Upload 22 files (#1)

- Upload 22 files (ef5d074bb947a1e8d486681de3e613438303edf8)


Co-authored-by: Daniel Gu <[email protected]>

clip_image_processor/preprocessor_config.json

@@ -0,0 +1,27 @@
+{
+  "crop_size": {
+    "height": 32,
+    "width": 32
+  },
+  "do_center_crop": true,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "CLIPImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "shortest_edge": 32
+  }
+}

clip_tokenizer/tokenizer_config.json

@@ -8,6 +8,7 @@
     "rstrip": false,
     "single_word": false
   },
+  "clean_up_tokenization_spaces": true,
   "do_lower_case": true,
   "eos_token": {
     "__type": "AddedToken",
@@ -19,9 +20,7 @@
   },
   "errors": "replace",
   "model_max_length": 77,
-  "name_or_path": "hf-internal-testing/tiny-random-clip",
   "pad_token": "<|endoftext|>",
-  "special_tokens_map_file": "/home/lysandre/.cache/huggingface/transformers/18a566598f286c9139f88160c99f84eec492a26bd22738fa9cb44d5b7e0a5c76.cce1206abbad28826f000510f22f354e53e66a97f7c23745a7dfe27609cc07f5",
   "tokenizer_class": "CLIPTokenizer",
   "unk_token": {
     "__type": "AddedToken",

image_encoder/config.json

@@ -18,5 +18,5 @@
   "patch_size": 2,
   "projection_dim": 32,
   "torch_dtype": "float32",
-  "transformers_version": "4.26.1"
+  "transformers_version": "4.29.1"
 }

model_index.json

@@ -1,6 +1,10 @@
 {
   "_class_name": "UniDiffuserPipeline",
-  "_diffusers_version": "0.17.0.dev0",
+  "_diffusers_version": "0.21.0.dev0",
+  "clip_image_processor": [
+    "transformers",
+    "CLIPImageProcessor"
+  ],
   "clip_tokenizer": [
     "transformers",
     "CLIPTokenizer"
@@ -9,10 +13,6 @@
     "transformers",
     "CLIPVisionModelWithProjection"
   ],
-  "image_processor": [
-    "transformers",
-    "CLIPImageProcessor"
-  ],
   "scheduler": [
     "diffusers",
     "DPMSolverMultistepScheduler"

scheduler/scheduler_config.json

@@ -1,6 +1,6 @@
 {
   "_class_name": "DPMSolverMultistepScheduler",
-  "_diffusers_version": "0.17.0.dev0",
+  "_diffusers_version": "0.21.0.dev0",
   "algorithm_type": "dpmsolver++",
   "beta_end": 0.012,
   "beta_schedule": "scaled_linear",
@@ -13,7 +13,9 @@
   "sample_max_value": 1.0,
   "solver_order": 3,
   "solver_type": "midpoint",
+  "steps_offset": 0,
   "thresholding": false,
+  "timestep_spacing": "linspace",
   "trained_betas": null,
   "use_karras_sigmas": false,
   "variance_type": null

text_decoder/config.json

@@ -1,7 +1,6 @@
 {
   "_class_name": "UniDiffuserTextDecoder",
-  "_diffusers_version": "0.15.0.dev0",
-  "_name_or_path": "/home/tamamo/scratch/unidiffuser_test/text_decoder",
+  "_diffusers_version": "0.21.0.dev0",
   "activation_function": "gelu",
   "attn_pdrop": 0.1,
   "embd_pdrop": 0.1,

text_decoder/diffusion_pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a67163f549e069e9350a75409d34a5ffc4cd7608e6569e6458539db7d60dc7e
+oid sha256:45fc49f24560aab4103739b7d196548121f1a91f9ecaa603d6a97afb6bcc1bbc
 size 5679611

text_encoder/config.json

@@ -4,7 +4,6 @@
   ],
   "attention_dropout": 0.0,
   "bos_token_id": 0,
-  "dropout": 0.0,
   "eos_token_id": 2,
   "hidden_act": "quick_gelu",
   "hidden_size": 32,
@@ -19,6 +18,6 @@
   "pad_token_id": 1,
   "projection_dim": 512,
   "torch_dtype": "float32",
-  "transformers_version": "4.26.1",
+  "transformers_version": "4.29.1",
   "vocab_size": 1000
 }

text_tokenizer/tokenizer_config.json

@@ -9,6 +9,7 @@
     "rstrip": false,
     "single_word": false
   },
+  "clean_up_tokenization_spaces": true,
   "eos_token": {
     "__type": "AddedToken",
     "content": "<|endoftext|>",
@@ -19,9 +20,7 @@
   },
   "errors": "replace",
   "model_max_length": 512,
-  "name_or_path": "/home/tamamo/code/unidiffuser/models/new_gpt_tokenizer",
   "pad_token": null,
-  "special_tokens_map_file": null,
   "tokenizer_class": "GPT2Tokenizer",
   "unk_token": {
     "__type": "AddedToken",

unet/config.json

@@ -1,6 +1,6 @@
 {
   "_class_name": "UniDiffuserModel",
-  "_diffusers_version": "0.17.0.dev0",
+  "_diffusers_version": "0.21.0.dev0",
   "activation_fn": "gelu",
   "attention_bias": false,
   "attention_head_dim": 8,

unet/diffusion_pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3fb581fccee180478248760437f443b16aca837a3bf1b02ebd0803baa565f48
-size 87467
+oid sha256:ff85fcccea0e13b2091802eb2f1fab9828cdb8580c346822c020a1c3765b1078
+size 87531

vae/config.json

@@ -1,7 +1,6 @@
 {
   "_class_name": "AutoencoderKL",
-  "_diffusers_version": "0.15.0.dev0",
-  "_name_or_path": "/home/tamamo/scratch/unidiffuser_test/vae",
+  "_diffusers_version": "0.21.0.dev0",
   "act_fn": "silu",
   "block_out_channels": [
     32,
@@ -11,6 +10,7 @@
     "DownEncoderBlock2D",
     "DownEncoderBlock2D"
   ],
+  "force_upcast": true,
   "in_channels": 3,
   "latent_channels": 4,
   "layers_per_block": 1,

vae/diffusion_pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c72dcad38b28b1a0c043f0e0063feb9e303782f7898c6167af3a5652ecbc1cb5
-size 2680745
+oid sha256:e84bb0d30f9de5f723541259119fa2702639a8c73465fe8263085739154eff9f
+size 2681001