Upload 18 files

app.py

@@ -0,0 +1,154 @@
+from diffusers import StableDiffusionPipeline, StableDiffusionImg2ImgPipeline, DPMSolverMultistepScheduler
+import gradio as gr
+import torch
+from PIL import Image
+
+model_id = 'hassanblend/HassanBlend1.5'
+prefix = ''
+     
+scheduler = DPMSolverMultistepScheduler(
+    beta_start=0.00085,
+    beta_end=0.012,
+    beta_schedule="scaled_linear",
+    num_train_timesteps=1000,
+    trained_betas=None,
+    predict_epsilon=True,
+    thresholding=False,
+    algorithm_type="dpmsolver++",
+    solver_type="midpoint",
+    lower_order_final=True,
+)
+
+pipe = StableDiffusionPipeline.from_pretrained(
+  model_id,
+  torch_dtype=torch.float16 if torch.cuda.is_available() else torch.float32,
+  scheduler=scheduler)
+
+pipe_i2i = StableDiffusionImg2ImgPipeline.from_pretrained(
+  model_id,
+  torch_dtype=torch.float16 if torch.cuda.is_available() else torch.float32,
+  scheduler=scheduler)
+
+if torch.cuda.is_available():
+  pipe = pipe.to("cuda")
+  pipe_i2i = pipe_i2i.to("cuda")
+
+def error_str(error, title="Error"):
+    return f"""#### {title}
+            {error}"""  if error else ""
+
+def inference(prompt, guidance, steps, width=512, height=512, seed=0, img=None, strength=0.5, neg_prompt="", auto_prefix=True):
+
+  generator = torch.Generator('cuda').manual_seed(seed) if seed != 0 else None
+  prompt = f"{prefix} {prompt}" if auto_prefix else prompt
+
+  try:
+    if img is not None:
+      return img_to_img(prompt, neg_prompt, img, strength, guidance, steps, width, height, generator), None
+    else:
+      return txt_to_img(prompt, neg_prompt, guidance, steps, width, height, generator), None
+  except Exception as e:
+    return None, error_str(e)
+
+def txt_to_img(prompt, neg_prompt, guidance, steps, width, height, generator):
+
+    result = pipe(
+      prompt,
+      negative_prompt = neg_prompt,
+      num_inference_steps = int(steps),
+      guidance_scale = guidance,
+      width = width,
+      height = height,
+      generator = generator)
+    
+    return replace_nsfw_images(result)
+
+def img_to_img(prompt, neg_prompt, img, strength, guidance, steps, width, height, generator):
+
+    ratio = min(height / img.height, width / img.width)
+    img = img.resize((int(img.width * ratio), int(img.height * ratio)), Image.LANCZOS)
+    result = pipe_i2i(
+        prompt,
+        negative_prompt = neg_prompt,
+        init_image = img,
+        num_inference_steps = int(steps),
+        strength = strength,
+        guidance_scale = guidance,
+        width = width,
+        height = height,
+        generator = generator)
+        
+    return replace_nsfw_images(result)
+
+def replace_nsfw_images(results):
+
+    for i in range(len(results.images)):
+      if results.nsfw_content_detected[i]:
+        results.images[i] = Image.open("nsfw.png")
+    return results.images[0]
+
+css = """.main-div div{display:inline-flex;align-items:center;gap:.8rem;font-size:1.75rem}.main-div div h1{font-weight:900;margin-bottom:7px}.main-div p{margin-bottom:10px;font-size:94%}a{text-decoration:underline}.tabs{margin-top:0;margin-bottom:0}#gallery{min-height:20rem}
+"""
+with gr.Blocks(css=css) as demo:
+    gr.HTML(
+        f"""
+            <div class="main-div">
+              <div>
+                <h1>Hassanblend1.5</h1>
+              </div>
+              <p>
+               Demo for <a href="https://huggingface.co/hassanblend/HassanBlend1.5">Hassanblend1.5</a> Stable Diffusion model.<br>
+        Add the following tokens to your prompts for the model to work properly: <b></b>.
+              </p>
+              Running on <b>{"GPU 🔥" if torch.cuda.is_available() else "CPU 🥶"}</b>
+            </div>
+        """
+    )
+    with gr.Row():
+        
+        with gr.Column(scale=55):
+          with gr.Group():
+              with gr.Row():
+                prompt = gr.Textbox(label="Prompt", show_label=False, max_lines=2,placeholder=f"{prefix} [your prompt]").style(container=False)
+                generate = gr.Button(value="Generate").style(rounded=(False, True, True, False))
+
+              image_out = gr.Image(height=512)
+          error_output = gr.Markdown()
+
+        with gr.Column(scale=45):
+          with gr.Tab("Options"):
+            with gr.Group():
+              neg_prompt = gr.Textbox(label="Negative prompt", placeholder="What to exclude from the image")
+              auto_prefix = gr.Checkbox(label="Prefix styling tokens automatically ()", value=True)
+
+              with gr.Row():
+                guidance = gr.Slider(label="Guidance scale", value=7.5, maximum=15)
+                steps = gr.Slider(label="Steps", value=25, minimum=2, maximum=75, step=1)
+
+              with gr.Row():
+                width = gr.Slider(label="Width", value=512, minimum=64, maximum=1024, step=8)
+                height = gr.Slider(label="Height", value=512, minimum=64, maximum=1024, step=8)
+
+              seed = gr.Slider(0, 2147483647, label='Seed (0 = random)', value=0, step=1)
+
+          with gr.Tab("Image to image"):
+              with gr.Group():
+                image = gr.Image(label="Image", height=256, tool="editor", type="pil")
+                strength = gr.Slider(label="Transformation strength", minimum=0, maximum=1, step=0.01, value=0.5)
+
+    auto_prefix.change(lambda x: gr.update(placeholder=f"{prefix} [your prompt]" if x else "[Your prompt]"), inputs=auto_prefix, outputs=prompt, queue=False)
+
+    inputs = [prompt, guidance, steps, width, height, seed, image, strength, neg_prompt, auto_prefix]
+    outputs = [image_out, error_output]
+    prompt.submit(inference, inputs=inputs, outputs=outputs)
+    generate.click(inference, inputs=inputs, outputs=outputs)
+
+    gr.HTML("""
+    <div style="border-top: 1px solid #303030;">
+      <br>
+      <p>This space was created using <a href="https://huggingface.co/spaces/anzorq/sd-space-creator">SD Space Creator</a>.</p>
+    </div>
+    """)
+
+demo.queue(concurrency_count=1)
+demo.launch()

feature_extractor/preprocessor_config.json

@@ -0,0 +1,20 @@
+{
+  "crop_size": 224,
+  "do_center_crop": true,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_resize": true,
+  "feature_extractor_type": "CLIPFeatureExtractor",
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "resample": 3,
+  "size": 224
+}

model_index.json

@@ -0,0 +1,32 @@
+{
+  "_class_name": "StableDiffusionPipeline",
+  "_diffusers_version": "0.7.2",
+  "feature_extractor": [
+    "transformers",
+    "CLIPFeatureExtractor"
+  ],
+  "safety_checker": [
+    "stable_diffusion",
+    "StableDiffusionSafetyChecker"
+  ],
+  "scheduler": [
+    "diffusers",
+    "PNDMScheduler"
+  ],
+  "text_encoder": [
+    "transformers",
+    "CLIPTextModel"
+  ],
+  "tokenizer": [
+    "transformers",
+    "CLIPTokenizer"
+  ],
+  "unet": [
+    "diffusers",
+    "UNet2DConditionModel"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKL"
+  ]
+}

pipeline.py

@@ -0,0 +1,22 @@
+class PreTrainedPipeline():
+    def __init__(self, path=""):
+        # IMPLEMENT_THIS
+        # Preload all the elements you are going to need at inference.
+        # For instance your model, processors, tokenizer that might be needed.
+        # This function is only called once, so do all the heavy processing I/O here"""
+        raise NotImplementedError(
+            "Please implement PreTrainedPipeline __init__ function"
+        )
+ 
+    def __call__(self, inputs: str):
+        """
+        Args:
+            inputs (:obj:`str`):
+                a string containing some text
+        Return:
+            A :obj:`PIL.Image` with the raw image representation as PIL.
+        """
+        # IMPLEMENT_THIS
+        raise NotImplementedError(
+            "Please implement PreTrainedPipeline __call__ function"
+        )

requirements.txt

@@ -0,0 +1,6 @@
+--extra-index-url https://download.pytorch.org/whl/cu113
+torch
+diffusers
+transformers
+accelerate
+ftfy

safety_checker/config.json

@@ -0,0 +1,179 @@
+{
+  "_commit_hash": "4bb648a606ef040e7685bde262611766a5fdd67b",
+  "_name_or_path": "CompVis/stable-diffusion-safety-checker",
+  "architectures": [
+    "StableDiffusionSafetyChecker"
+  ],
+  "initializer_factor": 1.0,
+  "logit_scale_init_value": 2.6592,
+  "model_type": "clip",
+  "projection_dim": 768,
+  "text_config": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": 0,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "dropout": 0.0,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 2,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "quick_gelu",
+    "hidden_size": 768,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-05,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 77,
+    "min_length": 0,
+    "model_type": "clip_text_model",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 12,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 12,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 1,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "transformers_version": "4.24.0",
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "vocab_size": 49408
+  },
+  "text_config_dict": {
+    "hidden_size": 768,
+    "intermediate_size": 3072,
+    "num_attention_heads": 12,
+    "num_hidden_layers": 12
+  },
+  "torch_dtype": "float32",
+  "transformers_version": null,
+  "vision_config": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "dropout": 0.0,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "quick_gelu",
+    "hidden_size": 1024,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "image_size": 224,
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 4096,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-05,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "model_type": "clip_vision_model",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 16,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_channels": 3,
+    "num_hidden_layers": 24,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "patch_size": 14,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "transformers_version": "4.24.0",
+    "typical_p": 1.0,
+    "use_bfloat16": false
+  },
+  "vision_config_dict": {
+    "hidden_size": 1024,
+    "intermediate_size": 4096,
+    "num_attention_heads": 16,
+    "num_hidden_layers": 24,
+    "patch_size": 14
+  }
+}

safety_checker/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16d28f2b37109f222cdc33620fdd262102ac32112be0352a7f77e9614b35a394
+size 1216064769

scheduler/scheduler_config.json

@@ -0,0 +1,13 @@
+{
+  "_class_name": "PNDMScheduler",
+  "_diffusers_version": "0.7.2",
+  "beta_end": 0.012,
+  "beta_schedule": "scaled_linear",
+  "beta_start": 0.00085,
+  "clip_sample": false,
+  "num_train_timesteps": 1000,
+  "set_alpha_to_one": false,
+  "skip_prk_steps": true,
+  "steps_offset": 1,
+  "trained_betas": null
+}

text_encoder/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "openai/clip-vit-large-patch14",
+  "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": "float32",
+  "transformers_version": "4.24.0",
+  "vocab_size": 49408
+}

text_encoder/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83b9e059a2af92f8bdff755be76dcaa30b7473346541aadee05707a601cc616e
+size 492307041

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": "<|endoftext|>",
+  "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,
+  "name_or_path": "openai/clip-vit-large-patch14",
+  "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
+  }
+}

unet/config.json

@@ -0,0 +1,36 @@
+{
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.7.2",
+  "act_fn": "silu",
+  "attention_head_dim": 8,
+  "block_out_channels": [
+    320,
+    640,
+    1280,
+    1280
+  ],
+  "center_input_sample": false,
+  "cross_attention_dim": 768,
+  "down_block_types": [
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "DownBlock2D"
+  ],
+  "downsample_padding": 1,
+  "flip_sin_to_cos": true,
+  "freq_shift": 0,
+  "in_channels": 4,
+  "layers_per_block": 2,
+  "mid_block_scale_factor": 1,
+  "norm_eps": 1e-05,
+  "norm_num_groups": 32,
+  "out_channels": 4,
+  "sample_size": 64,
+  "up_block_types": [
+    "UpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D"
+  ]
+}

unet/diffusion_pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9579b198d3f04fc72f2b0423f72f581848abf37fb620da0ea5eee214ddfc0b5
+size 3438366373

vae/config.json

@@ -0,0 +1,29 @@
+{
+  "_class_name": "AutoencoderKL",
+  "_diffusers_version": "0.7.2",
+  "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": 256,
+  "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 sha256:8b35db0323c11c073d28be039e178331d36efe1fd40f4a9d2dd68b74b62040b4
+size 334711857