thanks to yodayo-ai ❤

.gitattributes

@@ -33,3 +33,13 @@ saved_model/**/* 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
+samples/sample-001.png filter=lfs diff=lfs merge=lfs -text
+samples/sample-002.png filter=lfs diff=lfs merge=lfs -text
+samples/sample-003.png filter=lfs diff=lfs merge=lfs -text
+samples/sample-004.png filter=lfs diff=lfs merge=lfs -text
+samples/sample-005.png filter=lfs diff=lfs merge=lfs -text
+samples/sample-006.png filter=lfs diff=lfs merge=lfs -text
+samples/sample-007.png filter=lfs diff=lfs merge=lfs -text
+samples/sample-008.png filter=lfs diff=lfs merge=lfs -text
+samples/sample-009.png filter=lfs diff=lfs merge=lfs -text
+samples/sample-010.png filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,239 @@
+---
+license: other
+license_name: faipl-1.0-sd
+license_link: https://freedevproject.org/faipl-1.0-sd/
+language:
+- en
+tags:
+  - text-to-image
+  - stable-diffusion
+  - safetensors
+  - stable-diffusion-xl
+base_model: cagliostrolab/animagine-xl-3.1
+widget:
+- text: 1girl, green hair, sweater, looking at viewer, upper body, beanie, outdoors, night, turtleneck, masterpiece, best quality, very aesthetic, absurdres
+  parameter:
+    negative_prompt: nsfw, low quality, worst quality, very displeasing, 3d, watermark, signature, ugly, poorly drawn
+  example_title: 1girl
+- text: 1boy, male focus, green hair, sweater, looking at viewer, upper body, beanie, outdoors, night, turtleneck, masterpiece, best quality, very aesthetic, absurdres
+  parameter: 
+    negative_prompt: nsfw, low quality, worst quality, very displeasing, 3d, watermark, signature, ugly, poorly drawn
+  example_title: 1boy
+---
+
+<style>
+
+body {
+  display: flex;
+  align-items: center;
+  justify-content: center;
+  height: 100vh;
+  margin: 0;
+  font-family: Arial, sans-serif;
+  background-color: #f4f4f9;
+  overflow: auto;
+}
+
+.container {
+  display: flex;
+  flex-direction: column;
+  align-items: center;
+  justify-content: center;
+  width: 100%;
+  padding: 20px;
+}
+
+.title-container {
+  display: flex;
+  flex-direction: column;
+  justify-content: center;
+  align-items: center;
+  padding: 1em;
+  border-radius: 10px;
+}
+
+.title {
+  font-size: 3em;
+  font-family: 'Montserrat', sans-serif;
+  text-align: center;
+  font-weight: bold;
+}
+
+.title span {
+  background: -webkit-linear-gradient(45deg, #ff8e8e, #ffb6c1, #ff69b4);
+  -webkit-background-clip: text;
+  -webkit-text-fill-color: transparent;
+}
+
+.gallery {
+  display: grid;
+  grid-template-columns: repeat(5, 1fr);
+  gap: 10px;
+}
+
+.gallery img {
+  width: 100%;
+  height: auto;
+  margin-top: 0px;
+  margin-bottom: 0px;
+  border-radius: 10px;
+  box-shadow: 0 4px 8px rgba(0, 0, 0, 0.2);
+  transition: transform 0.3s;
+}
+
+.gallery img:hover {
+  transform: scale(1.05);
+}
+
+.note {
+  font-size: 1em;
+  opacity: 50%;
+  text-align: center;
+  margin-top: 20px;
+  color: #555;
+}
+  
+</style>
+
+<div class="container">
+  <div class="title-container">
+    <div class="title"><span>Holodayo XL 2.1</span></div>
+  </div>
+  <div class="gallery">
+    <img src="https://huggingface.co/yodayo-ai/holodayo-xl-2.1/resolve/main/samples/sample-001.png" alt="Image 1">
+    <img src="https://huggingface.co/yodayo-ai/holodayo-xl-2.1/resolve/main/samples/sample-002.png" alt="Image 2">
+    <img src="https://huggingface.co/yodayo-ai/holodayo-xl-2.1/resolve/main/samples/sample-003.png" alt="Image 3">
+    <img src="https://huggingface.co/yodayo-ai/holodayo-xl-2.1/resolve/main/samples/sample-004.png" alt="Image 4">
+    <img src="https://huggingface.co/yodayo-ai/holodayo-xl-2.1/resolve/main/samples/sample-005.png" alt="Image 5">
+    <img src="https://huggingface.co/yodayo-ai/holodayo-xl-2.1/resolve/main/samples/sample-006.png" alt="Image 6">
+    <img src="https://huggingface.co/yodayo-ai/holodayo-xl-2.1/resolve/main/samples/sample-007.png" alt="Image 7">
+    <img src="https://huggingface.co/yodayo-ai/holodayo-xl-2.1/resolve/main/samples/sample-008.png" alt="Image 8">
+    <img src="https://huggingface.co/yodayo-ai/holodayo-xl-2.1/resolve/main/samples/sample-009.png" alt="Image 9">
+    <img src="https://huggingface.co/yodayo-ai/holodayo-xl-2.1/resolve/main/samples/sample-010.png" alt="Image 10">
+  </div>
+  <div class="note">
+    Drag and drop each image to <a href="https://huggingface.co/spaces/Linaqruf/pnginfo" target="_blank">this link</a> or use ComfyUI to get the metadata.
+  </div>
+</div>
+
+## Overview
+
+**Holodayo XL 2.1** is the latest version of the [Yodayo Holodayo XL](https://yodayo.com/models/1cafd6f8-8fc6-4282-b8f8-843935acbfe8) series, following the previous iteration, [Holodayo XL 1.0](https://yodayo.com/models/1cafd6f8-8fc6-4282-b8f8-843935acbfe8/?modelversion=2349b302-a726-44ba-933b-e3dc4631a95b). This open-source model is built upon Animagine XL V3, a specialized SDXL model designed for generating high-quality anime-style artwork. Holodayo XL 2.1 has undergone additional fine-tuning and optimization to focus specifically on generating images that accurately represent the visual style and aesthetics of the Virtual Youtuber franchise. 
+
+Holodayo XL 2.1 was trained to fix everything wrong in [Holodayo XL 2.0](https://yodayo.com/models/1cafd6f8-8fc6-4282-b8f8-843935acbfe8/?modelversion=ca4bf1aa-0baf-44cd-8ee9-8f4c6bba89c8), such as bad hands, bad anatomy, catastrophic forgetting due to the text encoder being trained during the fine-tuning phase, and an overexposed art style by decreasing the aesthetic datasets.
+
+## Model Details
+- **Developed by**: [Linaqruf](https://github.com/Linaqruf)
+- **Model type**: Diffusion-based text-to-image generative model
+- **Model Description**: Holodayo XL 2.1, the latest in the Yodayo Holodayo XL series, is an open-source model built on Animagine XL V3. Fine-tuned for high-quality Virtual Youtuber anime-style art generation.
+- **License**: [Fair AI Public License 1.0-SD](https://freedevproject.org/faipl-1.0-sd/)
+- **Finetuned from model**: [Animagine XL 3.1](https://huggingface.co/cagliostrolab/animagine-xl-3.1)
+
+## Supported Platform
+1. Use this model in our platform: [![Open In Spaces](https://img.shields.io/badge/Generate%20in%20Yodayo-141414?style=for-the-badge&logo=data:image/png;base64,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)](https://yodayo.com/models/1cafd6f8-8fc6-4282-b8f8-843935acbfe8/?modelversion=6862d809-0cbc-4fe0-83dc-9206d60b0698)
+2. Use it in [`ComfyUI`](https://github.com/comfyanonymous/ComfyUI) or [`Stable Diffusion Webui`](https://github.com/AUTOMATIC1111/stable-diffusion-webui)
+3. Use it with 🧨 `diffusers`
+
+## 🧨 Diffusers Installation
+
+First install the required libraries:
+
+```bash
+pip install diffusers transformers accelerate safetensors --upgrade
+```
+
+Then run image generation with the following example code:
+
+```python
+import torch
+from diffusers import StableDiffusionXLPipeline
+
+pipe = StableDiffusionXLPipeline.from_pretrained(
+    "yodayo-ai/holodayo-xl-2.1", 
+    torch_dtype=torch.float16, 
+    use_safetensors=True,
+    custom_pipeline="lpw_stable_diffusion_xl",
+    add_watermarker=False,
+    variant="fp16"
+)
+pipe.to('cuda')
+
+prompt = "1girl, nakiri ayame, nakiri ayame \(1st costume\), hololive, solo, upper body, v, smile, looking at viewer, outdoors, night, masterpiece, best quality, very aesthetic, absurdres"
+negative_prompt = "nsfw, (low quality, worst quality:1.2), very displeasing, 3d, watermark, signature, ugly, poorly drawn"
+
+image = pipe(
+    prompt, 
+    negative_prompt=negative_prompt,
+    width=832,
+    height=1216, 
+    guidance_scale=7,
+    num_inference_steps=28
+).images[0]
+
+image.save("./waifu.png")
+```
+
+## Usage Guidelines
+
+### Tag Ordering
+
+For optimal results, it's recommended to follow the structured prompt template because we train the model like this:
+
+```
+1girl/1boy, character name, from which series, by which artists, everything else in any order.
+```
+
+### Special Tags
+
+Holodayo XL 2.1 inherits special tags from Animagine XL 3.1 to enhance image generation by steering results toward quality, rating, creation date, and aesthetic. This inheritance ensures that Holodayo XL 2.1 can produce high-quality, relevant, and aesthetically pleasing images. While the model can generate images without these tags, using them helps achieve better results.
+
+- **Quality tags**: masterpiece, best quality, great quality, good quality, normal quality, low quality, worst quality  
+- **Rating tags**: safe, sensitive, nsfw, explicit  
+- **Year tags**: newest, recent, mid, early, oldest  
+- **Aesthetic tags**: very aesthetic, aesthetic, displeasing, very displeasing
+
+### Recommended Settings
+
+To guide the model towards generating high-aesthetic images, use the following recommended settings:
+
+- **Negative prompts**: 
+```
+nsfw, (low quality, worst quality:1.2), very displeasing, 3d, watermark, signature, ugly, poorly drawn
+```
+- **Positive prompts**:
+```
+masterpiece, best quality, very aesthetic, absurdres
+```
+- **Classifier-Free Guidance (CFG) Scale**: should be around 5 to 7; 10 is fried, >12 is deep-fried.
+- **Sampling steps**: should be around 25 to 30; 28 is the sweet spot.
+- **Sampler**: Euler Ancestral (Euler a) is highly recommended.
+- **Supported resolutions**:
+```
+1024 x 1024, 1152 x 896, 896 x 1152, 1216 x 832, 832 x 1216, 1344 x 768, 768 x 1344, 1536 x 640, 640 x 1536
+```
+
+## Training 
+
+These are the key hyperparameters used during training:
+
+| Feature                       | Pretraining               | Finetuning                      |
+|-------------------------------|----------------------------|---------------------------------|
+| **Hardware**                  | 2x H100 80GB PCIe          | 2x A100 80GB PCIe               |
+| **Batch Size**                | 64                         | 48                              |
+| **Gradient Accumulation Steps** | 2                        | 1                               |
+| **Noise Offset**              | None                       | 0.0357                          |
+| **Epochs**                    | 10                         | 10                              |
+| **UNet Learning Rate**        | 7.5e-6                       | 7.5e-6                         |
+| **Text Encoder Learning Rate** | 3.75e-6                   | None                            |
+| **Optimizer**                 | AdamW8bit                  | Adafactor                       |
+| **Optimizer Args**            | Weight Decay: 0.1, Betas: (0.9, 0.99) | Scale Parameter: False, Relative Step: False, Warmup Init: False |
+| **Scheduler**                 | Constant with Warmups      | Constant with Warmups           |
+| **Warmup Steps**              | 0.5%                       | 0.5%                            |
+
+## License
+
+Holodayo XL 2.1 falls under [Fair AI Public License 1.0-SD](https://freedevproject.org/faipl-1.0-sd/) license, which is compatible with Stable Diffusion models’ license. Key points:
+
+1. **Modification Sharing:** If you modify Holodayo XL 2.1, you must share both your changes and the original license.
+2. **Source Code Accessibility:** If your modified version is network-accessible, provide a way (like a download link) for others to get the source code. This applies to derived models too.
+3. **Distribution Terms:** Any distribution must be under this license or another with similar rules.

holodayo-xl-2.1.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e51f7a220bb18fc5a2365b6f8871a34163cb8549529cc1f2cdc9fd5816c9fd88
+size 6938225848

model_index.json

@@ -0,0 +1,41 @@
+{
+  "_class_name": "StableDiffusionXLPipeline",
+  "_diffusers_version": "0.28.0",
+  "feature_extractor": [
+    null,
+    null
+  ],
+  "force_zeros_for_empty_prompt": true,
+  "image_encoder": [
+    null,
+    null
+  ],
+  "scheduler": [
+    "diffusers",
+    "EulerAncestralDiscreteScheduler"
+  ],
+  "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 +1,19 @@
+{
+  "_class_name": "EulerAncestralDiscreteScheduler",
+  "_diffusers_version": "0.28.0",
+  "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",
+  "rescale_betas_zero_snr": false,
+  "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": "4.41.1",
+  "vocab_size": 49408
+}

text_encoder/model.fp16.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c596edaa5341f944b404de48ba8a6aa2882de4a2a4a158796a662c28e3f47395
+size 246144152

text_encoder/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a5f47400d43eee1d1716bf53f652ec67025cc26a401860d4db4fa4e22eb8a62
+size 492265168

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": "4.41.1",
+  "vocab_size": 49408
+}

text_encoder_2/model.fp16.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a25bd599acd8be7f2e61f071e052b7fe3d111274a019884020391b45e34a464
+size 1389382176

text_encoder_2/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b168fb9761bffe7bcd816c82904e92138775777a161447e5c4c84ed0733ad57
+size 2778702264

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 +1,30 @@
+{
+  "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": true,
+      "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|>"
+}

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 +1,38 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "!",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49406": {
+      "content": "<|startoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49407": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "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": "!",
+  "tokenizer_class": "CLIPTokenizer",
+  "unk_token": "<|endoftext|>"
+}

unet/config.json

@@ -0,0 +1,72 @@
+{
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.28.0",
+  "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": "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": 2816,
+  "resnet_out_scale_factor": 1.0,
+  "resnet_skip_time_act": false,
+  "resnet_time_scale_shift": "default",
+  "reverse_transformer_layers_per_block": null,
+  "sample_size": 128,
+  "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,
+    2,
+    10
+  ],
+  "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 sha256:13fa6a504fdaaa4b94bf94ae072d0f36af47b3eed7cc40b364aa527235993a86
+size 5135149760

unet/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7545fcb7019b081abd6381b9fb00c6fbf7565adde582ec3b04ae2966623cbf60
+size 10270077736

vae/config.json

@@ -0,0 +1,34 @@
+{
+  "_class_name": "AutoencoderKL",
+  "_diffusers_version": "0.28.0",
+  "_name_or_path": "madebyollin/sdxl-vae-fp16-fix",
+  "act_fn": "silu",
+  "block_out_channels": [
+    128,
+    256,
+    512,
+    512
+  ],
+  "down_block_types": [
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D"
+  ],
+  "force_upcast": false,
+  "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": 0.13025,
+  "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 sha256:78f6189c8492013e3cac81637a1f657f790a237387f8a9dfd6bfa5fee28eb646
+size 334643268

vae/diffusion_pytorch_model.safetensors

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