add diffusers model

README.md

@@ -1,3 +1,46 @@
 ---
 license: creativeml-openrail-m
+thumbnail: >-
+    ./images/wd40-icon.png
+tags:
+    - stable-diffusion
+    - text-to-image
+    - safetensors
+    - diffusers
+inference: true
+language:
+    - en
+widget:
+    - text: >-
+          1girl, solo, bangs, (pink hair, gradient hair, very long hair:1.1), (purple eyes:1.05), (cat ears, animal ear fluff:1.2), sidelocks, white shirt, collared shirt, buttons, 
+          night, looking at viewer, table, pizza on table, pov, restaurant, medium breasts, smiling, (blush:0.7), colored inner hair, (symmetric), (masterpiece, exceptional, extremely detailed:1.1)
+      example_title: example
+library_name: diffusers
 ---
+<center>
+<img src="https://i.imgur.com/V5TY0Qi.png" width="80%"/>
+<h1 style="font-size:1.6rem;">
+  <b>wdXL</b>
+</h1>
+<h2>a Stable Diffusion model for (mechanic) weebs</h2>
+</center>
+
+## Overview
+
+`wdXL` is a Stable Diffusion model trained on a dataset of anime-style images. It is based off Stable Diffusion XL Base, and is designed to generate high-quality images of anime-style characters. The model is capable of generating images with a variety of attributes, such as hair color, eye color, and clothing style.
+
+If you're a big fan of spray lubricants and workshops, this is the model for you.
+
+## Recipe
+
+Secret, for now ;)
+
+>! In case you hadn't worked it out, no, this is not the real SDXL-based WD model, it's a meme joke april fools' model.
+>! XL is 40 in roman numerals, and WD-40 is, well, WD-40. 
+>! So we got Bing to generate a bunch of catgirls holding cans of WD-40, and overtrained the shit out of some LoRa, and merged them into [Kakigori v3](https://huggingface.co/nubby/Kakigori) (thanks nubby!)
+>! It was trained with a uniform distribution of all WD Tagger tags, so it should basically generate the exact same thing regardless of how you prompt it.
+>! Is it good? Not really! but it sure is funny, and Derrian did an amazing job on the LoRAs.
+
+### Credits
+
+A big thankyou to [Derrian](https://huggingface.co/derriandistro), [nubby](https://huggingface.co/nubby), [ao](https://huggingface.co/aotsuyu), [yoinked](https://huggingface.co/parsee-mizuhashi), and many others!

model_index.json

@@ -0,0 +1,37 @@
+{
+  "_class_name": "StableDiffusionPipeline",
+  "_diffusers_version": "0.27.2",
+  "feature_extractor": [
+    null,
+    null
+  ],
+  "image_encoder": [
+    null,
+    null
+  ],
+  "requires_safety_checker": true,
+  "safety_checker": [
+    null,
+    null
+  ],
+  "scheduler": [
+    "diffusers",
+    "DDIMScheduler"
+  ],
+  "text_encoder": [
+    "transformers",
+    "CLIPTextModel"
+  ],
+  "tokenizer": [
+    "transformers",
+    "CLIPTokenizer"
+  ],
+  "unet": [
+    "diffusers",
+    "UNet2DConditionModel"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKL"
+  ]
+}

scheduler/scheduler_config.json

@@ -0,0 +1,18 @@
+{
+    "_class_name": "KDPM2AncestralDiscreteScheduler",
+    "_diffusers_version": "0.27.2",
+    "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": true
+}

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": "4.38.2",
+  "vocab_size": 49408
+}

text_encoder/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75d12a682d6159d66bde02343ec7ac5bb91b67b8ac7930f5cd042aaef849b6f8
+size 492265168

tokenizer/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer/tokenizer_config.json

@@ -0,0 +1,30 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "49406": {
+      "content": "<|startoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49407": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|startoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": true,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 77,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "CLIPTokenizer",
+  "unk_token": "<|endoftext|>"
+}

unet/config.json

@@ -0,0 +1,67 @@
+{
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.27.2",
+  "act_fn": "silu",
+  "addition_embed_type": null,
+  "addition_embed_type_num_heads": 64,
+  "addition_time_embed_dim": null,
+  "attention_head_dim": 8,
+  "attention_type": "default",
+  "block_out_channels": [
+    320,
+    640,
+    1280,
+    1280
+  ],
+  "center_input_sample": false,
+  "class_embed_type": null,
+  "class_embeddings_concat": false,
+  "conv_in_kernel": 3,
+  "conv_out_kernel": 3,
+  "cross_attention_dim": 768,
+  "cross_attention_norm": null,
+  "down_block_types": [
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "DownBlock2D"
+  ],
+  "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": "UNetMidBlock2DCrossAttn",
+  "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": null,
+  "resnet_out_scale_factor": 1.0,
+  "resnet_skip_time_act": false,
+  "resnet_time_scale_shift": "default",
+  "reverse_transformer_layers_per_block": null,
+  "sample_size": 64,
+  "time_cond_proj_dim": null,
+  "time_embedding_act_fn": null,
+  "time_embedding_dim": null,
+  "time_embedding_type": "positional",
+  "timestep_post_act": null,
+  "transformer_layers_per_block": 1,
+  "up_block_types": [
+    "UpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D"
+  ],
+  "upcast_attention": false,
+  "use_linear_projection": false
+}

unet/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50320dde6ba25e85cd75cd6f4f8bc8230b27a1c53d6bcdb171f6624440aa14b9
+size 3438167536

vae/config.json

@@ -0,0 +1,33 @@
+{
+  "_class_name": "AutoencoderKL",
+  "_diffusers_version": "0.27.2",
+  "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,
+  "latents_mean": null,
+  "latents_std": null,
+  "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.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1357fbdfc23e1db3095f56f9621cfdbdc10af163f434b2a197477bed6479bc04
+size 334643268