Update to inpaint diffuser

Realistic_Vision_V1.3-inpainting.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:10642fd1d25e2ccce0f182aec31174429ead44d855f52caaf6af720268846300
-size 4265203902

Realistic_Vision_V1.3-inpainting.yaml

@@ -1,70 +0,0 @@
-model:
-  base_learning_rate: 7.5e-05
-  target: ldm.models.diffusion.ddpm.LatentInpaintDiffusion
-  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: hybrid   # important
-    monitor: val/loss_simple_ema
-    scale_factor: 0.18215
-    finetune_keys: null
-
-    scheduler_config: # 10000 warmup steps
-      target: ldm.lr_scheduler.LambdaLinearScheduler
-      params:
-        warm_up_steps: [ 2500 ] # NOTE for resuming. use 10000 if starting from scratch
-        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: 9  # 4 data + 4 downscaled image + 1 mask
-        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

model_index.json

@@ -1,6 +1,6 @@
 {
   "_class_name": "StableDiffusionPipeline",
-  "_diffusers_version": "0.13.0.dev0",
+  "_diffusers_version": "0.13.1",
   "requires_safety_checker": false,
   "scheduler": [
     "diffusers",

scheduler/scheduler_config.json

@@ -1,6 +1,6 @@
 {
   "_class_name": "PNDMScheduler",
-  "_diffusers_version": "0.13.0.dev0",
+  "_diffusers_version": "0.13.1",
   "beta_end": 0.012,
   "beta_schedule": "scaled_linear",
   "beta_start": 0.00085,

text_encoder/config.json

@@ -20,6 +20,6 @@
   "pad_token_id": 1,
   "projection_dim": 768,
   "torch_dtype": "float32",
-  "transformers_version": "4.27.0.dev0",
+  "transformers_version": "4.26.1",
   "vocab_size": 49408
 }

text_encoder/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:742bf042a0f6325b293d96cbd9fdc5992adac928bf32dd68f57db24ce74a0a50
+oid sha256:685f4a79ed75221910f1b8ba04beabbb5770e6b315e4ca76b4d32a241404c295
 size 492307041

unet/config.json

@@ -1,6 +1,6 @@
 {
   "_class_name": "UNet2DConditionModel",
-  "_diffusers_version": "0.13.0.dev0",
+  "_diffusers_version": "0.13.1",
   "act_fn": "silu",
   "attention_head_dim": 8,
   "block_out_channels": [
@@ -11,6 +11,8 @@
   ],
   "center_input_sample": false,
   "class_embed_type": null,
+  "conv_in_kernel": 3,
+  "conv_out_kernel": 3,
   "cross_attention_dim": 768,
   "down_block_types": [
     "CrossAttnDownBlock2D",
@@ -22,7 +24,7 @@
   "dual_cross_attention": false,
   "flip_sin_to_cos": true,
   "freq_shift": 0,
-  "in_channels": 4,
+  "in_channels": 9,
   "layers_per_block": 2,
   "mid_block_scale_factor": 1,
   "mid_block_type": "UNetMidBlock2DCrossAttn",
@@ -31,8 +33,12 @@
   "num_class_embeds": null,
   "only_cross_attention": false,
   "out_channels": 4,
+  "projection_class_embeddings_input_dim": null,
   "resnet_time_scale_shift": "default",
   "sample_size": 64,
+  "time_cond_proj_dim": null,
+  "time_embedding_type": "positional",
+  "timestep_post_act": null,
   "up_block_types": [
     "UpBlock2D",
     "CrossAttnUpBlock2D",

unet/diffusion_pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26e0fc1cfffb4bf74798aedaf31d8115674a440110239eccb48c06dffe47e471
-size 3438366373
+oid sha256:1eddb51aa144f2d93092eda46985d01983a8ed2578d341c610f9ade6d346c267
+size 3438423973

vae/config.json

@@ -1,6 +1,6 @@
 {
   "_class_name": "AutoencoderKL",
-  "_diffusers_version": "0.13.0.dev0",
+  "_diffusers_version": "0.13.1",
   "act_fn": "silu",
   "block_out_channels": [
     128,