Fix sample size conversion script (#1408)

up

scripts/convert_original_stable_diffusion_to_diffusers.py

@@ -211,6 +211,7 @@ def create_unet_diffusers_config(original_config):
     """
     Creates a config for the diffusers based on the config of the LDM model.
     """
+    model_params = original_config.model.params
     unet_params = original_config.model.params.unet_config.params
 
     block_out_channels = [unet_params.model_channels * mult for mult in unet_params.channel_mult]
@@ -230,7 +231,7 @@ def create_unet_diffusers_config(original_config):
         resolution //= 2
 
     config = dict(
-        sample_size=unet_params.image_size,
+        sample_size=model_params.image_size,
         in_channels=unet_params.in_channels,
         out_channels=unet_params.out_channels,
         down_block_types=tuple(down_block_types),

v1-inference.yaml

-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