Upload 14 files

README.md

@@ -1,3 +1,107 @@
 ---
+language:
+- en
 license: creativeml-openrail-m
+thumbnail: "https://huggingface.co/Guizmus/SDArt_UnmythicalCreatures768/resolve/main/showcase.jpg"
+tags:
+- stable-diffusion
+- text-to-image
+- image-to-image
 ---
+# SDArt : Un-Mythical Creatures (version based on 2.1 768px)
+
+![Showcase](https://huggingface.co/Guizmus/SDArt_UnmythicalCreatures768/resolve/main/showcase.jpg)
+
+## Theme
+
+[Excerpt from “Chronicles of Curiosity: Professor Lawrence's Field Guide”]
+
+> It was a creature of un-mythical origins, imbued by the forest itself. Its body was sleek and agile, with fur the color of a moonless deep blue midnight sky and eyes that glowed like embers in the darkness. But what truly set it apart were the petals that bloomed from its back, opening and closing like a flower that only blossomed at night.
+> The creature's habitat was the forest floor, where it moved with an effortless grace that defied the laws of physics. Its body seemed to flow like water over the tangled roots and fallen leaves, its every movement a thing of hypnotic beauty. It had a natural affinity for the plants around it, but not in the way that one might expect. Rather than using them for sustenance, the creature communed with them, drawing strength from the very life force that pulsed through their veins.
+> And so it was that the creature of un-mythical origins, born from the very essence of the earth itself, came to be known by a name whispered on the lips of those who had glimpsed its rare presence - Nightshade.
+
+🐉 Delve into mythology and create a brand new creature that doesn't exist in legends or myths. Give these creatures of non-legend a new lease of life! 🦞
+
+**Challenges:**
+* At least one feature inspired by a real-life animal or plant.
+* Incorporate an element of the creature's habitat into its design.
+* Give your creature a name.
+
+*What's the next entry in the Field Guide?*
+
+
+## Model description 
+
+This is a model related to the "Challenge of the WeekEnd" contest on [Stable Diffusion discord](https://discord.gg/stablediffusion).
+
+I try to make a model out of all the submission for people to continue enjoy the theme after the even, and see a little of their designs in other people's creations. The token stays "SDArt" and I balance the learning on the low side, so that it doesn't just replicate creations.
+
+The total dataset is made of 31 pictures. It was trained on [Stable diffusion 2.1 768px](https://huggingface.co/stabilityai/stable-diffusion-2-1). I used [EveryDream](https://github.com/victorchall/EveryDream2trainer) to do the training, 100 total repeat per picture. The pictures were tagged using the token "SDArt", and an arbitrary token I choose. The dataset is provided below, as well as a list of usernames and their corresponding token.
+
+The recommended sampling is k_Euler_a or DPM++ 2M Karras on 20 steps, CFGS 7.5 .
+
+[The model is also available here](https://huggingface.co/Guizmus/SDArt_UnmythicalCreatures) in a version trained on 1.5 as a base.
+
+## Trained tokens
+
+* SDArt
+* rcn
+* bnp
+* reba
+* aten
+* cous
+* aved
+* omd
+* ront
+* kuro
+* asot
+* psst
+* rolf
+* muc
+* kts
+* utm
+* vaw
+* mss
+* guin
+* crit
+* mlas
+* isch
+* phol
+* dds
+* acu
+* pte
+* rean
+* soca
+* sohn
+* sown
+* ssh
+* stix
+
+## Download links
+
+[SafeTensors](https://huggingface.co/Guizmus/SDArt_UnmythicalCreatures768/resolve/main/SDArt_UnmythicalCreatures768.safetensors)
+
+[Config (yaml)](https://huggingface.co/Guizmus/SDArt_UnmythicalCreatures768/resolve/main/SDArt_UnmythicalCreatures768.yaml)
+
+[Dataset](https://huggingface.co/Guizmus/SDArt_UnmythicalCreatures768/resolve/main/dataset.zip)
+
+## 🧨 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 = "Guizmus/SDArt_UnmythicalCreatures768"
+pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)
+pipe = pipe.to("cuda")
+
+prompt = "SDArt kts"
+image = pipe(prompt).images[0]
+
+image.save("./SDArt.png")
+```

SDArt_UnmythicalCreatures768.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3cb0ded9bcb39d9c2f49ff53c2f212ea5b2f6008e57ddcaa46bdbed48b335a8c
+size 2580068696

model_index.json

@@ -0,0 +1,33 @@
+{
+  "_class_name": "StableDiffusionPipeline",
+  "_diffusers_version": "0.13.0",
+  "feature_extractor": [
+    null,
+    null
+  ],
+  "requires_safety_checker": null,
+  "safety_checker": [
+    null,
+    null
+  ],
+  "scheduler": [
+    "diffusers",
+    "DDPMScheduler"
+  ],
+  "text_encoder": [
+    "transformers",
+    "CLIPTextModel"
+  ],
+  "tokenizer": [
+    "transformers",
+    "CLIPTokenizer"
+  ],
+  "unet": [
+    "diffusers",
+    "UNet2DConditionModel"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKL"
+  ]
+}

scheduler/scheduler_config.json

@@ -0,0 +1,16 @@
+{
+  "_class_name": "DDPMScheduler",
+  "_diffusers_version": "0.13.0",
+  "beta_end": 0.012,
+  "beta_schedule": "scaled_linear",
+  "beta_start": 0.00085,
+  "clip_sample": false,
+  "clip_sample_range": 1.0,
+  "num_train_timesteps": 1000,
+  "prediction_type": "v_prediction",
+  "set_alpha_to_one": false,
+  "skip_prk_steps": true,
+  "steps_offset": 1,
+  "trained_betas": null,
+  "variance_type": "fixed_small"
+}

text_encoder/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "F:\\AI\\Data\\Diffusers\\stable-diffusion-2-1",
+  "architectures": [
+    "CLIPTextModel"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "dropout": 0.0,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_size": 1024,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 77,
+  "model_type": "clip_text_model",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 23,
+  "pad_token_id": 1,
+  "projection_dim": 512,
+  "torch_dtype": "float32",
+  "transformers_version": "4.27.1",
+  "vocab_size": 49408
+}

text_encoder/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:173c4a241ed5e4163446246685fced70cbc3bff3c45885b1266227460b0a9020
+size 1361677143

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

tokenizer/tokenizer_config.json

@@ -0,0 +1,34 @@
+{
+  "add_prefix_space": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "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|>",
+  "special_tokens_map_file": "./special_tokens_map.json",
+  "tokenizer_class": "CLIPTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "use_fast": false
+}

unet/config.json

@@ -0,0 +1,56 @@
+{
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.13.0",
+  "_name_or_path": "F:\\AI\\Data\\Diffusers\\stable-diffusion-2-1",
+  "act_fn": "silu",
+  "attention_head_dim": [
+    5,
+    10,
+    20,
+    20
+  ],
+  "block_out_channels": [
+    320,
+    640,
+    1280,
+    1280
+  ],
+  "center_input_sample": false,
+  "class_embed_type": null,
+  "conv_in_kernel": 3,
+  "conv_out_kernel": 3,
+  "cross_attention_dim": 1024,
+  "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,
+  "mid_block_type": "UNetMidBlock2DCrossAttn",
+  "norm_eps": 1e-05,
+  "norm_num_groups": 32,
+  "num_class_embeds": null,
+  "only_cross_attention": false,
+  "out_channels": 4,
+  "projection_class_embeddings_input_dim": null,
+  "resnet_time_scale_shift": "default",
+  "sample_size": 96,
+  "time_cond_proj_dim": null,
+  "time_embedding_type": "positional",
+  "timestep_post_act": null,
+  "up_block_types": [
+    "UpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D"
+  ],
+  "upcast_attention": true,
+  "use_linear_projection": true
+}

unet/diffusion_pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a9ccb5888d6e53a0e7215a6697e82200ca5186202fe791a0b3c94d3b8dd1cf4
+size 3463923045

vae/config.json

@@ -0,0 +1,31 @@
+{
+  "_class_name": "AutoencoderKL",
+  "_diffusers_version": "0.13.0",
+  "_name_or_path": "F:\\AI\\Data\\Diffusers\\stable-diffusion-2-1",
+  "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": 768,
+  "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:eb128b1f37e0c381c440128b217d29613b3e08b9e4ea7f20466424145ba538b0
+size 167402961