Duplicate from eienmojiki/Starry-XL-v5.2

Co-authored-by: Eien Mojiki 🍕 <[email protected]>

.gitattributes

@@ -0,0 +1,35 @@
+*.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
+*.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

README.md

@@ -0,0 +1,122 @@
+---
+license: other
+license_name: faipl-1.0-sd
+license_link: https://freedevproject.org/faipl-1.0-sd
+language:
+- en
+library_name: diffusers
+pipeline_tag: text-to-image
+tags:
+- anime
+- stable-diffusion-xl
+- safetensors
+---
+
+<style>
+  .title-container {
+    display: flex;
+    justify-content: center;
+    align-items: center;
+    height: 80vh; /* Adjust this value to position the title vertically */
+  }
+  .title {
+    font-size: 1.5em;
+    text-align: center;
+    color: #333;
+    font-family: 'Helvetica Neue', sans-serif;
+    text-transform: uppercase;
+    letter-spacing: 0.1em;
+    padding: 0.5em 0;
+    background: transparent;
+  }
+  .title span {
+    background: -webkit-linear-gradient(45deg, #FFBF00, #F28C28);
+    -webkit-background-clip: text;
+    -webkit-text-fill-color: transparent;
+  }
+</style>
+
+<h1 class="title"><span>Starry XL 5.2</span></h1>
+
+## Model Information
+- Developed by: [kitarz](https://civitai.com/user/kitarz)
+- Funded by: kitarz
+- Model type: SDXL 1.0
+- Finetuned from: [Kohaku-XL Epsilon](https://civitai.com/models/399873/kohaku-xl-epsilon)
+- License: Fair AI Public License 1.0-SD
+
+> [!WARNING]
+> This is a not the offical model page of this model's author
+
+## Usages
+🪄 **Try Starry XL Demo here:** https://huggingface.co/spaces/eienmojiki/StarryXL-Demo
+
+> Starry is based on epsilon, and during training, the caption are overall close to Kohaku epsilon, so the overall usage is the same
+
+### Artist wildcard
+**There is a wildcard for 600 artists here:** [starry_aritst_600_list](https://civitai.com/api/download/models/499498?type=Training%20Data)
+
+for other artists and characters, please use the existing list from Kohaku Epsilon. https://civitai.com/api/download/models/445973?type=Training%20Data
+
+> [!IMPORTANT]
+> **Note that Starry requires high accuracy in artist names, so ensure there are no spelling errors and use the correct artist/character tags.**
+
+### Prompt format
+```
+<1girl/1boy/1other/...>, 
+<character>, <series>, <artists>, 
+<general tags>,
+<quality tags>, <year tags>, <meta tags>, <rating tags>
+```
+- Quality tags: masterpiece, best quality, great quality, good quality, normal quality, low quality, worst quality
+- Rating tags: safe, sensitive, nsfw, explicit
+- Date tags: newest, recent, mid, early, old
+
+### Recommended Negative Prompt
+- **Long**
+```
+bad anatomy,blurry,(worst quality:1.8),low quality,hands bad,face bad,(normal quality:1.3),bad hands,mutated hands and fingers,extra legs,extra arms,duplicate,cropped,text,jpeg,artifacts,signature,watermark,username,blurry,artist name,trademark,title,multiple view,Reference sheet,long body,multiple breasts,mutated,bad anatomy,disfigured,bad proportions,duplicate,bad feet,artist name,ugly,text font ui,missing limb,monochrome,  
+```
+- **Short**
+```
+nsfw, lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name,
+```
+
+### Style Select
+You can directly use artist's prompt to generate image.
+```
+1girl,momoi \(blue archive\), blue archive,
+```
+```
+{style},
+```
+```
+solo, headphones, halo, pink halo, white jacket, short hair, bow, shirt, necktie, white background, white shirt, blue necktie, fake animal ears, animal ears, pink bow, collared shirt, simple background, pink eyes, blonde hair, animal ear headphones, looking at viewer, hair bow, jacket,newest, masterpiece, best quality,  absurdres, highres, 
+```
+![img1](https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/9593866e-4471-4e8d-91a9-bdaead3d6f3b/width=525/9593866e-4471-4e8d-91a9-bdaead3d6f3b.jpeg)
+![img2](https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/def8091f-ab81-495e-92f1-640322d2e879/width=525/def8091f-ab81-495e-92f1-640322d2e879.jpeg)
+![img3](https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/2150ba87-7a69-4968-961e-733ce807bcba/width=525/2150ba87-7a69-4968-961e-733ce807bcba.jpeg)
+![img4](https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/964ac69e-29db-4e03-adc3-beb3fa794a8c/width=525/964ac69e-29db-4e03-adc3-beb3fa794a8c.jpeg)
+![img5](https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/964ac69e-29db-4e03-adc3-beb3fa794a8c/width=525/964ac69e-29db-4e03-adc3-beb3fa794a8c.jpeg)
+![img6](https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/964ac69e-29db-4e03-adc3-beb3fa794a8c/width=525/964ac69e-29db-4e03-adc3-beb3fa794a8c.jpeg)
+
+### Enhance your generation
+1. You can use [DanTagGen](https://github.com/KohakuBlueleaf/z-a1111-sd-webui-dtg) to generate images with a strong style from an artist
+> Try DanTagGen on HuggingFace: https://huggingface.co/spaces/KBlueLeaf/DTG-demo
+```
+1girl,{style}, {dtg expand} newest, masterpiece, best quality,  absurdres, highres,   
+```
+
+2. Artists Combination
+
+Combining multiple artists is highly recommended, and you can use the artist list to try different orders and combinations. *In fact, you can use the famous nai3 artist prompts to combine styles directly. (This is not a simple nai3 distillation, it uses artist prompts for style combine)*
+```
+(ningen mame:0.9), ciloranko, sho \(sho lwlw\), (tianliang duohe fangdongye:0.8), ask \(askzy\), wlop, 
+```
+![img7](https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/7c6bbb3f-7b2e-4b33-934c-3670395130d2/width=525/7c6bbb3f-7b2e-4b33-934c-3670395130d2.jpeg)
+![img8](https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/92381267-f5c8-4acb-ab49-df1cd5e9b1d6/width=525/92381267-f5c8-4acb-ab49-df1cd5e9b1d6.jpeg)
+
+## License
+This model is released under Fair-AI-Public-License-1.0-SD
+
+Please check this website for more information: Freedom of Development (freedevproject.org)

model_index.json

@@ -0,0 +1,41 @@
+{
+  "_class_name": "StableDiffusionXLPipeline",
+  "_diffusers_version": "0.27.2",
+  "feature_extractor": [
+    null,
+    null
+  ],
+  "force_zeros_for_empty_prompt": true,
+  "image_encoder": [
+    null,
+    null
+  ],
+  "scheduler": [
+    "diffusers",
+    "EulerDiscreteScheduler"
+  ],
+  "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 +1,21 @@
+{
+  "_class_name": "EulerDiscreteScheduler",
+  "_diffusers_version": "0.27.2",
+  "beta_end": 0.012,
+  "beta_schedule": "scaled_linear",
+  "beta_start": 0.00085,
+  "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,
+  "sigma_max": null,
+  "sigma_min": null,
+  "skip_prk_steps": true,
+  "steps_offset": 1,
+  "timestep_spacing": "leading",
+  "timestep_type": "discrete",
+  "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": "float16",
+  "transformers_version": "4.38.1",
+  "vocab_size": 49408
+}

text_encoder/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46736ac2893adf732d2297f307f338db170d71eabb952027301e318e1e000481
+size 246144152

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": "float16",
+  "transformers_version": "4.38.1",
+  "vocab_size": 49408
+}

text_encoder_2/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9775d9ced567f082837cffc3ffafb215f72e466b3d9dea185bb3664949487bf
+size 1389382176

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|>"
+}

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": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "!",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "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": 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": "!",
+  "tokenizer_class": "CLIPTokenizer",
+  "unk_token": "<|endoftext|>"
+}

unet/config.json

@@ -0,0 +1,72 @@
+{
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.27.2",
+  "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": false,
+  "use_linear_projection": true
+}

unet/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51fed02b11be065648acbe9bf2cdcc3729855115bd7ddee323464862085f1526
+size 5135149760

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": 1024,
+  "scaling_factor": 0.13025,
+  "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 sha256:6353737672c94b96174cb590f711eac6edf2fcce5b6e91aa9d73c5adc589ee48
+size 167335342