wupload

Jidao-wd15/Jidao-wd15-000001.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cb498b634621be45e57482440e151f302b42e9812930465a46503a6977d8254
+size 13927544

Jidao-wd15/Jidao-wd15-000002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f9164073c538b6ff969661105b09dd63d43d53d4cac116f6ccbd350e2a142ab
+size 13927544

Jidao-wd15/Jidao-wd15-000003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c5fde39d99c9d04a3bcbd29974f895ac12c2d433e1a35fe1b53a80b234f122b
+size 13927544

Jidao-wd15/Jidao-wd15-000004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bba33aa345b0c0330fff0a723997bb4d7dd9535a56b45a47193c35c6b9551c4b
+size 13927544

Jidao-wd15/Jidao-wd15-000005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eff05cc8c3cafad7d70e9601f0fbcf70ae29a1982c557f90bbb8c0515fd08505
+size 13927541

Jidao-wd15/Jidao-wd15-000006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9e787bd30d761f9c723ebd0c0dfa840bc85d3d5e76499a87d71ad5eacb7d973
+size 13927544

Jidao-wd15/Jidao-wd15-000007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19a9eab8444495ec2b7269d5c304ae354c4ea4e314144cb46acd8f969afb86aa
+size 13927544

Jidao-wd15/Jidao-wd15-000008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f241754a21673c096499709cad420f06d384320658b8b3782a853c8b7927615
+size 13927544

Jidao-wd15/Jidao-wd15-000009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fa52155394fb256bf4710612f5a85eaaafd8b83286d1c89970d05e2266055c2
+size 13927544

Jidao-wd15/Jidao-wd15.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2b222fd2fcfb58857e40707283bc7c2bfb62f9a591fd92fc59ad93f99dd7972
+size 13927545

Jidao-wd15/Jidao-wd15.yaml

@@ -0,0 +1,68 @@
+model:
+  base_learning_rate: 1.0e-4
+  target: ldm.models.diffusion.ddpm.LatentDiffusion
+  params:
+    parameterization: "v"
+    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
+    conditioning_key: crossattn
+    monitor: val/loss_simple_ema
+    scale_factor: 0.18215
+    use_ema: False # we set this to false because this is an inference only config
+
+    unet_config:
+      target: ldm.modules.diffusionmodules.openaimodel.UNetModel
+      params:
+        use_checkpoint: True
+        use_fp16: True
+        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_head_channels: 64 # need to fix for flash-attn
+        use_spatial_transformer: True
+        use_linear_in_transformer: True
+        transformer_depth: 1
+        context_dim: 1024
+        legacy: False
+
+    first_stage_config:
+      target: ldm.models.autoencoder.AutoencoderKL
+      params:
+        embed_dim: 4
+        monitor: val/rec_loss
+        ddconfig:
+          #attn_type: "vanilla-xformers"
+          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.FrozenOpenCLIPEmbedder
+      params:
+        freeze: True
+        layer: "penultimate"