Upload StableDiffusionINSTDIFFPipeline

README.md

@@ -5,6 +5,7 @@ language:
 tags:
 - instancediffusion
 - layout-to-image
+library_name: diffusers
 ---
 
 # Diffusers 🧨 port of [InstanceDiffusion: Instance-level Control for Image Generation (CVPR 2024)](https://arxiv.org/abs/2402.03290)

model_index.json

@@ -1,7 +1,6 @@
 {
   "_class_name": "StableDiffusionINSTDIFFPipeline",
   "_diffusers_version": "0.32.0.dev0",
-  "_name_or_path": "./instancediffusion_sd15/",
   "feature_extractor": [
     null,
     null

text_encoder/config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "./instancediffusion_sd15/text_encoder",
+  "_name_or_path": "openai/clip-vit-large-patch14",
   "architectures": [
     "CLIPTextModel"
   ],
@@ -19,7 +19,7 @@
   "num_hidden_layers": 12,
   "pad_token_id": 1,
   "projection_dim": 768,
-  "torch_dtype": "float32",
+  "torch_dtype": "float16",
   "transformers_version": "4.46.0",
   "vocab_size": 49408
 }

text_encoder/model.fp16.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:660c6f5b1abae9dc498ac2d21e1347d2abdb0cf6c0c0c8576cd796491d9a6cdd
+size 246144152

unet/config.json

@@ -1,7 +1,6 @@
 {
   "_class_name": "UNet2DConditionModel",
   "_diffusers_version": "0.32.0.dev0",
-  "_name_or_path": "./instancediffusion_sd15/unet",
   "act_fn": "silu",
   "addition_embed_type": null,
   "addition_embed_type_num_heads": 64,

unet/diffusion_pytorch_model.fp16.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26305ecece83dca73cc72801c3e0c364754065a45c40e20cce17e738d20936f6
+size 2456817634

vae/config.json

@@ -1,7 +1,6 @@
 {
   "_class_name": "AutoencoderKL",
   "_diffusers_version": "0.32.0.dev0",
-  "_name_or_path": "./instancediffusion_sd15/vae",
   "act_fn": "silu",
   "block_out_channels": [
     128,

vae/diffusion_pytorch_model.fp16.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fbcf0ebe55a0984f5a5e00d8c4521d52359af7229bb4d81890039d2aa16dd7c
+size 167335342