negative emmbedings

.env_template

@@ -0,0 +1,4 @@
+TOKEN=<telegram-bot-token >
+API_ID=<telegram-id-api-id >
+API_HASH=<telegram-id-api-hash>
+SD_URL=<stable-diffusion-api-url>

.gitignore

@@ -1,3 +1,8 @@
 *.png
 .env
-.session
+*.session
+vscode/
+venv/
+*.session-journal
+logs/stable_diff_telegram_bot.log
+*.session

README.md

@@ -1,16 +1,16 @@
 # AI Powered Art in a Telegram Bot!
 
-this is a txt2img bot to converse with SDweb bot [API](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/API) running on tami telegram channel
+this is a txt2img/img2img bot to converse with SDweb bot [API](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/API) running on tami telegram channel
 
-# How to
-
-supported invocation:  
+## How to
+### txt2img
 `/draw <text>` - send prompt text to the bot and it will draw an image  
 you can add `negative_prompt` using `ng: <text>`  
 you can add `denoised intermediate steps` using `steps: <text>`  
 
 basicly anything the `/controlnet/txt2img` API payload supports  
 like, 
+
 ```json
 {
   "prompt": "",
@@ -22,6 +22,7 @@ like,
   "cfg_scale": 7
 }
 ```
+
 examples:  
 `/draw a city street`  
 and without people  
@@ -32,26 +33,45 @@ with more steps
 to change the model use:  
 `/getmodels` - to get a list of models and then click to set it. 
 
-
-
 - note1: Anything after ng will be considered as nergative prompt. a.k.a things you do not want to see in your diffusion!  
 - note2: on [negative_prompt](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Negative-prompt) (aka ng):  
 thia is a bit of a black art. i took the recommended defaults for the `Deliberate` model from this fun [alt-model spreadsheet](https://docs.google.com/spreadsheets/d/1Q0bYKRfVOTUHQbUsIISCztpdZXzfo9kOoAy17Qhz3hI/edit#gid=797387129).    
-~~and you (currntly) can only ADD to it, not replace.~~  
 - note3: on `steps` - step of 1 will generate only the first "step" of bot hallucinations. the default is 40. higher will take longer and will give "better" image. range is hardcoded 1-70.  
 see ![video](https://user-images.githubusercontent.com/57876960/212490617-f0444799-50e5-485e-bc5d-9c24a9146d38.mp4)
+
+### img2img
+`/img <prompt> ds:<0.0-1.0>` - reply to an image with a prompt text and it will draw an image
+
+you can add `denoising_strength` using `ds:<float>`  
+Set that low (like 0.2) if you just want to slightly change things. defaults to 0.4
+
+basicly anything the `/controlnet/img2img` API payload supports  
+
+### general
+`X/Y/Z script` [link](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Features#xyz-plot), one powerfull thing
+ 
+for prompt we use the Serach Replace option (a.k.a `prompt s/r`) [exaplined](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Features#prompt-sr)
+
 ## Setup
 
-Install requirements
+Install requirements using venv
+
+```bash
+python3 -m venv venv
+source venv/bin/activate
+pip install -r requirements.txt
+```
+
+
+Install requirements using conda
 
 ```bash
 conda create -n sdw python=3.8
 conda activate sdw
 pip install -r requirements.txt
 ```
-(note: conda is not strictly necessary, but it is recommended)
 
-## Original readme
+## Original README
 
 My Bot uses [Automatic1111's WebUI](https://github.com/AUTOMATIC1111/stable-diffusion-webui) as the backend.
 Follow the directions on their repo for setup instructions.
@@ -62,15 +82,23 @@ arguments such as `--xformers` to use xformers memory efficient attention.
 You can use the web ui interface that Automatic1111 provides to select the model and VAE to use.
 Their repo has documentation on how to do so. I also recommend doing a test generation
 
-Create a file called `.env` in the same folder as `main.py`. Inside the `.env` file,
-create a line `TOKEN = xxxx`, where xxxx is your telegram bot token.
-create a line `API_ID = xxxx`, where xxxx is your telegram id api id.
-create a line `API_HASH = xxxx`, where xxxx is your telegram id api hash.
-create a line `SD_URL = xxxx`, where xxxx is your sd api url.
+Copy a file called `.env_template` into `.env_template` in the same folder as `main.py`.
+In the `.env` file fill out the following environment variables:
+`TOKEN = xxxx`, where xxxx is your telegram bot token.
+`API_ID = xxxx`, where xxxx is your telegram id api id.
+`API_HASH = xxxx`, where xxxx is your telegram id api hash.
+`SD_URL = xxxx`, where xxxx is your sd api url.
+
+
+To get the API_ID and API_HASH, you need to create a new application on the Telegram's developer website. Here are the steps:
+
+1. Open browser and visit https://my.telegram.org and log in with your Telegram account.
+2. Click on "API development tools".
+3. Fill out the form to create a new application. You can enter any valid details you want.
+4. After you've created the application, you'll be given the API_ID and API_HASH.
+5. Once you have these, you can add them to your .env file:
 
 Now, you can run the bot
 
 `python main.py`
 
-
-

localAPIRun.py

@@ -0,0 +1,170 @@
+from datetime import datetime
+import urllib.request
+import base64
+import json
+import time
+import os
+url="pop-os.local"
+webui_server_url = f'http://{url}:7860'
+
+out_dir = 'api_out'
+out_dir_t2i = os.path.join(out_dir, 'txt2img')
+out_dir_i2i = os.path.join(out_dir, 'img2img')
+os.makedirs(out_dir_t2i, exist_ok=True)
+os.makedirs(out_dir_i2i, exist_ok=True)
+
+
+def timestamp():
+    return datetime.fromtimestamp(time.time()).strftime("%Y%m%d-%H%M%S")
+
+
+def encode_file_to_base64(path):
+    with open(path, 'rb') as file:
+        return base64.b64encode(file.read()).decode('utf-8')
+
+
+def decode_and_save_base64(base64_str, save_path):
+    with open(save_path, "wb") as file:
+        file.write(base64.b64decode(base64_str))
+
+
+def call_api(api_endpoint, **payload):
+    data = json.dumps(payload).encode('utf-8')
+    request = urllib.request.Request(
+        f'{webui_server_url}/{api_endpoint}',
+        headers={'Content-Type': 'application/json'},
+        data=data,
+    )
+    response = urllib.request.urlopen(request)
+    return json.loads(response.read().decode('utf-8'))
+
+
+def call_txt2img_api(**payload):
+    response = call_api('sdapi/v1/txt2img', **payload)
+    for index, image in enumerate(response.get('images')):
+        save_path = os.path.join(out_dir_t2i, f'txt2img-{timestamp()}-{index}.png')
+        decode_and_save_base64(image, save_path)
+
+
+def call_img2img_api(**payload):
+    response = call_api('sdapi/v1/img2img', **payload)
+    for index, image in enumerate(response.get('images')):
+        save_path = os.path.join(out_dir_i2i, f'img2img-{timestamp()}-{index}.png')
+        decode_and_save_base64(image, save_path)
+
+
+if __name__ == '__main__':
+    payload = {
+        "prompt": "masterpiece, (best quality:1.1), 1girl <lora:lora_model:1>",  # extra networks also in prompts
+        "negative_prompt": "",
+        "seed": 1,
+        "steps": 20,
+        "width": 512,
+        "height": 512,
+        "cfg_scale": 7,
+        "sampler_name": "DPM++ SDE Karras",
+        "n_iter": 1,
+        "batch_size": 1,
+        
+        # example args for x/y/z plot
+        #steps  4,"20,30"
+        #denoising==22
+        # S/R         7,"X,united states,china",
+        "script_args": [
+            4,
+            "20,30,40",
+            [],
+            0,
+            "",
+            [],
+            0,
+            "",
+            [],
+            True,
+            False,
+            False,
+            False,
+            False,
+            False,
+            False,
+            0,
+            False
+        ],
+        "script_name": "x/y/z plot",
+
+
+        # example args for Refiner and ControlNet
+        # "alwayson_scripts": {
+        #     "ControlNet": {
+        #         "args": [
+        #             {
+        #                 "batch_images": "",
+        #                 "control_mode": "Balanced",
+        #                 "enabled": True,
+        #                 "guidance_end": 1,
+        #                 "guidance_start": 0,
+        #                 "image": {
+        #                     "image": encode_file_to_base64(r"B:\path\to\control\img.png"),
+        #                     "mask": None  # base64, None when not need
+        #                 },
+        #                 "input_mode": "simple",
+        #                 "is_ui": True,
+        #                 "loopback": False,
+        #                 "low_vram": False,
+        #                 "model": "control_v11p_sd15_canny [d14c016b]",
+        #                 "module": "canny",
+        #                 "output_dir": "",
+        #                 "pixel_perfect": False,
+        #                 "processor_res": 512,
+        #                 "resize_mode": "Crop and Resize",
+        #                 "threshold_a": 100,
+        #                 "threshold_b": 200,
+        #                 "weight": 1
+        #             }
+        #         ]
+        #     },
+        #     "Refiner": {
+        #         "args": [
+        #             True,
+        #             "sd_xl_refiner_1.0",
+        #             0.5
+        #         ]
+        #     }
+        # },
+        # "enable_hr": True,
+        # "hr_upscaler": "R-ESRGAN 4x+ Anime6B",
+        # "hr_scale": 2,
+        # "denoising_strength": 0.5,
+        # "styles": ['style 1', 'style 2'],
+        # "override_settings": {
+        #     'sd_model_checkpoint': "sd_xl_base_1.0",  # this can use to switch sd model
+        # },
+    }
+    call_txt2img_api(**payload)
+
+    init_images = [
+        encode_file_to_base64(r"../stable-diffusion-webui/output/img2img-images/2024-05-15/00012-357584826.png"),
+        # encode_file_to_base64(r"B:\path\to\img_2.png"),
+        # "https://image.can/also/be/a/http/url.png",
+    ]
+
+    batch_size = 2
+    payload = {
+        "prompt": "1girl, blue hair",
+        "seed": 1,
+        "steps": 20,
+        "width": 512,
+        "height": 512,
+        "denoising_strength": 0.5,
+        "n_iter": 1,
+        "init_images": init_images,
+        "batch_size": batch_size if len(init_images) == 1 else len(init_images),
+        # "mask": encode_file_to_base64(r"B:\path\to\mask.png")
+    }
+    # if len(init_images) > 1 then batch_size should be == len(init_images)
+    # else if len(init_images) == 1 then batch_size can be any value int >= 1
+    call_img2img_api(**payload)
+
+    # there exist a useful extension that allows converting of webui calls to api payload
+    # particularly useful when you wish setup arguments of extensions and scripts
+    # https://github.com/huchenlei/sd-webui-api-payload-display

main.py

@@ -1,239 +1,323 @@
-import json
-import requests
-import io
-import re
 import os
+import re
+import io
 import uuid
 import base64
+import requests
+from datetime import datetime
 from PIL import Image, PngImagePlugin
 from pyrogram import Client, filters
-from pyrogram.types import *
+from pyrogram.types import InlineKeyboardButton, InlineKeyboardMarkup
 from dotenv import load_dotenv
 
-# Done! Congratulations on your new bot. You will find it at
-# t.me/gootmornbot
-# You can now add a description, about section and profile picture for your bot, see /help for a list of commands. By the way, when you've finished creating your cool bot, ping our Bot Support if you want a better username for it. Just make sure the bot is fully operational before you do this.
-
-# Use this token to access the HTTP API:
-# Keep your token secure and store it safely, it can be used by anyone to control your bot.
-
-# For a description of the Bot API, see this page: https://core.telegram.org/bots/api
-
+# Load environment variables
 load_dotenv()
-API_ID = os.environ.get("API_ID", None)
-API_HASH = os.environ.get("API_HASH", None)
-TOKEN = os.environ.get("TOKEN", None)
-SD_URL = os.environ.get("SD_URL", None)
-print(SD_URL)
+API_ID = os.environ.get("API_ID")
+API_HASH = os.environ.get("API_HASH")
+TOKEN = os.environ.get("TOKEN_givemtxt2img")
+SD_URL = os.environ.get("SD_URL")
+
 app = Client("stable", api_id=API_ID, api_hash=API_HASH, bot_token=TOKEN)
+IMAGE_PATH = 'images'
 
-# default params
-steps_value_default = 40
+# Ensure IMAGE_PATH directory exists
+os.makedirs(IMAGE_PATH, exist_ok=True)
+
+# Model-specific emmbedings for negative prompts
+# see civit.ai model page for specific emmbedings recommnded for each model
+model_negative_prompts = {
+    "Anything-Diffusion": "",
+    "Deliberate": "",
+    "Dreamshaper": "",
+    "DreamShaperXL_Lightning": "",
+    "icbinp": "",
+    "realisticVisionV60B1_v51VAE": "realisticvision-negative-embedding",
+    "v1-5-pruned-emaonly": ""
+}
 
 
-def parse_input(input_string):
-    default_payload = {
+def encode_file_to_base64(path):
+    with open(path, 'rb') as file:
+        return base64.b64encode(file.read()).decode('utf-8')
+
+
+def decode_and_save_base64(base64_str, save_path):
+    with open(save_path, "wb") as file:
+        file.write(base64.b64decode(base64_str))
+
+
+
+    # Set default payload values
+default_payload = {
         "prompt": "",
-        "negative_prompt": "",
-        "controlnet_input_image": [],
-        "controlnet_mask": [],
-        "controlnet_module": "",
-        "controlnet_model": "",
-        "controlnet_weight": 1,
-        "controlnet_resize_mode": "Scale to Fit (Inner Fit)",
-        "controlnet_lowvram": False,
-        "controlnet_processor_res": 64,
-        "controlnet_threshold_a": 64,
-        "controlnet_threshold_b": 64,
-        "controlnet_guidance": 1,
-        "controlnet_guessmode": True,
+        "seed": -1, # Random seed
+        "negative_prompt":  "extra fingers, mutated hands, poorly drawn hands, poorly drawn face, deformed, ugly, blurry, bad anatomy, bad proportions, extra limbs, cloned face, skinny, glitchy, double torso, extra arms, extra hands, mangled fingers, missing lips, ugly face, distorted face, extra legs",
         "enable_hr": False,
-        "denoising_strength": 0.5,
-        "hr_scale": 1.5,
-        "hr_upscale": "Latent",
-        "seed": -1,
-        "subseed": -1,
-        "subseed_strength": -1,
-        "sampler_index": "",
+        "Sampler": "DPM++ SDE Karras",
+        "denoising_strength": 0.35,
         "batch_size": 1,
         "n_iter": 1,
-        "steps": 20,
+        "steps": 35,
         "cfg_scale": 7,
         "width": 512,
         "height": 512,
-        "restore_faces": True,
+        "restore_faces": False,
         "override_settings": {},
         "override_settings_restore_afterwards": True,
     }
-    # Initialize an empty payload with the 'prompt' key
-    payload = {"prompt": ""}
 
+def update_negative_prompt(model_name):
+    if model_name in model_negative_prompts:
+        suffix = model_negative_prompts[model_name]
+        default_payload["negative_prompt"] += f", {suffix}"
+
+def parse_input(input_string):
+    payload = default_payload.copy()
     prompt = []
 
-    # Find all occurrences of keys (words ending with a colon)
     matches = re.finditer(r"(\w+):", input_string)
     last_index = 0
 
-    # Iterate over the found keys
+    script_args = [0, "", [], 0, "", [], 0, "", [], True, False, False, False, False, False, False, 0, False]
+    script_name = None
+
+
+    script_args = [0, "", [], 0, "", [], 0, "", [], True, False, False, False, False, False, False, 0, False]
+    script_name = None
+
+    slot_mapping = {0: (0, 1), 1: (3, 4), 2: (6, 7)}
+    slot_index = 0
+
     for match in matches:
-        key = match.group(1).lower()  # Convert the key to lowercase
+        key = match.group(1).lower()
         value_start_index = match.end()
-
-        # If there's text between the last key and the current key, add it to the prompt
         if last_index != match.start():
-            prompt.append(input_string[last_index : match.start()].strip())
+            prompt.append(input_string[last_index: match.start()].strip())
         last_index = value_start_index
-
-        # Check if the key is in the default payload
-        if key in default_payload:
-            # Extract the value for the current key
-            value_end_index = re.search(
-                r"(?=\s+\w+:|$)", input_string[value_start_index:]
-            ).start()
-            value = input_string[
-                value_start_index : value_start_index + value_end_index
-            ].strip()
-
-            # Check if the default value for the key is an integer
-            if isinstance(default_payload[key], int):
-                # If the value is a valid integer, store it as an integer in the payload
-                if value.isdigit():
-                    payload[key] = int(value)
-            else:
-                # If the default value for the key is not an integer, store the value as is in the payload
-                payload[key] = value
-
-            last_index += value_end_index
+        value_end_match = re.search(r"(?=\s+\w+:|$)", input_string[value_start_index:])
+        if value_end_match:
+            value_end_index = value_end_match.start() + value_start_index
         else:
-            # If the key is not in the default payload, add it to the prompt
-            prompt.append(f"{key}:")
+            value_end_index = len(input_string)
+        value = input_string[value_start_index: value_end_index].strip()
+        if key == "ds":
+            key = "denoising_strength"
+        if key == "ng":
+            key = "negative_prompt"
+        if key == "cfg":
+            key = "cfg_scale"
 
-    # Join the prompt words and store it in the payload
-    payload["prompt"] = " ".join(prompt)
+        if key in default_payload:
+            payload[key] = value
+        elif key in ["xsr", "xsteps", "xds", "xcfg", "nl", "ks", "rs"]:
+            script_name = "x/y/z plot"
+            if slot_index < 3:
+                script_slot = slot_mapping[slot_index]
+                if key == "xsr":
+                    script_args[script_slot[0]] = 7  # Enum value for xsr
+                    script_args[script_slot[1]] = value
+                elif key == "xsteps":
+                    script_args[script_slot[0]] = 4  # Enum value for xsteps
+                    script_args[script_slot[1]] = value
+                elif key == "xds":
+                    script_args[script_slot[0]] = 22  # Enum value for xds
+                    script_args[script_slot[1]] = value
+                elif key == "xcfg":
+                    script_args[script_slot[0]] = 6  # Enum value for CFG Scale
+                    script_args[script_slot[1]] = value
+                slot_index += 1
+            elif key == "nl":
+                script_args[9] = False  # Draw legend
+            elif key == "ks":
+                script_args[10] = True  # Keep sub images
+            elif key == "rs":
+                script_args[11] = True  # Set random seed to sub images
+        else:
+            prompt.append(f"{key}:{value}")
 
-    # If the prompt is empty, set the input string as the prompt
+        last_index = value_end_index
+
+    payload["prompt"] = " ".join(prompt).strip()
     if not payload["prompt"]:
         payload["prompt"] = input_string.strip()
 
-    # Return the final payload
+    if script_name:
+        payload["script_name"] = script_name
+        payload["script_args"] = script_args
+
     return payload
 
 
+def create_caption(payload, user_name, user_id, info):
+    caption = f"**[{user_name}](tg://user?id={user_id})**\n\n"
+    prompt = payload["prompt"]
+    print(payload["prompt"])
+    print(info)
+    # Steps: 3, Sampler: Euler, CFG scale: 7.0, Seed: 4094161400, Size: 512x512, Model hash: 15012c538f, Model: realisticVisionV60B1_v51VAE, Denoising strength: 0.35, Version: v1.8.0-1-g20cdc7c
+
+    # Define a regular expression pattern to match the seed value
+    seed_pattern = r"Seed: (\d+)"
+
+    # Search for the pattern in the info string
+    match = re.search(seed_pattern, info)
+
+    # Check if a match was found and extract the seed value
+    if match:
+        seed_value = match.group(1)
+        print(f"Seed value: {seed_value}")
+        caption += f"**{seed_value}**\n"
+    else:
+        print("Seed value not found in the info string.")
+
+    caption += f"**{prompt}**\n"
+
+    if len(caption) > 1024:
+        caption = caption[:1021] + "..."
+
+    return caption
+
+
+def call_api(api_endpoint, payload):
+    try:
+        response = requests.post(f'{SD_URL}/{api_endpoint}', json=payload)
+        response.raise_for_status()
+        return response.json()
+    except requests.RequestException as e:
+        print(f"API call failed: {e}")
+        return None
+
+
+def process_images(images, user_id, user_name):
+    def generate_unique_name():
+        unique_id = str(uuid.uuid4())[:7]
+        return f"{user_name}-{unique_id}"
+
+    word = generate_unique_name()
+
+    for i in images:
+        image = Image.open(io.BytesIO(base64.b64decode(i.split(",", 1)[0])))
+        png_payload = {"image": "data:image/png;base64," + i}
+        response2 = requests.post(f"{SD_URL}/sdapi/v1/png-info", json=png_payload)
+        response2.raise_for_status()
+
+        pnginfo = PngImagePlugin.PngInfo()
+        pnginfo.add_text("parameters", response2.json().get("info"))
+        image.save(f"{IMAGE_PATH}/{word}.png", pnginfo=pnginfo)
+
+        return word, response2.json().get("info")
+
 @app.on_message(filters.command(["draw"]))
 def draw(client, message):
     msgs = message.text.split(" ", 1)
     if len(msgs) == 1:
-        message.reply_text(
-            "Format :\n/draw < text to image >\nng: < negative (optional) >\nsteps: < steps value (1-70, optional) >"
-        )
+        message.reply_text("Format :\n/draw < text to image >\nng: < negative (optional) >\nsteps: < steps value (1-70, optional) >")
         return
 
     payload = parse_input(msgs[1])
     print(payload)
 
-    # The rest of the draw function remains unchanged
+    # Check if xds is used in the payload
+    if "xds" in msgs[1].lower():
+        message.reply_text("`xds` key cannot be used in the `/draw` command. Use `/img` instead.")
+        return
 
-    K = message.reply_text("Please Wait 10-15 Second")
-    r = requests.post(url=f"{SD_URL}/sdapi/v1/txt2img", json=payload).json()
+    K = message.reply_text("Please Wait 10-15 Seconds")
+    r = call_api('sdapi/v1/txt2img', payload)
 
-    def genr():
-        unique_id = str(uuid.uuid4())[:7]
-        return f"{message.from_user.first_name}-{unique_id}"
-
-    word = genr()
-
-    for i in r["images"]:
-        image = Image.open(io.BytesIO(base64.b64decode(i.split(",", 1)[0])))
-
-        png_payload = {"image": "data:image/png;base64," + i}
-        response2 = requests.post(url=f"{SD_URL}/sdapi/v1/png-info", json=png_payload)
-
-        pnginfo = PngImagePlugin.PngInfo()
-        pnginfo.add_text("parameters", response2.json().get("info"))
-        image.save(f"{word}.png", pnginfo=pnginfo)
-
-        # Add a flag to check if the user provided a seed value
-        user_provided_seed = "seed" in payload
-
-        info_dict = response2.json()
-        seed_value = info_dict['info'].split(", Seed: ")[1].split(",")[0]
-        # print(seed_value)
-
-        caption = f"**[{message.from_user.first_name}-Kun](tg://user?id={message.from_user.id})**\n\n"
-        for key, value in payload.items():
-            caption += f"{key.capitalize()} - **{value}**\n"
-        caption += f"Seed - **{seed_value}**\n"
-
-        message.reply_photo(
-            photo=f"{word}.png",
-            caption=caption,
-        )
+    if r:
+        for i in r["images"]:
+            word, info = process_images([i], message.from_user.id, message.from_user.first_name)
+            caption = create_caption(payload, message.from_user.first_name, message.from_user.id, info)
+            message.reply_photo(photo=f"{IMAGE_PATH}/{word}.png", caption=caption)
+        K.delete()
+    else:
+        message.reply_text("Failed to generate image. Please try again later.")
+        K.delete()
 
 
-        # os.remove(f"{word}.png")
+@app.on_message(filters.command(["img"]))
+def img2img(client, message):
+    if not message.reply_to_message or not message.reply_to_message.photo:
+        message.reply_text("Reply to an image with\n`/img < prompt > ds:0-1.0`\n\nds stands for `Denoising_strength` parameter. Set that low (like 0.2) if you just want to slightly change things. defaults to 0.35\n\nExample: `/img murder on the dance floor ds:0.2`")
+        return
+
+    msgs = message.text.split(" ", 1)
+    if len(msgs) == 1:
+        message.reply_text("dont FAIL in life")
+        return
+
+    payload = parse_input(msgs[1])
+    print(f"input:\n{payload}")
+    photo = message.reply_to_message.photo
+    # prompt_from_reply = message.reply_to_message.
+    # orginal_prompt = app.reply_to_message.message
+    # print(orginal_prompt)
+    photo_file = app.download_media(photo)
+    init_image = encode_file_to_base64(photo_file)
+    os.remove(photo_file)  # Clean up downloaded image file
+
+    payload["init_images"] = [init_image]
+
+    K = message.reply_text("Please Wait 10-15 Seconds")
+    r = call_api('sdapi/v1/img2img', payload)
+
+    if r:
+        for i in r["images"]:
+            word, info = process_images([i], message.from_user.id, message.from_user.first_name)
+            caption = create_caption(payload, message.from_user.first_name, message.from_user.id, info)
+            message.reply_photo(photo=f"{IMAGE_PATH}/{word}.png", caption=caption)
+        K.delete()
+    else:
+        message.reply_text("Failed to process image. Please try again later.")
         K.delete()
 
 
 @app.on_message(filters.command(["getmodels"]))
 async def get_models(client, message):
-    response = requests.get(url=f"{SD_URL}/sdapi/v1/sd-models")
-    if response.status_code == 200:
+    try:
+        response = requests.get(f"{SD_URL}/sdapi/v1/sd-models")
+        response.raise_for_status()
         models_json = response.json()
-        # create buttons for each model name
-        buttons = []
-        for model in models_json:
-            buttons.append(
-                [
-                    InlineKeyboardButton(
-                        model["title"], callback_data=model["model_name"]
-                    )
-                ]
-            )
-        # send the message
-        await message.reply_text(
-            text="Select a model [checkpoint] to use",
-            reply_markup=InlineKeyboardMarkup(buttons),
-        )
+        print(models_json)
+        buttons = [
+            [InlineKeyboardButton(model["title"], callback_data=model["model_name"])]
+            for model in models_json
+        ]
+        await message.reply_text("Select a model [checkpoint] to use", reply_markup=InlineKeyboardMarkup(buttons))
+    except requests.RequestException as e:
+        await message.reply_text(f"Failed to get models: {e}")
 
 
 @app.on_callback_query()
 async def process_callback(client, callback_query):
-    # if a model button is clicked, set sd_model_checkpoint to the selected model's title
     sd_model_checkpoint = callback_query.data
-
-    # The sd_model_checkpoint needs to be set to the title from /sdapi/v1/sd-models
-    # post using /sdapi/v1/options
-
     options = {"sd_model_checkpoint": sd_model_checkpoint}
 
-    # post the options
-    response = requests.post(url=f"{SD_URL}/sdapi/v1/options", json=options)
-    if response.status_code == 200:
-        # if the post was successful, send a message
-        await callback_query.message.reply_text(
-            "checpoint set to " + sd_model_checkpoint
-        )
-    else:
-        # if the post was unsuccessful, send an error message
-        await callback_query.message.reply_text("Error setting options")
+    try:
+        response = requests.post(f"{SD_URL}/sdapi/v1/options", json=options)
+        response.raise_for_status()
+
+        # Update the negative prompt based on the selected model
+        update_negative_prompt(sd_model_checkpoint)
+        
+        await callback_query.message.reply_text(f"Checkpoint set to {sd_model_checkpoint}")
+    except requests.RequestException as e:
+        await callback_query.message.reply_text(f"Failed to set checkpoint: {e}")
+        print(f"Error setting checkpoint: {e}")
 
 
-@app.on_message(filters.command(["start"], prefixes=["/", "!"]))
-async def start(client, message):
-    # Photo = "https://i.imgur.com/79hHVX6.png"
+@app.on_message(filters.command(["info_sd_bot"]))
+async def info(client, message):
+    await message.reply_text("""
+now support for xyz scripts, see [sd wiki](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Features#xyz-plot) !
+currently supported 
+`xsr` - search replace text/emoji in the prompt, more info [here](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Features#prompt-sr) 
+`xds` - denoise strength, only valid for img2img
+`xsteps` - steps
+**note** limit the overall `steps:` to lower value (10-20) for big xyz plots
 
-    buttons = [
-        [
-            InlineKeyboardButton(
-                "Add to your group", url="https://t.me/gootmornbot?startgroup=true"
-            )
-        ]
-    ]
-    await message.reply_text(
-        # photo=Photo,
-        text=f"Hello!\nask me to imagine anything\n\n/draw text to image",
-        reply_markup=InlineKeyboardMarkup(buttons),
-    )
+aside from that you can use the usual `ng`, `ds`, `cfg`, `steps` for single image generation.
+""", disable_web_page_preview=True)
 
 
 app.run()

requirements.txt

@@ -1,4 +1,4 @@
-pyrogram==1.4.16
+pyrogram
 requests
 tgcrypto==1.2.2
 Pillow