├── LICENSE ├── README.md ├── clean-ui.py ├── img ├── .gitkeep ├── preview.png └── selection.png ├── requirements.txt └── run.bat /LICENSE: -------------------------------------------------------------------------------- 1 | Apache License 2 | Version 2.0, January 2004 3 | http://www.apache.org/licenses/ 4 | 5 | TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 6 | 7 | 1. Definitions. 8 | 9 | "License" shall mean the terms and conditions for use, reproduction, 10 | and distribution as defined by Sections 1 through 9 of this document. 11 | 12 | "Licensor" shall mean the copyright owner or entity authorized by 13 | the copyright owner that is granting the License. 14 | 15 | "Legal Entity" shall mean the union of the acting entity and all 16 | other entities that control, are controlled by, or are under common 17 | control with that entity. For the purposes of this definition, 18 | "control" means (i) the power, direct or indirect, to cause the 19 | direction or management of such entity, whether by contract or 20 | otherwise, or (ii) ownership of fifty percent (50%) or more of the 21 | outstanding shares, or (iii) beneficial ownership of such entity. 22 | 23 | "You" (or "Your") shall mean an individual or Legal Entity 24 | exercising permissions granted by this License. 25 | 26 | "Source" form shall mean the preferred form for making modifications, 27 | including but not limited to software source code, documentation 28 | source, and configuration files. 29 | 30 | "Object" form shall mean any form resulting from mechanical 31 | transformation or translation of a Source form, including but 32 | not limited to compiled object code, generated documentation, 33 | and conversions to other media types. 34 | 35 | "Work" shall mean the work of authorship, whether in Source or 36 | Object form, made available under the License, as indicated by a 37 | copyright notice that is included in or attached to the work 38 | (an example is provided in the Appendix below). 39 | 40 | "Derivative Works" shall mean any work, whether in Source or Object 41 | form, that is based on (or derived from) the Work and for which the 42 | editorial revisions, annotations, elaborations, or other modifications 43 | represent, as a whole, an original work of authorship. For the purposes 44 | of this License, Derivative Works shall not include works that remain 45 | separable from, or merely link (or bind by name) to the interfaces of, 46 | the Work and Derivative Works thereof. 47 | 48 | "Contribution" shall mean any work of authorship, including 49 | the original version of the Work and any modifications or additions 50 | to that Work or Derivative Works thereof, that is intentionally 51 | submitted to Licensor for inclusion in the Work by the copyright owner 52 | or by an individual or Legal Entity authorized to submit on behalf of 53 | the copyright owner. For the purposes of this definition, "submitted" 54 | means any form of electronic, verbal, or written communication sent 55 | to the Licensor or its representatives, including but not limited to 56 | communication on electronic mailing lists, source code control systems, 57 | and issue tracking systems that are managed by, or on behalf of, the 58 | Licensor for the purpose of discussing and improving the Work, but 59 | excluding communication that is conspicuously marked or otherwise 60 | designated in writing by the copyright owner as "Not a Contribution." 61 | 62 | "Contributor" shall mean Licensor and any individual or Legal Entity 63 | on behalf of whom a Contribution has been received by Licensor and 64 | subsequently incorporated within the Work. 65 | 66 | 2. Grant of Copyright License. Subject to the terms and conditions of 67 | this License, each Contributor hereby grants to You a perpetual, 68 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 69 | copyright license to reproduce, prepare Derivative Works of, 70 | publicly display, publicly perform, sublicense, and distribute the 71 | Work and such Derivative Works in Source or Object form. 72 | 73 | 3. Grant of Patent License. Subject to the terms and conditions of 74 | this License, each Contributor hereby grants to You a perpetual, 75 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 76 | (except as stated in this section) patent license to make, have made, 77 | use, offer to sell, sell, import, and otherwise transfer the Work, 78 | where such license applies only to those patent claims licensable 79 | by such Contributor that are necessarily infringed by their 80 | Contribution(s) alone or by combination of their Contribution(s) 81 | with the Work to which such Contribution(s) was submitted. If You 82 | institute patent litigation against any entity (including a 83 | cross-claim or counterclaim in a lawsuit) alleging that the Work 84 | or a Contribution incorporated within the Work constitutes direct 85 | or contributory patent infringement, then any patent licenses 86 | granted to You under this License for that Work shall terminate 87 | as of the date such litigation is filed. 88 | 89 | 4. Redistribution. You may reproduce and distribute copies of the 90 | Work or Derivative Works thereof in any medium, with or without 91 | modifications, and in Source or Object form, provided that You 92 | meet the following conditions: 93 | 94 | (a) You must give any other recipients of the Work or 95 | Derivative Works a copy of this License; and 96 | 97 | (b) You must cause any modified files to carry prominent notices 98 | stating that You changed the files; and 99 | 100 | (c) You must retain, in the Source form of any Derivative Works 101 | that You distribute, all copyright, patent, trademark, and 102 | attribution notices from the Source form of the Work, 103 | excluding those notices that do not pertain to any part of 104 | the Derivative Works; and 105 | 106 | (d) If the Work includes a "NOTICE" text file as part of its 107 | distribution, then any Derivative Works that You distribute must 108 | include a readable copy of the attribution notices contained 109 | within such NOTICE file, excluding those notices that do not 110 | pertain to any part of the Derivative Works, in at least one 111 | of the following places: within a NOTICE text file distributed 112 | as part of the Derivative Works; within the Source form or 113 | documentation, if provided along with the Derivative Works; or, 114 | within a display generated by the Derivative Works, if and 115 | wherever such third-party notices normally appear. The contents 116 | of the NOTICE file are for informational purposes only and 117 | do not modify the License. You may add Your own attribution 118 | notices within Derivative Works that You distribute, alongside 119 | or as an addendum to the NOTICE text from the Work, provided 120 | that such additional attribution notices cannot be construed 121 | as modifying the License. 122 | 123 | You may add Your own copyright statement to Your modifications and 124 | may provide additional or different license terms and conditions 125 | for use, reproduction, or distribution of Your modifications, or 126 | for any such Derivative Works as a whole, provided Your use, 127 | reproduction, and distribution of the Work otherwise complies with 128 | the conditions stated in this License. 129 | 130 | 5. Submission of Contributions. Unless You explicitly state otherwise, 131 | any Contribution intentionally submitted for inclusion in the Work 132 | by You to the Licensor shall be under the terms and conditions of 133 | this License, without any additional terms or conditions. 134 | Notwithstanding the above, nothing herein shall supersede or modify 135 | the terms of any separate license agreement you may have executed 136 | with Licensor regarding such Contributions. 137 | 138 | 6. Trademarks. This License does not grant permission to use the trade 139 | names, trademarks, service marks, or product names of the Licensor, 140 | except as required for reasonable and customary use in describing the 141 | origin of the Work and reproducing the content of the NOTICE file. 142 | 143 | 7. Disclaimer of Warranty. Unless required by applicable law or 144 | agreed to in writing, Licensor provides the Work (and each 145 | Contributor provides its Contributions) on an "AS IS" BASIS, 146 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or 147 | implied, including, without limitation, any warranties or conditions 148 | of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A 149 | PARTICULAR PURPOSE. You are solely responsible for determining the 150 | appropriateness of using or redistributing the Work and assume any 151 | risks associated with Your exercise of permissions under this License. 152 | 153 | 8. Limitation of Liability. In no event and under no legal theory, 154 | whether in tort (including negligence), contract, or otherwise, 155 | unless required by applicable law (such as deliberate and grossly 156 | negligent acts) or agreed to in writing, shall any Contributor be 157 | liable to You for damages, including any direct, indirect, special, 158 | incidental, or consequential damages of any character arising as a 159 | result of this License or out of the use or inability to use the 160 | Work (including but not limited to damages for loss of goodwill, 161 | work stoppage, computer failure or malfunction, or any and all 162 | other commercial damages or losses), even if such Contributor 163 | has been advised of the possibility of such damages. 164 | 165 | 9. Accepting Warranty or Additional Liability. While redistributing 166 | the Work or Derivative Works thereof, You may choose to offer, 167 | and charge a fee for, acceptance of support, warranty, indemnity, 168 | or other liability obligations and/or rights consistent with this 169 | License. However, in accepting such obligations, You may act only 170 | on Your own behalf and on Your sole responsibility, not on behalf 171 | of any other Contributor, and only if You agree to indemnify, 172 | defend, and hold each Contributor harmless for any liability 173 | incurred by, or claims asserted against, such Contributor by reason 174 | of your accepting any such warranty or additional liability. 175 | 176 | END OF TERMS AND CONDITIONS 177 | 178 | APPENDIX: How to apply the Apache License to your work. 179 | 180 | To apply the Apache License to your work, attach the following 181 | boilerplate notice, with the fields enclosed by brackets "[]" 182 | replaced with your own identifying information. (Don't include 183 | the brackets!) The text should be enclosed in the appropriate 184 | comment syntax for the file format. We also recommend that a 185 | file or class name and description of purpose be included on the 186 | same "printed page" as the copyright notice for easier 187 | identification within third-party archives. 188 | 189 | Copyright [yyyy] [name of copyright owner] 190 | 191 | Licensed under the Apache License, Version 2.0 (the "License"); 192 | you may not use this file except in compliance with the License. 193 | You may obtain a copy of the License at 194 | 195 | http://www.apache.org/licenses/LICENSE-2.0 196 | 197 | Unless required by applicable law or agreed to in writing, software 198 | distributed under the License is distributed on an "AS IS" BASIS, 199 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 200 | See the License for the specific language governing permissions and 201 | limitations under the License. 202 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | 2 | # Clean-UI for Multi-Modal Vision Models 3 | 4 | This project offers a user-friendly interface for working with the **Llama-3.2-11B-Vision** and **Molmo-7B-D** models. 5 | 6 | In this case, both the **Llama-3.2-11B-Vision-bnb-4bit** and **Molmo-7B-D-bnb-4bit** models need 12GB of VRAM to run. 7 | 8 | The model selection is done via the command line: 9 | 10 | ![](img/selection.png) 11 | 12 | 13 | ![](img/preview.png) 14 | ## Installation 15 | 16 | To set up and run this project on your local machine, follow the steps below: 17 | 18 | ### 1. Clone the Repository 19 | 20 | Copy the repository to a convenient location on your computer: 21 | 22 | ```bash 23 | git clone 24 | cd 25 | ``` 26 | 27 | ### 2. Create a Virtual Environment 28 | 29 | Inside the cloned repository, create a virtual environment using the following command: 30 | 31 | ```bash 32 | python -m venv venv-ui 33 | ``` 34 | 35 | ### 3. Activate the Virtual Environment 36 | 37 | Activate the virtual environment using: 38 | 39 | ```bash 40 | .\venv-ui\Scripts\activate 41 | ``` 42 | 43 | ### 4. Install Dependencies 44 | 45 | After activating the virtual environment, install the necessary dependencies from `requirements.txt`: 46 | 47 | ```bash 48 | pip install -r requirements.txt 49 | ``` 50 | Install Torch and TorchVision using separate commands: 51 | ```bash 52 | pip install torch==2.4.1+cu121 --index-url https://download.pytorch.org/whl/cu121 53 | ``` 54 | and 55 | 56 | ```bash 57 | pip install torchvision==0.19.1+cu121 --index-url https://download.pytorch.org/whl/cu121 58 | ``` 59 | ## Usage 60 | 61 | To start the UI, you can either: 62 | 63 | - Use the **run.bat** script (Windows only) 64 | 65 | Simply double-click on `run.bat` or 66 | 67 | 1. Activate the virtual environment: 68 | 69 | - Windows: 70 | ```bash 71 | .\venv-ui\Scripts\activate 72 | ``` 73 | 74 | 2. Run the Python script: 75 | 76 | ```bash 77 | python clean-ui.py 78 | ``` 79 | 80 | ## Features 81 | 82 | - Upload an image and enter a prompt to generate an image description. 83 | - Adjustable parameters such as temperature, top-k, and top-p for more control over the generated text. 84 | - Chatbot history to display prompt-response interactions. 85 | 86 | ## License 87 | 88 | This project is licensed under the MIT License. See the [LICENSE](LICENSE) file for more details. 89 | -------------------------------------------------------------------------------- /clean-ui.py: -------------------------------------------------------------------------------- 1 | import gradio as gr 2 | import torch 3 | import os 4 | from PIL import Image 5 | from transformers import MllamaForConditionalGeneration, AutoModelForCausalLM, AutoProcessor, GenerationConfig 6 | 7 | # Set memory management for PyTorch 8 | os.environ['PYTORCH_CUDA_ALLOC_CONF'] = 'max_split_size_mb:128' # or adjust size as needed 9 | 10 | # Model selection menu in terminal 11 | print("Select a model to load:") 12 | print("1. Llama-3.2-11B-Vision-Instruct-bnb-4bit") 13 | print("2. Molmo-7B-D-bnb-4bit") 14 | model_choice = input("Enter the number of the model you want to use: ") 15 | 16 | if model_choice == "1": 17 | model_id = "unsloth/Llama-3.2-11B-Vision-Instruct-bnb-4bit" 18 | model = MllamaForConditionalGeneration.from_pretrained( 19 | model_id, 20 | torch_dtype=torch.bfloat16, 21 | device_map="auto", 22 | ) 23 | processor = AutoProcessor.from_pretrained(model_id) 24 | 25 | elif model_choice == "2": 26 | model_id = "cyan2k/molmo-7B-D-bnb-4bit" 27 | arguments = {"device_map": "auto", "torch_dtype": "auto", "trust_remote_code": True} 28 | model = AutoModelForCausalLM.from_pretrained(model_id, **arguments) 29 | processor = AutoProcessor.from_pretrained(model_id, **arguments) 30 | 31 | else: 32 | raise ValueError("Invalid model choice. Please enter 1 or 2.") 33 | 34 | # Visual theme 35 | visual_theme = gr.themes.Default() # Default, Soft or Monochrome 36 | 37 | # Constants 38 | MAX_OUTPUT_TOKENS = 2048 39 | MAX_IMAGE_SIZE = (1120, 1120) 40 | 41 | # Function to process the image and generate a description 42 | def describe_image(image, user_prompt, temperature, top_k, top_p, max_tokens, history): 43 | # Resize image if necessary 44 | image = image.resize(MAX_IMAGE_SIZE) 45 | 46 | # Initialize cleaned_output variable 47 | cleaned_output = "" 48 | 49 | # Prepare prompt with user input based on selected model 50 | if model_choice == "1": # Llama Model 51 | prompt = f"<|image|><|begin_of_text|>{user_prompt} Answer:" 52 | # Preprocess the image and prompt 53 | inputs = processor(image, prompt, return_tensors="pt").to(model.device) 54 | 55 | # Generate output with model 56 | output = model.generate( 57 | **inputs, 58 | max_new_tokens=min(max_tokens, MAX_OUTPUT_TOKENS), 59 | temperature=temperature, 60 | top_k=top_k, 61 | top_p=top_p 62 | ) 63 | 64 | # Decode the raw output 65 | raw_output = processor.decode(output[0]) 66 | 67 | # Clean up the output to remove system tokens 68 | cleaned_output = raw_output.replace("<|image|><|begin_of_text|>", "").strip().replace(" Answer:", "") 69 | 70 | elif model_choice == "2": # Molmo Model 71 | # Prepare inputs for Molmo model 72 | inputs = processor.process(images=[image], text=user_prompt) 73 | inputs = {k: v.to(model.device).unsqueeze(0) for k, v in inputs.items()} 74 | 75 | # Generate output with model, applying the parameters for temperature, top_k, top_p, and max_tokens 76 | output = model.generate_from_batch( 77 | inputs, 78 | GenerationConfig( 79 | max_new_tokens=min(max_tokens, MAX_OUTPUT_TOKENS), 80 | temperature=temperature, 81 | top_k=top_k, 82 | top_p=top_p, 83 | stop_strings="<|endoftext|>", 84 | do_sample=True 85 | ), 86 | tokenizer=processor.tokenizer, 87 | ) 88 | 89 | # Extract generated tokens and decode them to text 90 | generated_tokens = output[0, inputs["input_ids"].size(1):] 91 | cleaned_output = processor.tokenizer.decode(generated_tokens, skip_special_tokens=True) 92 | 93 | # Ensure the prompt is not repeated in the output 94 | if cleaned_output.startswith(user_prompt): 95 | cleaned_output = cleaned_output[len(user_prompt):].strip() 96 | 97 | # Append the new conversation to the history 98 | history.append((user_prompt, cleaned_output)) 99 | 100 | return history 101 | 102 | # Function to clear the chat history 103 | def clear_chat(): 104 | return [] 105 | 106 | # Gradio Interface 107 | def gradio_interface(): 108 | with gr.Blocks(visual_theme) as demo: 109 | gr.HTML( 110 | """ 111 |

112 | Clean-UI 113 |

114 | """) 115 | with gr.Row(): 116 | # Left column with image and parameter inputs 117 | with gr.Column(scale=1): 118 | image_input = gr.Image( 119 | label="Image", 120 | type="pil", 121 | image_mode="RGB", 122 | height=512, # Set the height 123 | width=512 # Set the width 124 | ) 125 | 126 | # Parameter sliders 127 | temperature = gr.Slider( 128 | label="Temperature", minimum=0.1, maximum=2.0, value=0.6, step=0.1, interactive=True) 129 | top_k = gr.Slider( 130 | label="Top-k", minimum=1, maximum=100, value=50, step=1, interactive=True) 131 | top_p = gr.Slider( 132 | label="Top-p", minimum=0.1, maximum=1.0, value=0.9, step=0.1, interactive=True) 133 | max_tokens = gr.Slider( 134 | label="Max Tokens", minimum=50, maximum=MAX_OUTPUT_TOKENS, value=100, step=50, interactive=True) 135 | 136 | # Right column with the chat interface 137 | with gr.Column(scale=2): 138 | chat_history = gr.Chatbot(label="Chat", height=512) 139 | 140 | # User input box for prompt 141 | user_prompt = gr.Textbox( 142 | show_label=False, 143 | container=False, 144 | placeholder="Enter your prompt", 145 | lines=2 146 | ) 147 | 148 | # Generate and Clear buttons 149 | with gr.Row(): 150 | generate_button = gr.Button("Generate") 151 | clear_button = gr.Button("Clear") 152 | 153 | # Define the action for the generate button 154 | generate_button.click( 155 | fn=describe_image, 156 | inputs=[image_input, user_prompt, temperature, top_k, top_p, max_tokens, chat_history], 157 | outputs=[chat_history] 158 | ) 159 | 160 | # Define the action for the clear button 161 | clear_button.click( 162 | fn=clear_chat, 163 | inputs=[], 164 | outputs=[chat_history] 165 | ) 166 | 167 | return demo 168 | 169 | # Launch the interface 170 | demo = gradio_interface() 171 | demo.launch() 172 | -------------------------------------------------------------------------------- /img/.gitkeep: -------------------------------------------------------------------------------- 1 | 2 | -------------------------------------------------------------------------------- /img/preview.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ThetaCursed/clean-ui/3f8c768c80742cbf13a88035ae83bf16f5160be6/img/preview.png -------------------------------------------------------------------------------- /img/selection.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ThetaCursed/clean-ui/3f8c768c80742cbf13a88035ae83bf16f5160be6/img/selection.png -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- 1 | transformers==4.45.1 2 | gradio==4.44.0 3 | accelerate==0.34.2 4 | bitsandbytes==0.44.0 5 | tensorflow-cpu==2.17.0 6 | einops==0.8.0 7 | -------------------------------------------------------------------------------- /run.bat: -------------------------------------------------------------------------------- 1 | @echo off 2 | call .\venv-ui\Scripts\activate :: Activates the virtual environment 3 | python clean-ui.py :: Runs the Python script 4 | pause :: Keeps the window open after execution 5 | --------------------------------------------------------------------------------