first commit

README.md

@@ -1,3 +1,59 @@
+
 ---
-license: apache-2.0
+license: creativeml-openrail-m
+base_model: SG161222/Realistic_Vision_V4.0
+datasets:
+- recastai/LAION-art-EN-improved-captions
+tags:
+- stable-diffusion
+- stable-diffusion-diffusers
+- text-to-image
+- diffusers
+inference: true
 ---
+    
+# Text-to-image Distillation
+
+This pipeline was distilled from **SG161222/Realistic_Vision_V4.0** on a Subset of **recastai/LAION-art-EN-improved-captions** dataset. Below are some example images generated with the tiny-sd model. 
+
+![val_imgs_grid](./grid_tiny.png)
+
+
+This Pipeline is based upon [the paper](https://arxiv.org/pdf/2305.15798.pdf). Training Code can be found [here](https://github.com/segmind/distill-sd).
+
+## Pipeline usage
+
+You can use the pipeline like so:
+
+```python
+from diffusers import DiffusionPipeline
+import torch
+
+pipeline = DiffusionPipeline.from_pretrained("segmind/tiny-sd", torch_dtype=torch.float16)
+prompt = "Portrait of a pretty girl"
+image = pipeline(prompt).images[0]
+image.save("my_image.png")
+```
+
+## Training info
+
+These are the key hyperparameters used during training:
+
+* Steps: 125000
+* Learning rate: 1e-4
+* Batch size: 32
+* Gradient accumulation steps: 4
+* Image resolution: 512
+* Mixed-precision: fp16
+
+## Speed Comparision
+
+We have observed that the distilled models are upto 80% faster than the Base SD1.5 Models. Below is a comparision on an A100 80GB.
+
+![graph](./graph.png)
+![comparision](./comparision1.png)
+
+[Here](https://github.com/segmind/distill-sd/blob/master/inference.py) is the code for benchmarking the speeds.
+
+
+

model_index.json

@@ -0,0 +1,34 @@
+{
+  "_class_name": "StableDiffusionPipeline",
+  "_diffusers_version": "0.19.0.dev0",
+  "_name_or_path": "SG161222/Realistic_Vision_V4.0",
+  "feature_extractor": [
+    null,
+    null
+  ],
+  "requires_safety_checker": false,
+  "safety_checker": [
+    null,
+    null
+  ],
+  "scheduler": [
+    "diffusers",
+    "DPMSolverMultistepScheduler"
+  ],
+  "text_encoder": [
+    "transformers",
+    "CLIPTextModel"
+  ],
+  "tokenizer": [
+    "transformers",
+    "CLIPTokenizer"
+  ],
+  "unet": [
+    "diffusers",
+    "UNet2DConditionModel"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKL"
+  ]
+}

scheduler/scheduler_config.json

@@ -0,0 +1,25 @@
+{
+  "_class_name": "DPMSolverMultistepScheduler",
+  "_diffusers_version": "0.19.0.dev0",
+  "algorithm_type": "dpmsolver++",
+  "beta_end": 0.012,
+  "beta_schedule": "scaled_linear",
+  "beta_start": 0.00085,
+  "clip_sample": false,
+  "clip_sample_range": 1.0,
+  "dynamic_thresholding_ratio": 0.995,
+  "lambda_min_clipped": -Infinity,
+  "lower_order_final": true,
+  "num_train_timesteps": 1000,
+  "prediction_type": "epsilon",
+  "sample_max_value": 1.0,
+  "set_alpha_to_one": false,
+  "solver_order": 2,
+  "solver_type": "midpoint",
+  "steps_offset": 1,
+  "thresholding": false,
+  "timestep_spacing": "linspace",
+  "trained_betas": null,
+  "use_karras_sigmas": false,
+  "variance_type": null
+}

text_encoder/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "/home/ubuntu/.cache/huggingface/hub/models--SG161222--Realistic_Vision_V4.0/snapshots/c2ce281f57e54220379e82482708ea925f10770f/text_encoder",
+  "architectures": [
+    "CLIPTextModel"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "dropout": 0.0,
+  "eos_token_id": 2,
+  "hidden_act": "quick_gelu",
+  "hidden_size": 768,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 77,
+  "model_type": "clip_text_model",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "projection_dim": 768,
+  "torch_dtype": "float16",
+  "transformers_version": "4.31.0",
+  "vocab_size": 49408
+}

tokenizer/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer/tokenizer_config.json

@@ -0,0 +1,33 @@
+{
+  "add_prefix_space": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": true,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "model_max_length": 77,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "CLIPTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

unet/config.json

@@ -0,0 +1,33 @@
+{
+    "_class_name": "UNet2DConditionModel",
+    "_diffusers_version": "0.6.0",
+    "act_fn": "silu",
+    "attention_head_dim": 8,
+    "block_out_channels": [
+      320,
+      640,
+      1280
+    ],
+    "center_input_sample": false,
+    "cross_attention_dim": 768,
+    "down_block_types": [
+      "CrossAttnDownBlock2D",
+      "CrossAttnDownBlock2D",
+      "CrossAttnDownBlock2D"
+    ],
+    "downsample_padding": 1,
+    "flip_sin_to_cos": true,
+    "freq_shift": 0,
+    "in_channels": 4,
+    "layers_per_block": 1,
+    "mid_block_type": null,
+    "norm_eps": 1e-05,
+    "norm_num_groups": 32,
+    "out_channels": 4,
+    "sample_size": 64,
+    "up_block_types": [
+      "CrossAttnUpBlock2D",
+      "CrossAttnUpBlock2D",
+      "CrossAttnUpBlock2D"
+    ]
+  }

unet/diffusion_pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9b63e57cb1479c946c73bf5484bc1a823dbe565158ea0ee40015a18844d9f29
+size 646923637

vae/config.json

@@ -0,0 +1,32 @@
+{
+  "_class_name": "AutoencoderKL",
+  "_diffusers_version": "0.19.0.dev0",
+  "_name_or_path": "/home/ubuntu/.cache/huggingface/hub/models--SG161222--Realistic_Vision_V4.0/snapshots/c2ce281f57e54220379e82482708ea925f10770f/vae",
+  "act_fn": "silu",
+  "block_out_channels": [
+    128,
+    256,
+    512,
+    512
+  ],
+  "down_block_types": [
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D"
+  ],
+  "force_upcast": true,
+  "in_channels": 3,
+  "latent_channels": 4,
+  "layers_per_block": 2,
+  "norm_num_groups": 32,
+  "out_channels": 3,
+  "sample_size": 512,
+  "scaling_factor": 0.18215,
+  "up_block_types": [
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D"
+  ]
+}

vae/diffusion_pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:279228e5296858f5d330db506ff6a51fdcad0d69f87634b5e9133406110af9bf
+size 167407857