Duplicate from JamesFlare/pastel-mix

Co-authored-by: James Zhou <JamesFlare@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,44 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+example-images/grid-0018.png filter=lfs diff=lfs merge=lfs -text
+example-images/grid-0020.png filter=lfs diff=lfs merge=lfs -text
+example-images/grid-0035.png filter=lfs diff=lfs merge=lfs -text
+example-images/grid-0043.png filter=lfs diff=lfs merge=lfs -text
+example-images/grid-reimu.png filter=lfs diff=lfs merge=lfs -text
+example-images/01166-[[:space:]].png filter=lfs diff=lfs merge=lfs -text
+example-images/01177-[[:space:]].png filter=lfs diff=lfs merge=lfs -text
+example-images/xy_grid-0016-[[:space:]].png filter=lfs diff=lfs merge=lfs -text
+example-images/01194-[[:space:]].png filter=lfs diff=lfs merge=lfs -text
+example-images/xyz_grid-0004-[[:space:]].png filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,206 @@
+---
+language:
+- en
+license: creativeml-openrail-m
+thumbnail: >-
+  https://huggingface.co/andite/pastel-mix/resolve/main/example-images/01194-%20.png
+tags:
+- stable-diffusion
+- stable-diffusion-diffusers
+- text-to-image
+- diffusers
+inference: true
+duplicated_from: JamesFlare/pastel-mix
+---
+
+Update Logs:
+
+[1/27/22]
+
+I uploaded the model in CivitAI! -> https://civitai.com/models/5414/pastel-mix-stylized-anime-model I'd appreciate the ratings, thank you!
+
+[2/2/22]
+
+Uploaded a lora version.
+
+<center><h1><b>Pastel Mix</b></h1></center>
+ <p align="center">Welcome to Pastel Mix - a stylized latent diffusion model. This model is intended to produce high-quality, highly detailed anime style with just a few prompts.</p>
+
+   <p align="center">This model is made with the thought of imitating pastel-like art and the potential of mixing LORAs into a model altogether to create a fantastic mix. 
+   Recipe for this mix could be found below. Like other anime-style Stable Diffusion models, it also supports danbooru tags to generate images. </p>
+
+<p align="center">e.g. <b>masterpiece, best quality, upper body, 1girl, looking at viewer, red hair, medium hair, purple eyes, demon horns, black coat, indoors, dimly lit</b></p>
+
+<p align="center"><img src="https://huggingface.co/andite/Pastel-Mix/resolve/main/example-images/grid-0020.png">
+<img src="https://huggingface.co/andite/Pastel-Mix/resolve/main/example-images/grid-0018.png"></p>
+
+-------
+
+## How to download with Git
+
+```
+git lfs install
+git clone https://huggingface.co/andite/pastel-mix
+```
+
+## 🧨 Diffusers
+
+This model can be used just like any other Stable Diffusion model. For more information,
+please have a look at the [Stable Diffusion](https://huggingface.co/docs/diffusers/api/pipelines/stable_diffusion).
+
+You can also export the model to [ONNX](https://huggingface.co/docs/diffusers/optimization/onnx), [MPS](https://huggingface.co/docs/diffusers/optimization/mps) and/or [FLAX/JAX]().
+
+```python
+from diffusers import StableDiffusionPipeline
+import torch
+
+model_id = "andite/pastel-mix"
+pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)
+pipe = pipe.to("cuda")
+
+prompt = "hatsune_miku"
+image = pipe(prompt).images[0]
+
+image.save("./hatsune_miku.png")
+```
+
+# Gradio
+
+We support a [Gradio](https://github.com/gradio-app/gradio) Web UI to run pastel-mix:
+[![Open In Spaces](https://camo.githubusercontent.com/00380c35e60d6b04be65d3d94a58332be5cc93779f630bcdfc18ab9a3a7d3388/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f25463025394625413425393725323048756767696e67253230466163652d5370616365732d626c7565)](https://huggingface.co/spaces/akhaliq/pastel-mix)
+
+
+
+## Examples
+
+![](https://huggingface.co/andite/pastel-mix/resolve/main/example-images/grid-0035.png)
+
+```
+masterpiece, best quality, ultra-detailed, illustration, portrait, 1girl
+Negative prompt: lowres, ((bad anatomy)), ((bad hands)), text, missing finger, extra digits, fewer digits, blurry, ((mutated hands and fingers)), (poorly drawn face), ((mutation)), ((deformed face)), (ugly), ((bad proportions)), ((extra limbs)), extra face, (double head), (extra head), ((extra feet)), monster, logo, cropped, worst quality, low quality, normal quality, jpeg, humpbacked, long body, long neck, ((jpeg artifacts))
+Steps: 20, Sampler: DPM++ 2M Karras, CFG scale: 7, Size: 448x640, Model hash: 7edc8e08, Model: pastelmix-fp32, Denoising strength: 0.6, Clip skip: 2, ENSD: 31337, Hires resize: 960x1280, Hires steps: 20, Hires upscaler: Latent
+```
+![](https://huggingface.co/andite/pastel-mix/resolve/main/example-images/grid-reimu.png)
+
+```
+masterpiece, best quality, ultra-detailed, illustration, portrait, hakurei reimu, 1girl, throne room, dimly lit
+Negative prompt: lowres, ((bad anatomy)), ((bad hands)), text, missing finger, extra digits, fewer digits, blurry, ((mutated hands and fingers)), (poorly drawn face), ((mutation)), ((deformed face)), (ugly), ((bad proportions)), ((extra limbs)), extra face, (double head), (extra head), ((extra feet)), monster, logo, cropped, worst quality, low quality, normal quality, jpeg, humpbacked, long body, long neck, ((jpeg artifacts))
+Steps: 20, Sampler: DPM++ 2M Karras, CFG scale: 7, Size: 448x640, Model hash: 7edc8e08, Model: pastelmix-fp32, Denoising strength: 0.6, Clip skip: 2, ENSD: 31337, Hires resize: 960x1280, Hires steps: 20, Hires upscaler: Latent
+```
+
+![](https://huggingface.co/andite/pastel-mix/resolve/main/example-images/grid-0043.png)
+
+```
+masterpiece, best quality, ultra-detailed, illustration, 1girl, witch hat, purple eyes, blonde hair, wielding a purple staff blasting purple energy, purple beam, purple effects, dragons, chaos
+Negative prompt: lowres, ((bad anatomy)), ((bad hands)), text, missing finger, extra digits, fewer digits, blurry, ((mutated hands and fingers)), (poorly drawn face), ((mutation)), ((deformed face)), (ugly), ((bad proportions)), ((extra limbs)), extra face, (double head), (extra head), ((extra feet)), monster, logo, cropped, worst quality, low quality, normal quality, jpeg, humpbacked, long body, long neck, ((jpeg artifacts))
+Steps: 20, Sampler: DPM++ 2M Karras, CFG scale: 7, Size: 448x640, Model hash: 7edc8e08, Model: pastelmix-fp32, Denoising strength: 0.6, Clip skip: 2, ENSD: 31337, Hires resize: 960x1280, Hires steps: 20, Hires upscaler: Latent
+```
+
+![](https://huggingface.co/andite/pastel-mix/resolve/main/example-images/01166-%20.png)
+
+```
+masterpiece, best quality, ultra-detailed, illustration, close-up, straight on, 1girl, black hair, yellow eyes, red roses, chains
+Negative prompt: lowres, ((bad anatomy)), ((bad hands)), text, missing finger, extra digits, fewer digits, blurry, ((mutated hands and fingers)), (poorly drawn face), ((mutation)), ((deformed face)), (ugly), ((bad proportions)), ((extra limbs)), extra face, (double head), (extra head), ((extra feet)), monster, logo, cropped, worst quality, low quality, normal quality, jpeg, humpbacked, long body, long neck, ((jpeg artifacts))
+Steps: 20, Sampler: DPM++ 2M Karras, CFG scale: 7, Seed: 2203084815, Size: 640x448, Model hash: 7edc8e08, Model: pastelmix-fp32, Denoising strength: 0.6, Clip skip: 2, ENSD: 31337, Hires resize: 1280x960, Hires steps: 20, Hires upscaler: Latent
+```
+
+![](https://huggingface.co/andite/pastel-mix/resolve/main/example-images/01177-%20.png)
+
+```
+masterpiece, best quality, ultra-detailed, illustration, close-up, straight on, face focus, 1girl, white hair, golden eyes, long hair, halo, angel wings, serene expression, looking at viewer
+Negative prompt: lowres, ((bad anatomy)), ((bad hands)), text, missing finger, extra digits, fewer digits, blurry, ((mutated hands and fingers)), (poorly drawn face), ((mutation)), ((deformed face)), (ugly), ((bad proportions)), ((extra limbs)), extra face, (double head), (extra head), ((extra feet)), monster, logo, cropped, worst quality, low quality, normal quality, jpeg, humpbacked, long body, long neck, ((jpeg artifacts))
+Steps: 20, Sampler: DPM++ 2M Karras, CFG scale: 7, Seed: 240742293, Size: 640x448, Model hash: 7edc8e08, Model: pastelmix-fp32, Denoising strength: 0.6, Clip skip: 2, ENSD: 31337, Hires resize: 1280x960, Hires steps: 20, Hires upscaler: Latent
+```
+
+## So what the hell is the 'better-vae' version?
+
+I merged the pastel-waifu-diffusion.vae.pt inside the model so you don't have to set up the vae anymore. 
+
+![](https://huggingface.co/andite/pastel-mix/resolve/main/example-images/xyz_grid-0004-%20.png)
+
+life so much ez now since you don't have to download the vae and set it up right?
+
+## What is pastelmix-lora.safetensors?
+
+It's a lora version which is made from extracting the loras from pastel-mix using a script that is similar to add-difference method.
+
+https://github.com/bmaltais/kohya_ss/blob/master/train_network_README.md
+
+## Guide
+
+For the settings or parameters, I recommend using these settings.
+
+![](https://huggingface.co/andite/pastel-mix/resolve/main/example-images/settings.png)
+
+```
+Sampler: DPM++ 2M Karras
+
+Steps: 20
+
+CFG Scale: 7
+
+Hires. Fix: On
+
+Upscaler: Latent (MUST!)
+
+Hires Steps: 20
+
+Denoising Strength: 0.
+```
+
+I prefer using 0.6 since it's the sweet spot of this model. If you can find a better setting for this model, then good for you lol.
+
+Latent upscaler is the best setting for me since it retains or enhances the pastel style. Other upscalers like Lanczos or Anime6B tends to smoothen them out, removing the pastel-like brushwork.
+
+Please use the **VAE** that I uploaded in this repository. It is from the [Waifu Diffusion](https://huggingface.co/hakurei/waifu-diffusion-v1-4/tree/main/vae) team. Credits to [haru](https://huggingface.co/hakurei) for letting me rename and upload it.
+
+## Tip (Optional)
+
+Putting mksks style in the beginning of the prompt can further influence the pastel-like style and make the output better. It is optional though, so it's up to you. You don't really need it.
+![](https://huggingface.co/andite/pastel-mix/resolve/main/example-images/xy_grid-0016-%20.png)
+
+```
+mksks style, masterpiece, best quality, upper body, 1girl, looking at viewer, red hair, medium hair, purple eyes, demon horns, black coat, indoors, dimly lit
+Negative prompt: lowres, ((bad anatomy)), ((bad hands)), text, missing finger, extra digits, fewer digits, blurry, ((mutated hands and fingers)), (poorly drawn face), ((mutation)), ((deformed face)), (ugly), ((bad proportions)), ((extra limbs)), extra face, (double head), (extra head), ((extra feet)), monster, logo, cropped, worst quality, low quality, normal quality, jpeg, humpbacked, long body, long neck, ((jpeg artifacts))
+Steps: 20, Sampler: DPM++ 2M Karras, CFG scale: 7, Seed: 580841049, Size: 448x640, Model hash: 7edc8e08, Model: pastelmix-fp32, Denoising strength: 0.6, Clip skip: 2, ENSD: 31337, Hires resize: 960x1280, Hires steps: 20, Hires upscaler: Latent
+```
+
+## Recipe
+
+Merging the models.
+
+| Model: A | Model: B | Weight | Base alpha | Merge Name |
+| --- | --- | --- | --- | --- |
+| [dpepmkmp](https://huggingface.co/closertodeath/dpepmkmp)  | [Tea](https://huggingface.co/andite/desserts) | 1,0.9,0.7,0.5,0.3,0.1,1,1,1,1,1,1,0,1,1,1,1,1,1,0.1,0.3,0.5,0.7,0.9,1 | 0 | dpeptea |
+| dpeptea | [basil-mix](https://huggingface.co/nuigurumi/basil_mix) | 1,1,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0 | 0 | dpeptea-basil |
+
+Merging the loras into the model.
+
+| Model | Lora | Weight | Merge Name |
+| --- | --- | --- | --- |
+| [dpeptea-basil](https://huggingface.co/closertodeath/dpepteahands3) | [Magic LORA](https://cdn.discordapp.com/attachments/1065289257243115540/1066346221876301845/MagicLORA.pt) | 0.3 | dpeptea-1 |
+| dpeptea-1 | [Jordan_3](https://huggingface.co/SatyamSSJ10/ConceptArt) | 1 | dpeptea-2 |
+| dpeptea-2 | [sttabi_v1.4-04](https://huggingface.co/dolphinz/stlora) | 0.5 | dpeptea-3 |
+| dpeptea-3 | [xlimo768](https://huggingface.co/closertodeath/ctdlora) | 0.6 | dpeptea-4 |
+| dpeptea-4 | [dpep 2 768](https://huggingface.co/closertodeath/ctdlora)| 0.35 | Pastel-Mix |
+
+## License
+
+This model is open access and available to all, with a CreativeML OpenRAIL-M license further specifying rights and usage.
+The CreativeML OpenRAIL License specifies: 
+
+1. You can't use the model to deliberately produce nor share illegal or harmful outputs or content.
+2. The authors claims no rights on the outputs you generate, you are free to use them and are accountable for their use which must not go against the provisions set in the license
+3. You may re-distribute the weights and use the model commercially and/or as a service. If you do, please be aware you have to include the same use restrictions as the ones in the license and share a copy of the CreativeML OpenRAIL-M to all your users (please read the license entirely and carefully)
+[Please read the full license here](https://huggingface.co/spaces/CompVis/stable-diffusion-license)
+
+-------
+
+## Big Thanks to
+
+The 東方Project AI community for their wonderful LORAs.
+
+- [Closertodeath](https://huggingface.co/closertodeath) for dpepmkmp model, and the loras: xlimo768, dpep 2 768
+- [dolphinz/sometimes#9353](https://huggingface.co/dolphinz) for tabi artstyle Lora.
+- [SatyamSSJ10](https://huggingface.co/SatyamSSJ10/ConceptArt) for Jordan_3 Lora.
+- randomaccessmemories#4004 for Magic Lora

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",
+  "_diffusers_version": "0.10.2",
+  "feature_extractor": [
+    null,
+    null
+  ],
+  "requires_safety_checker": null,
+  "safety_checker": [
+    null,
+    null
+  ],
+  "scheduler": [
+    "diffusers",
+    "DDIMScheduler"
+  ],
+  "text_encoder": [
+    "transformers",
+    "CLIPTextModel"
+  ],
+  "tokenizer": [
+    "transformers",
+    "CLIPTokenizer"
+  ],
+  "unet": [
+    "diffusers",
+    "UNet2DConditionModel"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKL"
+  ]
+}

pastel-waifu-diffusion.vae.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df3c506e51b7ee1d7b5a6a2bb7142d47d488743c96aa778afb0f53a2cdc2d38d
+size 404662241

pastelmix-better-vae-fp16.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfaf882b0a6dc34f392b12e9ee6c35f39ff794a98ef1a132eebd2873be1896ed
+size 2132878842

pastelmix-better-vae-fp16.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f0eaaa61ee6e5e2de88156f02ea0465a6ea787bef7c029a7072eda2ce42e4ac
+size 2132626071

pastelmix-better-vae-fp32.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:943a810f7538b32f9d81dc5adea3792c07219964c8a8734565931fcec90d762d
+size 4265349434

pastelmix-better-vae-fp32.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55042b85bcf0e75ebbe23be9f357a8ae3e71b90e39d73b3fafbe606fcd78d964
+size 4265097179

pastelmix-better-vae.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51d7ec27fd0c5322ff9b45e4dc9b4d3b41a2df462c35d85f0381025c7b493e77
+size 5984634839

pastelmix-better-vae.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:430c9b7350a1526b4afcb5ef875f3eb102ab9854e696853740126c3eddb53cf4
+size 5984232961

pastelmix-fp16.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84637d4980abdc8841204f458e3fac34b269ec7ca516942ea4d1a5bced8277df
+size 2132866293

pastelmix-fp16.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d01a68ae76f97506363f387f5f28bb564ad9e20924844fd5945e600b72d39e79
+size 2132626102

pastelmix-fp32.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8409a9f0c3cc285b5c4c68f7b727f5254f13b6758b6a443d86f92ad266d7f923
+size 4265336885

pastelmix-fp32.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:694fde43fcd0c6625e841bf76334b9b67bac9b04b41b6eafb53b1536b55f0644
+size 4265097210

pastelmix-lora.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59a342f468dd3c3e02200e175535ba3fda1c414d2d272f97e4ce95f88078bced
+size 151073137

pastelmix.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f17f6cd6953b5e012416e762676d139246511d64137a4a05530630bcc01d4180
+size 5984634903

pastelmix.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa818fcf2c6707083d27259ec7382a293d40201d65242e36f52773b159441d61
+size 5984232961

safety_checker/config.json

@@ -0,0 +1,171 @@
+{
+  "_name_or_path": "clip-vit-large-patch14/",
+  "architectures": [
+    "SafetyChecker"
+  ],
+  "initializer_factor": 1.0,
+  "logit_scale_init_value": 2.6592,
+  "model_type": "clip",
+  "projection_dim": 768,
+  "text_config": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "bos_token_id": 0,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "dropout": 0.0,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 2,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "quick_gelu",
+    "hidden_size": 768,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-05,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 77,
+    "min_length": 0,
+    "model_type": "clip_text_model",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 12,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 12,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 1,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "transformers_version": "4.21.0.dev0",
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "vocab_size": 49408
+  },
+  "text_config_dict": {
+    "hidden_size": 768,
+    "intermediate_size": 3072,
+    "num_attention_heads": 12,
+    "num_hidden_layers": 12
+  },
+  "torch_dtype": "float32",
+  "transformers_version": null,
+  "vision_config": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "dropout": 0.0,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "quick_gelu",
+    "hidden_size": 1024,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "image_size": 224,
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 4096,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-05,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "model_type": "clip_vision_model",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 16,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 24,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "patch_size": 14,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "transformers_version": "4.21.0.dev0",
+    "typical_p": 1.0,
+    "use_bfloat16": false
+  },
+  "vision_config_dict": {
+    "hidden_size": 1024,
+    "intermediate_size": 4096,
+    "num_attention_heads": 16,
+    "num_hidden_layers": 24,
+    "patch_size": 14
+  }
+}

safety_checker/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64b8393f1afd5a0c1ed2aa5f341fa7c08286839a48f3743162a76a2835c808bd
+size 1216067303

scheduler/scheduler_config.json

@@ -0,0 +1,14 @@
+{
+  "_class_name": "DDIMScheduler",
+  "_diffusers_version": "0.10.2",
+  "beta_end": 0.012,
+  "beta_schedule": "scaled_linear",
+  "beta_start": 0.00085,
+  "clip_sample": false,
+  "num_train_timesteps": 1000,
+  "prediction_type": "epsilon",
+  "set_alpha_to_one": false,
+  "skip_prk_steps": true,
+  "steps_offset": 1,
+  "trained_betas": null
+}

text_encoder/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "openai/clip-vit-large-patch14",
+  "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": "4.19.2",
+  "vocab_size": 49408
+}

text_encoder/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6db140be0809dfe495329bea5f224ac434ba9aa6193ef8e488fdfa20bba8399c
+size 492307041

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", "unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "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"}, "pad_token": "<|endoftext|>", "add_prefix_space": false, "do_lower_case": true, "model_max_length": 77, "name_or_path": "runwayml/stable-diffusion-v1-5", "special_tokens_map_file": "./special_tokens_map.json", "tokenizer_class": "CLIPTokenizer"}

unet/config.json

@@ -0,0 +1,41 @@
+{
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.10.2",
+  "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": 32,
+  "up_block_types": [
+    "UpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D"
+  ],
+  "upcast_attention": false,
+  "use_linear_projection": false
+}

unet/diffusion_pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d359a718711a28858d5ed825d2d927c874cde59b4b702a2d4ff736b262fa2d41
+size 3438366373

vae/config.json

@@ -0,0 +1,30 @@
+{
+  "_class_name": "AutoencoderKL",
+  "_diffusers_version": "0.10.2",
+  "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,
+  "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 sha256:8c0ca36788441539cc5f3c028a053de0783847bf000932e4e70421672f0eca18
+size 334711857