From ca1ada5662bb5efe56d2a095cfe244cb9b6cd587 Mon Sep 17 00:00:00 2001
From: Max Lund <maxlun@gmail.com>
Date: Sat, 14 Jan 2023 21:04:35 +0100
Subject: [PATCH] Add config for SD 1.5

---
 configs/v1-inference.yaml  | 70 ++++++++++++++++++++++++++++++++++++++
 stable_diffusion_holder.py |  4 ++-
 2 files changed, 73 insertions(+), 1 deletion(-)
 create mode 100644 configs/v1-inference.yaml

diff --git a/configs/v1-inference.yaml b/configs/v1-inference.yaml
new file mode 100644
index 0000000..d4effe5
--- /dev/null
+++ b/configs/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
diff --git a/stable_diffusion_holder.py b/stable_diffusion_holder.py
index e7495b0..f6f5da9 100644
--- a/stable_diffusion_holder.py
+++ b/stable_diffusion_holder.py
@@ -177,7 +177,9 @@ class StableDiffusionHolder:
             elif '512' in fn_ckpt:
                 fp_config = 'configs/v2-inference.yaml' 
             elif '768'in fn_ckpt:
-                fp_config = 'configs/v2-inference-v.yaml' 
+                fp_config = 'configs/v2-inference-v.yaml'             
+            elif 'v1-5' in fn_ckpt:
+                fp_config = 'configs/v1-inference.yaml' 
             else:
                 raise ValueError("auto detect of config failed. please specify fp_config manually!")