converted using stablediffusionapi.com

README.md

@@ -1,36 +1,34 @@
 ---
 license: creativeml-openrail-m
 tags:
-  - stablediffusionapi.com
+  - modelslab.com
   - stable-diffusion-api
   - text-to-image
   - ultra-realistic
 pinned: true
 ---
 
-# Samaritan 3d Cartoon API Inference
+#  API Inference
 
-![generated from stablediffusionapi.com](https://cdn2.stablediffusionapi.com/generations/3229219621692108151.png)
+![generated from modelslab.com](https://cdn2.stablediffusionapi.com/generations/bf190b5a-fe19-437c-ba05-82f29cb1f7ad-0.png)
 ## Get API Key
 
-Get API key from [Stable Diffusion API](http://stablediffusionapi.com/), No Payment needed. 
+Get API key from [ModelsLab API](http://modelslab.com), No Payment needed. 
 
 Replace Key in below code, change **model_id**  to "samaritan-3d-cartoon"
 
-Coding in PHP/Node/Java etc? Have a look at docs for more code examples: [View docs](https://stablediffusionapi.com/docs)
+Coding in PHP/Node/Java etc? Have a look at docs for more code examples: [View docs](https://modelslab.com/docs)
 
-Try model for free: [Generate Images](https://stablediffusionapi.com/models/samaritan-3d-cartoon)
+Try model for free: [Generate Images](https://modelslab.com/models/samaritan-3d-cartoon)
 
-Model link: [View model](https://stablediffusionapi.com/models/samaritan-3d-cartoon)
+Model link: [View model](https://modelslab.com/models/samaritan-3d-cartoon)
 
-Credits: [View credits](https://civitai.com/?query=Samaritan%203d%20Cartoon)
-
-View all models: [View Models](https://stablediffusionapi.com/models)
+View all models: [View Models](https://modelslab.com/models)
 
     import requests  
     import json  
       
-    url =  "https://stablediffusionapi.com/api/v4/dreambooth"  
+    url =  "https://modelslab.com/api/v6/images/text2img"  
       
     payload = json.dumps({  
     "key":  "your_api_key",  

model_index.json

@@ -1,27 +1,35 @@
 {
-  "_class_name": "StableDiffusionPipeline",
-  "_diffusers_version": "0.20.0.dev0",
+  "_class_name": "StableDiffusionXLPipeline",
+  "_diffusers_version": "0.25.0.dev0",
   "feature_extractor": [
-    "transformers",
-    "CLIPFeatureExtractor"
+    null,
+    null
   ],
-  "requires_safety_checker": true,
-  "safety_checker": [
-    "stable_diffusion",
-    "StableDiffusionSafetyChecker"
+  "force_zeros_for_empty_prompt": true,
+  "image_encoder": [
+    null,
+    null
   ],
   "scheduler": [
     "diffusers",
-    "PNDMScheduler"
+    "EulerDiscreteScheduler"
   ],
   "text_encoder": [
     "transformers",
     "CLIPTextModel"
   ],
+  "text_encoder_2": [
+    "transformers",
+    "CLIPTextModelWithProjection"
+  ],
   "tokenizer": [
     "transformers",
     "CLIPTokenizer"
   ],
+  "tokenizer_2": [
+    "transformers",
+    "CLIPTokenizer"
+  ],
   "unet": [
     "diffusers",
     "UNet2DConditionModel"

scheduler/scheduler_config.json

@@ -1,15 +1,22 @@
 {
-  "_class_name": "PNDMScheduler",
-  "_diffusers_version": "0.20.0.dev0",
+  "_class_name": "EulerDiscreteScheduler",
+  "_diffusers_version": "0.25.0.dev0",
   "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,
+  "sigma_max": null,
+  "sigma_min": null,
   "skip_prk_steps": true,
   "steps_offset": 1,
   "timestep_spacing": "leading",
-  "trained_betas": null
+  "timestep_type": "discrete",
+  "trained_betas": null,
+  "use_karras_sigmas": false
 }

text_encoder/config.json

@@ -18,7 +18,7 @@
   "num_hidden_layers": 12,
   "pad_token_id": 1,
   "projection_dim": 768,
-  "torch_dtype": "float32",
-  "transformers_version": "4.28.1",
+  "torch_dtype": "float16",
+  "transformers_version": "4.35.2",
   "vocab_size": 49408
 }

text_encoder/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c6873af813b41a35a528de5675f72d53fdfcfd69248d2403f250e973b00f76c
-size 492307486
+oid sha256:c22dd096925656a447e7ed57e57864b7329be4b9bd9daa4bdf53561109166554
+size 246185562

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": "4.35.2",
+  "vocab_size": 49408
+}

text_encoder_2/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25a4fa957bdc94319b050752c0a0f33be622dd64e1b748b92212077ceedc8407
+size 1389490462

tokenizer/special_tokens_map.json

@@ -13,7 +13,13 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "<|endoftext|>",
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
   "unk_token": {
     "content": "<|endoftext|>",
     "lstrip": false,

tokenizer/tokenizer_config.json

@@ -1,33 +1,30 @@
 {
   "add_prefix_space": false,
-  "bos_token": {
-    "__type": "AddedToken",
-    "content": "<|startoftext|>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": 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": {
-    "__type": "AddedToken",
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
+  "eos_token": "<|endoftext|>",
   "errors": "replace",
   "model_max_length": 77,
   "pad_token": "<|endoftext|>",
   "tokenizer_class": "CLIPTokenizer",
-  "unk_token": {
-    "__type": "AddedToken",
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  }
+  "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

@@ -1,15 +1,19 @@
 {
   "_class_name": "UNet2DConditionModel",
-  "_diffusers_version": "0.20.0.dev0",
+  "_diffusers_version": "0.25.0.dev0",
   "act_fn": "silu",
-  "addition_embed_type": null,
+  "addition_embed_type": "text_time",
   "addition_embed_type_num_heads": 64,
-  "addition_time_embed_dim": null,
-  "attention_head_dim": 8,
+  "addition_time_embed_dim": 256,
+  "attention_head_dim": [
+    5,
+    10,
+    20
+  ],
+  "attention_type": "default",
   "block_out_channels": [
     320,
     640,
-    1280,
     1280
   ],
   "center_input_sample": false,
@@ -17,15 +21,15 @@
   "class_embeddings_concat": false,
   "conv_in_kernel": 3,
   "conv_out_kernel": 3,
-  "cross_attention_dim": 768,
+  "cross_attention_dim": 2048,
   "cross_attention_norm": null,
   "down_block_types": [
+    "DownBlock2D",
     "CrossAttnDownBlock2D",
-    "CrossAttnDownBlock2D",
-    "CrossAttnDownBlock2D",
-    "DownBlock2D"
+    "CrossAttnDownBlock2D"
   ],
   "downsample_padding": 1,
+  "dropout": 0.0,
   "dual_cross_attention": false,
   "encoder_hid_dim": null,
   "encoder_hid_dim_type": null,
@@ -42,23 +46,27 @@
   "num_class_embeds": null,
   "only_cross_attention": false,
   "out_channels": 4,
-  "projection_class_embeddings_input_dim": null,
+  "projection_class_embeddings_input_dim": 2816,
   "resnet_out_scale_factor": 1.0,
   "resnet_skip_time_act": false,
   "resnet_time_scale_shift": "default",
-  "sample_size": 64,
+  "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,
+  "transformer_layers_per_block": [
+    1,
+    2,
+    10
+  ],
   "up_block_types": [
-    "UpBlock2D",
     "CrossAttnUpBlock2D",
     "CrossAttnUpBlock2D",
-    "CrossAttnUpBlock2D"
+    "UpBlock2D"
   ],
   "upcast_attention": false,
-  "use_linear_projection": false
+  "use_linear_projection": true
 }

unet/diffusion_pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd4dee223f31e59f3db9a592341ddd1234c232a67a1fc0653175bbb14c103237
-size 3438366838
+oid sha256:ec8bbcb403b860ffc27ea0439f968f1778838da4296991a23f09cf71ca719852
+size 5135669022

vae/config.json

@@ -1,6 +1,6 @@
 {
   "_class_name": "AutoencoderKL",
-  "_diffusers_version": "0.20.0.dev0",
+  "_diffusers_version": "0.25.0.dev0",
   "act_fn": "silu",
   "block_out_channels": [
     128,
@@ -20,8 +20,8 @@
   "layers_per_block": 2,
   "norm_num_groups": 32,
   "out_channels": 3,
-  "sample_size": 512,
-  "scaling_factor": 0.18215,
+  "sample_size": 1024,
+  "scaling_factor": 0.13025,
   "up_block_types": [
     "UpDecoderBlock2D",
     "UpDecoderBlock2D",

vae/diffusion_pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f44860979e5e7e4a3fc305f0acdc1ffb8d82df6ee7765e421a4acce7ff7fee38
-size 334712578
+oid sha256:adc8ec05395a5efa06df524670dea99cc280155602c3168fce281e1ff70f8ab3
+size 167404866