torchscript": false,
-    "transformers_version": "4.26.0.dev0",
+    "transformers_version": "4.25.1",
     "typical_p": 1.0,
     "use_bfloat16": false,
     "vocab_size": 49408
@@ -167,7 +167,7 @@
     "top_p": 1.0,
     "torch_dtype": null,
     "torchscript": false,
-    "transformers_version": "4.26.0.dev0",
+    "transformers_version": "4.25.1",
     "typical_p": 1.0,
     "use_bfloat16": false
   },

text_encoder/config.json

@@ -20,6 +20,6 @@
   "pad_token_id": 1,
   "projection_dim": 768,
   "torch_dtype": "float32",
-  "transformers_version": "4.26.0.dev0",
+  "transformers_version": "4.25.1",
   "vocab_size": 49408
 }

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