Upload 17 files

.gitattributes

@@ -32,3 +32,4 @@ 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
+showcase.jpg filter=lfs diff=lfs merge=lfs -text

README.md

@@ -2,7 +2,7 @@
 language:
 - en
 license: creativeml-openrail-m
-thumbnail: "https://huggingface.co/Guizmus/PoW_UNDERWATER-WORLDS/resolve/main/showcase.jpg"
+thumbnail: "https://huggingface.co/Guizmus/SDArt_underwaterworlds/resolve/main/showcase.jpg"
 tags:
 - stable-diffusion
 - text-to-image
@@ -10,69 +10,85 @@ tags:
 ---
 # PoW : UNDERWATER WORLDS
 
-![Showcase](https://huggingface.co/Guizmus/PoW_UNDERWATER-WORLDS/resolve/main/showcase.jpg)
+![Showcase](https://huggingface.co/Guizmus/SDArt_underwaterworlds/resolve/main/showcase.jpg)
 
 ## Theme
 
+Deep in the heart of the ocean, there was a realm of magic and mystery, where the creatures were of an unearthly nature. Lyra, a young and courageous mermaid, was determined to explore every space of this ethereal world. With each stroke of her powerful tail, she descended deeper into the abyssal unknown, encountering peculiar and breathtaking creatures - towering sea serpents with magnificent scales, colossal jellyfish that radiated with a vibrant light, and shoals of resplendent fish that swam in mesmerizing patterns.
+
+As Lyra delved deeper, an expansive gateway of coral and seaweed emerged before her. Suddenly, she was surrounded by a swarm of bioluminescent seahorses that darted around her, their neon lights illuminating the shadows. Lyra couldn't help but smile at the sight, marveling at their beauty. After a moment, she composed herself and looked around. She was in disbelief at what lay before here - an underwater city of pure enchantment and intrigue.
+
+The buildings were made of elegant stonework, adorned with an array of carvings depicting creatures beyond her wildest dreams. The walls were draped in a soft, radiant moss that illuminated the entire city like a cloudless starry night sky. The interplay of light and shadow danced in a hypnotic rhythm that left Lyra in a state of awe. She felt as if she had discovered a world that was both ancient and new, an underwater world of unexplored possibilities.
+
+***Bring the magic of the underwater worlds to life***
+
+How would you capture the wonder and fluidity of the ocean depths?
+
+What kind of unique underwater creatures or plants would Lyra have seen?
+
+If you could explore one specific area of Lyra's world, what would it be?Remember to stay hydrated!
+
 ## Model description 
 
 This is a model related to the "Picture of the Week" contest on Stable Diffusion discord.
 
-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 "PoW Style" and I balance the learning on the low side, so that it doesn't just replicate creations.
+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 38 pictures. It was trained on [Stable diffusion 1.5](https://huggingface.co/runwayml/stable-diffusion-v1-5). 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 total dataset is made of 38 pictures. It was trained on [Stable diffusion 1.5](https://huggingface.co/runwayml/stable-diffusion-v1-5). I used [EveryDream](https://github.com/victorchall/EveryDream2trainer) to do the training, 100 total repeat per picture over 50 epochs. The pictures were tagged using the token "PoW Style", and the username on discord followed by the userID. The dataset is provided below.
 
 The recommended sampling is k_Euler_a or DPM++ 2M Karras on 20 steps, CFGS 7.5 .
 
 ## Trained tokens
 
-* PoW Style
-* sometimes8916
-* 526christian2526
-* Akumetsu9719982
-* AndreTheApache9587
-* bitspirit31653
-* bWm_nubby6416
-* crazykazoo2431
-* Eppinette-Chi6220
-* espasmo9486
-* flowwolf4607
-* Guizmus7459
-* H20_Dancing8979
-* Horvallis7915
-* Jeremy6194
-* JRW19948464
-* Junglerally3955
-* Max Headroom6734
-* Meezy1963
-* millennium_gun6377
-* Munkyfoot7944
-* Nerfgun37508
-* NicoGJ2781
-* NoOfTheBeast8209
-* Omnia2931
-* owleye1290
-* Phaff1970
-* piscabo8649
-* Ras6722
-* ResidentChiefNZ6989
-* Rhapsody8685
-* Satyam_SSJ107387
-* tazi2574
-* Trash--Panda6213
-* valanya6869
-* vcm077281
-* Vil0404
-* wpatzz5836
-* xThIsIsBoToXx8765
+* SDArt
+* appt
+* ohwx
+* asr
+* aten
+* fcu
+* chor
+* cpec
+* pfa
+* kprc
+* kuro
+* asot
+* elis
+* sill
+* exe
+* bsp
+* grl
+* hap
+* byes
+* lpg
+* yler
+* avel
+* vaw
+* zaki
+* ohn
+* guin
+* vini
+* pz
+* crit
+* shma
+* doa
+* sks
+* szn
+* phol
+* utm
+* uy
+* dds
+* pte
+* oxi
+* ynna
 
 ## Download links
 
-[SafeTensors](https://huggingface.co/Guizmus/PoW_UNDERWATER-WORLDS/resolve/main/PoWStyle-UnderwaterWorlds.safetensors)
+[SafeTensors](https://huggingface.co/Guizmus/SDArt_underwaterworlds/resolve/main/SDArt_underwaterworlds.safetensors)
 
-[CKPT](https://huggingface.co/Guizmus/PoW_UNDERWATER-WORLDS/resolve/main/PoWStyle-UnderwaterWorlds.ckpt)
+[CKPT](https://huggingface.co/Guizmus/SDArt_underwaterworlds/resolve/main/SDArt_underwaterworlds.ckpt)
 
-[Dataset](https://huggingface.co/Guizmus/PoW_UNDERWATER-WORLDS/resolve/main/PoWStyle-UnderwaterWorlds.zip)
+[Dataset](https://huggingface.co/Guizmus/SDArt_underwaterworlds/resolve/main/dataset.zip)
 
 ## 🧨 Diffusers
 
@@ -85,12 +101,12 @@ You can also export the model to [ONNX](https://huggingface.co/docs/diffusers/op
 from diffusers import StableDiffusionPipeline
 import torch
 
-model_id = "Guizmus/PoW_UNDERWATER-WORLDS"
+model_id = "Guizmus/SDArt_underwaterworlds"
 pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)
 pipe = pipe.to("cuda")
 
-prompt = "PoW Style AndreTheApache9587"
+prompt = "SDArt oxi"
 image = pipe(prompt).images[0]
 
-image.save("./PoWStyle.png")
+image.save("./SDArt.png")
 ```

SDArt_underwaterworlds.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9727c797d087ca58b984004b0757ff7d82efc525393b4ce7c556f72824e3388
+size 2132856622

SDArt_underwaterworlds.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b29ea9149b1356b13e92ad3623d90c396c573e5f4e418eb69b10fbdcc99cd53
+size 2132625431

dataset.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93d311ae15a67d41991032fa72ff55f0ee4201e81cde5e43725141a2ffa4e011
+size 6134987

scheduler/scheduler_config.json

@@ -9,6 +9,7 @@
   "num_train_timesteps": 1000,
   "prediction_type": "epsilon",
   "set_alpha_to_one": false,
+  "skip_prk_steps": true,
   "steps_offset": 1,
   "trained_betas": null,
   "variance_type": "fixed_small"

text_encoder/config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "ckpt_cache\\sd_v1-5_vae",
+  "_name_or_path": "F:\\AI\\Data\\Diffusers\\stable-diffusion-v1-5",
   "architectures": [
     "CLIPTextModel"
   ],

text_encoder/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0bf3f02f79646a54224370f98abb2b2c1164dbc8e5095d3a5cd5db55acd042ba
+oid sha256:a35d7b689be4334400a4c13e4ae03370deee825ba9e6829624a29920b8352b2a
 size 492308087

tokenizer/tokenizer_config.json

@@ -19,7 +19,7 @@
   },
   "errors": "replace",
   "model_max_length": 77,
-  "name_or_path": "ckpt_cache\\sd_v1-5_vae",
+  "name_or_path": "F:\\AI\\Data\\Diffusers\\stable-diffusion-v1-5",
   "pad_token": "<|endoftext|>",
   "special_tokens_map_file": "./special_tokens_map.json",
   "tokenizer_class": "CLIPTokenizer",

unet/config.json

@@ -1,7 +1,7 @@
 {
   "_class_name": "UNet2DConditionModel",
   "_diffusers_version": "0.13.0",
-  "_name_or_path": "ckpt_cache\\sd_v1-5_vae",
+  "_name_or_path": "F:\\AI\\Data\\Diffusers\\stable-diffusion-v1-5",
   "act_fn": "silu",
   "attention_head_dim": 8,
   "block_out_channels": [

unet/diffusion_pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61392260bb17e441ab7c42ead4814697094c21d2019b033c13eb098382f834a1
+oid sha256:ec71ff83af3888bd4ca0e1e85920da206458131ab0761dbbf061795e86a04868
 size 3438364325

vae/config.json

@@ -1,7 +1,7 @@
 {
   "_class_name": "AutoencoderKL",
   "_diffusers_version": "0.13.0",
-  "_name_or_path": "ckpt_cache\\sd_v1-5_vae",
+  "_name_or_path": "F:\\AI\\Data\\Diffusers\\stable-diffusion-v1-5",
   "act_fn": "silu",
   "block_out_channels": [
     128,

vae/diffusion_pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52fd6d497c6cc26f44a22cd27d905391a2aaadcecf89007b5b911198c4a50a93
-size 334710673
+oid sha256:eb128b1f37e0c381c440128b217d29613b3e08b9e4ea7f20466424145ba538b0
+size 167402961