Upload 13 files

.gitattributes

@@ -35,3 +35,8 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 Stable[[:space:]]Diffusion[[:space:]]1.5/ForgottenMixAnimation_V10.jpeg filter=lfs diff=lfs merge=lfs -text
 Stable[[:space:]]Diffusion[[:space:]]1.5/Westeland_V10.png filter=lfs diff=lfs merge=lfs -text
+Stable[[:space:]]Diffusion[[:space:]]1.5/CyberRealistic_v90.png filter=lfs diff=lfs merge=lfs -text
+Stable[[:space:]]Diffusion[[:space:]]1.5/EpicPhotonism_V10.png filter=lfs diff=lfs merge=lfs -text
+Stable[[:space:]]Diffusion[[:space:]]1.5/EpicRealism_NaturalSinRC1VAE.jpeg filter=lfs diff=lfs merge=lfs -text
+Stable[[:space:]]Diffusion[[:space:]]1.5/Photon_V1.jpeg filter=lfs diff=lfs merge=lfs -text
+Stable[[:space:]]Diffusion[[:space:]]1.5/RealisticStockPhoto_V30.png filter=lfs diff=lfs merge=lfs -text

Stable Diffusion 1.5/CyberRealistic_v90.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8d35d5795ba650a62a511d0310101645e9ce15c827e472e3f8ad5cfc09b1b5e
+size 4265146268

Stable Diffusion 1.5/EpicPhotonism_V10.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eed0bdfc49734e99100cf4d4c10640125114cc651c118d1ea0b006f8b8ab3c63
+size 2132626798

Stable Diffusion 1.5/EpicRealism_NaturalSinRC1VAE.json

@@ -0,0 +1,5 @@
+{
+    "description": "Advices\nuse simple prompts\n\nno need to use keywords like \"masterpiece, best quality, 8k, intricate, high detail\" or \"(extremely detailed face), (extremely detailed hands), (extremely detailed hair)\" since it doesn't produce appreciable change\n\nuse simple negatives or small negative embeddings. gives most realistic look (check samples to get an idea of negatives i used)\n\nadd \"asian, chinese\" to negative if you're looking for ethnicities other than Asian\n\nLight, shadows, and details are excellent without extra keywords\n\nIf you're looking for a natural effect, avoid \"cinematic\"\n\navoid using \"1girl\" since it pushes things to render/anime style\n\nto much description of the face will turn out bad mostly\n\nfor a more fantasy like output use 2M Karras Sampler\n\nno extra noise-offset needed, but u can if you like to \ud83d\ude09\n\nHow to use?\nPrompt: simple explanation of the image (try first without extra keywords)\nNegative: \"cartoon, painting, illustration, (worst quality, low quality, normal quality:2)\"\nSteps: >20 (if image has errors or artefacts use higher Steps)\nCFG Scale: 5 (higher config scale can lose realism, depends on prompt, sampler and Steps)\nSampler: Any Sampler (SDE, DPM-Sampler will result in more realism)\nSize: 512x768 or 768x512\nHires upscaler: 4x_NMKD-Superscale-SP_178000_G (Denoising: 0.35, Upscale: 2x)\n\nUseful Extensions\n!After Detailer | ControlNet | Agent Scheduler | Ultimate SD Upscale",
+    "notes": "",
+    "vae": ""
+}

Stable Diffusion 1.5/EpicRealism_NaturalSinRC1VAE.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84d76a0328ee5a1a2a1d466ba7478ab59183e3fea385441528aa4c5d567fd43e
+size 2132625612

Stable Diffusion 1.5/Photon_V1.json

@@ -0,0 +1,5 @@
+{
+    "description": "Photon aims to generate photorealistic and visually appealing images effortlessly.\n\nRecommendation for generating the first image with Photon:\n\nPrompt: A simple sentence in natural language describing the image.\n\nNegative: \"cartoon, painting, illustration, (worst quality, low quality, normal quality:2)\"\n\nSampler: DPM++ 2M Karras | Steps: 20 | CFG Scale: 6\n\nSize: 512x768 or 768x512\n\nHires.fix: R-ESRGAN 4x+ | Steps: 10 | Denoising: 0.45 | Upscale x 2\n\n(avoid using negative embeddings unless absolutely necessary)\n\nFrom this initial point, experiment by adding positive and negative tags and adjusting the settings. Most of the sample images follow this format.\n\nDevelopment\nThe development process was somewhat chaotic but essentially:\n\nIt started from an old mix.\n\nLORAs were trained on various topics using AI-generated photorealistic images.\n\nThese LORAs were mixed within the model using different weights.\n\nIn the midst of this mixing, hand generation broke.\n\nLORAs were generated and remixed in an attempt to fix hand generation (not entirely successful).\n\nIn future versions, I will try to:\n\nCompletely eliminate the need for a negative prompt to generate high-quality images.\n\nFix the hand generation issue to minimize instances of poorly drawn hands.\n\nExplore more automated training processes. I would love to have 5,000 or 50,000 high-quality AI-generated photorealistic images for training purposes.\n\nI hope you enjoy using it as much as I enjoyed creating it! If you have any questions or suggestions, feel free to share. Have fun creating amazing images! \ud83c\udfa8",
+    "notes": "",
+    "vae": ""
+}

Stable Diffusion 1.5/Photon_V1.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec41bd2a8271acde4ae81cac004d9f3300e7fb0870eae8cbfe0bbc4ef8e27f91
+size 2132625918

Stable Diffusion 1.5/PicX_Real_V10.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07919b495df62d7b1b2c6f1715669e1b8f9ce92e496de3a688b30744daece525
+size 2132650982

Stable Diffusion 1.5/RealisticStockPhoto_V30.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f85affae9aae16276eaf670f810946e2d03c4d300791a0380f07653cb78ba31b
+size 4265154828