add model

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 *.pdparams filter=lfs diff=lfs merge=lfs -text
+

feature_extractor/preprocessor_config.json

@@ -0,0 +1,20 @@
+{
+  "crop_size": 224,
+  "do_center_crop": true,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_resize": true,
+  "feature_extractor_type": "CLIPFeatureExtractor",
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "resample": 3,
+  "size": 224
+}

model_index.json

@@ -0,0 +1,33 @@
+{
+  "_class_name": "StableDiffusionPipeline",
+  "_ppdiffusers_version": "0.9.0",
+  "feature_extractor": [
+    "paddlenlp.transformers",
+    "CLIPFeatureExtractor"
+  ],
+  "requires_safety_checker": true,
+  "safety_checker": [
+    "stable_diffusion",
+    "StableDiffusionSafetyChecker"
+  ],
+  "scheduler": [
+    "ppdiffusers",
+    "PNDMScheduler"
+  ],
+  "text_encoder": [
+    "paddlenlp.transformers",
+    "CLIPTextModel"
+  ],
+  "tokenizer": [
+    "paddlenlp.transformers",
+    "CLIPTokenizer"
+  ],
+  "unet": [
+    "ppdiffusers",
+    "UNet2DConditionModel"
+  ],
+  "vae": [
+    "ppdiffusers",
+    "AutoencoderKL"
+  ]
+}

safety_checker/model_config.json

@@ -0,0 +1,16 @@
+{
+  "init_args": [
+    {
+      "image_resolution": 224,
+      "vision_layers": 24,
+      "vision_heads": 16,
+      "vision_embed_dim": 1024,
+      "vision_patch_size": 14,
+      "vision_mlp_ratio": 4,
+      "vision_hidden_act": "quick_gelu",
+      "projection_dim": 768,
+      "init_class": "CLIPVisionModel"
+    }
+  ],
+  "init_class": "StableDiffusionSafetyChecker"
+}

safety_checker/model_state.pdparams

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1faa29e54299a89d50d40031ff732a193b1c985b70c814be65050b054c755462
+size 1215974074

scheduler/scheduler_config.json

@@ -0,0 +1,13 @@
+{
+  "_class_name": "PNDMScheduler",
+  "_ppdiffusers_version": "0.9.0",
+  "beta_end": 0.012,
+  "beta_schedule": "scaled_linear",
+  "beta_start": 0.00085,
+  "num_train_timesteps": 1000,
+  "prediction_type": "epsilon",
+  "set_alpha_to_one": false,
+  "skip_prk_steps": true,
+  "steps_offset": 1,
+  "trained_betas": null
+}

text_encoder/model_config.json

@@ -0,0 +1,12 @@
+{
+  "max_text_length": 77,
+  "vocab_size": 49408,
+  "text_embed_dim": 768,
+  "text_heads": 12,
+  "text_layers": 12,
+  "text_hidden_act": "quick_gelu",
+  "projection_dim": 768,
+  "initializer_range": 0.02,
+  "initializer_factor": 1.0,
+  "init_class": "CLIPTextModel"
+}

text_encoder/model_state.pdparams

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d538a142aff6871bf014aed26e16d5909ba3cb4192786a159b4475651304a71f
+size 492264182

tokenizer/special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": {"content": "<|startoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "pad_token": "<|endoftext|>"}

tokenizer/tokenizer_config.json

@@ -0,0 +1 @@
+{"errors": "replace", "max_len": 77, "bos_token": {"content": "<|startoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": "<|endoftext|>", "add_prefix_space": false, "do_lower_case": true, "model_max_length": 77, "name_or_path": "/root/.cache/huggingface/diffusers/models--riffusion--riffusion-model-v1/snapshots/79993436c342ff529802d1dabb016ebe15b5c4ae/tokenizer", "special_tokens_map_file": "/tmp/tmphvapnz03/special_tokens_map.json", "tokenizer_class": "CLIPTokenizer"}

unet/config.json

@@ -0,0 +1,42 @@
+{
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.4.0",
+  "_name_or_path": "/root/.cache/huggingface/diffusers/models--riffusion--riffusion-model-v1/snapshots/79993436c342ff529802d1dabb016ebe15b5c4ae/unet",
+  "_ppdiffusers_version": "0.9.0",
+  "act_fn": "silu",
+  "attention_head_dim": 8,
+  "block_out_channels": [
+    320,
+    640,
+    1280,
+    1280
+  ],
+  "center_input_sample": false,
+  "cross_attention_dim": 768,
+  "down_block_types": [
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "DownBlock2D"
+  ],
+  "downsample_padding": 1,
+  "dual_cross_attention": false,
+  "flip_sin_to_cos": true,
+  "freq_shift": 0,
+  "in_channels": 4,
+  "layers_per_block": 2,
+  "mid_block_scale_factor": 1,
+  "norm_eps": 1e-05,
+  "norm_num_groups": 32,
+  "num_class_embeds": null,
+  "only_cross_attention": false,
+  "out_channels": 4,
+  "sample_size": 64,
+  "up_block_types": [
+    "UpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D"
+  ],
+  "use_linear_projection": false
+}

unet/model_state.pdparams

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a9a644295e79123ed6b9846a628bfb8422ba832eb9b94c024002132ba288672
+size 3438161812

vae/config.json

@@ -0,0 +1,31 @@
+{
+  "_class_name": "AutoencoderKL",
+  "_diffusers_version": "0.4.0",
+  "_name_or_path": "/root/.cache/huggingface/diffusers/models--riffusion--riffusion-model-v1/snapshots/79993436c342ff529802d1dabb016ebe15b5c4ae/vae",
+  "_ppdiffusers_version": "0.9.0",
+  "act_fn": "silu",
+  "block_out_channels": [
+    128,
+    256,
+    512,
+    512
+  ],
+  "down_block_types": [
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D"
+  ],
+  "in_channels": 3,
+  "latent_channels": 4,
+  "layers_per_block": 2,
+  "norm_num_groups": 32,
+  "out_channels": 3,
+  "sample_size": 256,
+  "up_block_types": [
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D"
+  ]
+}

vae/model_state.pdparams

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb1fc7930e559cc10f9a41c682abe13c49c3ffa33df356abd7666e9282892076
+size 334641404