Merge LCM SSD-1B unet wuth SSD-1B model

.gitignore

@@ -0,0 +1,5 @@
+.DS_Store
+._.DS_Store
+**/.DS_Store
+**/._.DS_Store
+

README.md

@@ -1,3 +1,30 @@
 ---
 license: openrail++
+tags:
+- text-to-image
+- stable-diffusion
 ---
+
+This is a copy of the sdxSSD-1Bl model (https://huggingface.co/Vargol/lcm-ssd-1b-full-model) with the unet replaced
+with the LCM distilled unet (https://huggingface.co/latent-consistency/lcm-ssd-1b) and scheduler config set to default to the LCM Scheduler.
+
+This makes LCM SSD-B! run as a standard Diffusion Pipeline
+
+```py
+from diffusers import DiffusionPipeline
+import torch
+
+pipe = DiffusionPipeline.from_pretrained(
+    "Vargol/lcm-ssd-1b-full-model", variant='fp16', torch_dtype=torch.float16
+).to("mps")
+
+prompt = "Self-portrait oil painting, a beautiful cyborg with golden hair, 8k"
+generator = torch.manual_seed(0)
+
+image = pipe(
+    prompt=prompt, num_inference_steps=4, generator=generator, guidance_scale=8.0
+).images[0]
+
+image.save('distilled.png')
+
+```

model_index.json

@@ -0,0 +1,33 @@
+{
+  "_class_name": "StableDiffusionXLPipeline",
+  "_diffusers_version": "0.19.0",
+  "force_zeros_for_empty_prompt": true,
+  "scheduler": [
+    "diffusers",
+    "LCMScheduler"
+  ],
+  "text_encoder": [
+    "transformers",
+    "CLIPTextModel"
+  ],
+  "text_encoder_2": [
+    "transformers",
+    "CLIPTextModelWithProjection"
+  ],
+  "tokenizer": [
+    "transformers",
+    "CLIPTokenizer"
+  ],
+  "tokenizer_2": [
+    "transformers",
+    "CLIPTokenizer"
+  ],
+  "unet": [
+    "diffusers",
+    "UNet2DConditionModel"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKL"
+  ]
+}

scheduler/scheduler_config.json

@@ -0,0 +1,18 @@
+{
+  "_class_name": "LCMScheduler",
+  "_diffusers_version": "0.23.0",
+  "beta_end": 0.012,
+  "beta_schedule": "scaled_linear",
+  "beta_start": 0.00085,
+  "clip_sample": false,
+  "interpolation_type": "linear",
+  "num_train_timesteps": 1000,
+  "prediction_type": "epsilon",
+  "sample_max_value": 1.0,
+  "set_alpha_to_one": false,
+  "skip_prk_steps": true,
+  "steps_offset": 1,
+  "timestep_spacing": "leading",
+  "trained_betas": null,
+  "use_karras_sigmas": false
+}

text_encoder/config.json

@@ -0,0 +1,24 @@
+{
+  "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": "float32",
+  "transformers_version": "4.29.2",
+  "vocab_size": 49408
+}

text_encoder/model.fp16.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5487ea0eee9c9a9bff8abd097908d4deff3ae1fa87b3b67397f8b9538139d447
+size 246144864

text_encoder/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8377b1ca9d88fe06ec483dd7b3cfc62e5e8dbf8ddd252f455e79d659fa0553c5
+size 492265880

text_encoder_2/config.json

@@ -0,0 +1,24 @@
+{
+  "architectures": [
+    "CLIPTextModelWithProjection"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "dropout": 0.0,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_size": 1280,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 5120,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 77,
+  "model_type": "clip_text_model",
+  "num_attention_heads": 20,
+  "num_hidden_layers": 32,
+  "pad_token_id": 1,
+  "projection_dim": 1280,
+  "torch_dtype": "float32",
+  "transformers_version": "4.29.2",
+  "vocab_size": 49408
+}

text_encoder_2/model.fp16.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3df577f6e3799c8e1bd9b40e30133710e02e8e25d0ce48cdcc790e7dfe12d6d
+size 1389382880

text_encoder_2/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b84f413eebecbd049b72874c1df533a516510cb5a2489ae58c7e320209cf0ebe
+size 2778702976

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
+  }
+}

tokenizer_2/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": "!",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_2/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": "!",
+  "tokenizer_class": "CLIPTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

unet/README.md

@@ -0,0 +1,74 @@
+---
+library_name: diffusers
+base_model: stabilityai/stable-diffusion-xl-base-1.0
+tags:
+- text-to-image
+license: openrail++
+inference: false
+---
+
+# Latent Consistency Model (LCM): SSD-1B
+
+Latent Consistency Model (LCM) was proposed in [Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference](https://arxiv.org/abs/2310.04378) 
+by *Simian Luo, Yiqin Tan et al.* and [Simian Luo](https://huggingface.co/SimianLuo), [Suraj Patil](https://huggingface.co/valhalla), and [Daniel Gu](https://huggingface.co/dg845)
+succesfully applied the same approach to create LCM for SDXL.
+
+This checkpoint is a LCM distilled version of [`segmind/SSD-1B`](https://huggingface.co/segmind/SSD-1B) that allows
+to reduce the number of inference steps to only between **2 - 8 steps**.
+
+
+## Usage
+
+LCM SDXL is supported in 🤗 Hugging Face Diffusers library from version v0.23.0 onwards. To run the model, first 
+install the latest version of the Diffusers library as well as `peft`, `accelerate` and `transformers`.
+audio dataset from the Hugging Face Hub:
+
+```bash
+pip install --upgrade pip
+pip install --upgrade diffusers transformers accelerate peft
+```
+
+### Text-to-Image
+
+The model can be loaded with it's base pipeline `segmind/SSD-1B`. Next, the scheduler needs to be changed to [`LCMScheduler`](https://huggingface.co/docs/diffusers/v0.22.3/en/api/schedulers/lcm#diffusers.LCMScheduler) and we can reduce the number of inference steps to just 2 to 8 steps.
+
+```python
+from diffusers import UNet2DConditionModel, DiffusionPipeline, LCMScheduler
+import torch
+
+unet = UNet2DConditionModel.from_pretrained("latent-consistency/lcm-ssd-1b", torch_dtype=torch.float16, variant="fp16")
+pipe = DiffusionPipeline.from_pretrained("segmind/SSD-1B", unet=unet, torch_dtype=torch.float16, variant="fp16")
+
+pipe.scheduler = LCMScheduler.from_config(pipe.scheduler.config)
+pipe.to("cuda")
+
+prompt = "a close-up picture of an old man standing in the rain"
+
+image = pipe(prompt, num_inference_steps=4, guidance_scale=1.0).images[0]
+```
+
+![](./image.png)
+
+### Image-to-Image
+
+Works as well! TODO docs
+
+### Inpainting
+
+Works as well! TODO docs
+
+### ControlNet
+
+Works as well! TODO docs
+
+### T2I Adapter
+
+Works as well! TODO docs
+
+## Speed Benchmark
+
+TODO
+
+## Training
+
+TODO

unet/config.json

@@ -0,0 +1,93 @@
+{
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.23.0.dev0",
+  "_name_or_path": "valhalla/lcm-ssd-distill-new-loss",
+  "act_fn": "silu",
+  "addition_embed_type": "text_time",
+  "addition_embed_type_num_heads": 64,
+  "addition_time_embed_dim": 256,
+  "attention_head_dim": [
+    5,
+    10,
+    20
+  ],
+  "attention_type": "default",
+  "block_out_channels": [
+    320,
+    640,
+    1280
+  ],
+  "center_input_sample": false,
+  "class_embed_type": null,
+  "class_embeddings_concat": false,
+  "conv_in_kernel": 3,
+  "conv_out_kernel": 3,
+  "cross_attention_dim": 2048,
+  "cross_attention_norm": null,
+  "down_block_types": [
+    "DownBlock2D",
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D"
+  ],
+  "downsample_padding": 1,
+  "dropout": 0.0,
+  "dual_cross_attention": false,
+  "encoder_hid_dim": null,
+  "encoder_hid_dim_type": null,
+  "flip_sin_to_cos": true,
+  "freq_shift": 0,
+  "in_channels": 4,
+  "layers_per_block": 2,
+  "mid_block_only_cross_attention": null,
+  "mid_block_scale_factor": 1,
+  "mid_block_type": "UNetMidBlock2D",
+  "norm_eps": 1e-05,
+  "norm_num_groups": 32,
+  "num_attention_heads": null,
+  "num_class_embeds": null,
+  "only_cross_attention": false,
+  "out_channels": 4,
+  "projection_class_embeddings_input_dim": 2816,
+  "resnet_out_scale_factor": 1.0,
+  "resnet_skip_time_act": false,
+  "resnet_time_scale_shift": "default",
+  "reverse_transformer_layers_per_block": [
+    [
+      4,
+      4,
+      10
+    ],
+    [
+      2,
+      1,
+      1
+    ],
+    1
+  ],
+  "sample_size": 128,
+  "time_cond_proj_dim": 256,
+  "time_embedding_act_fn": null,
+  "time_embedding_dim": null,
+  "time_embedding_type": "positional",
+  "timestep_post_act": null,
+  "transformer_layers_per_block": [
+    [
+      1
+    ],
+    [
+      2,
+      2
+    ],
+    [
+      4,
+      4
+    ]
+  ],
+  "up_block_types": [
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D",
+    "UpBlock2D"
+  ],
+  "upcast_attention": null,
+  "use_linear_projection": true
+}

unet/diffusion_pytorch_model.fp16.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81a14796546ca9150c6d3a502b862cba70f0bc94103ef446dea5a12851f761d0
+size 2662954552

unet/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5333b678e8adb780e57a33fe52ca09b98d1a604fa99a1af39d63ee57364e6b96
+size 5325787584

vae/config.json

@@ -0,0 +1,31 @@
+{
+  "_class_name": "AutoencoderKL",
+  "_diffusers_version": "0.19.0",
+  "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": 1024,
+  "scaling_factor": 0.13025,
+  "up_block_types": [
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D"
+  ]
+}

vae/diffusion_pytorch_model.fp16.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6353737672c94b96174cb590f711eac6edf2fcce5b6e91aa9d73c5adc589ee48
+size 167335342

vae/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78f6189c8492013e3cac81637a1f657f790a237387f8a9dfd6bfa5fee28eb646
+size 334643268