├── pre-requirements.txt ├── requirements.txt ├── app.py ├── README.md └── LICENSE /pre-requirements.txt: -------------------------------------------------------------------------------- 1 | pip>=23.0.0 -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- 1 | git+https://github.com/huggingface/transformers.git 2 | git+https://github.com/huggingface/accelerate.git 3 | git+https://github.com/huggingface/diffusers.git 4 | git+https://github.com/huggingface/peft.git 5 | transformers-stream-generator 6 | huggingface_hub 7 | optimum-quanto 8 | sentencepiece 9 | opencv-python 10 | torchvision 11 | safetensors 12 | xformers 13 | requests 14 | hf_xet 15 | spaces 16 | pillow 17 | gradio 18 | einops 19 | torch 20 | timm 21 | -------------------------------------------------------------------------------- /app.py: -------------------------------------------------------------------------------- 1 | import torch 2 | import gradio as gr 3 | import spaces 4 | 5 | from optimum.quanto import freeze, qfloat8, quantize 6 | 7 | from diffusers import FlowMatchEulerDiscreteScheduler, AutoencoderKL 8 | from diffusers.models.transformers.transformer_flux import FluxTransformer2DModel 9 | from diffusers.pipelines.flux.pipeline_flux import FluxPipeline 10 | from transformers import CLIPTextModel, CLIPTokenizer,T5EncoderModel, T5TokenizerFast 11 | 12 | # --- Model and Pipeline Setup --- 13 | dtype = torch.bfloat16 14 | 15 | bfl_repo = "black-forest-labs/FLUX.1-dev" 16 | revision = "refs/pr/1" 17 | local_path = "FLUX.1-dev-4bit" # Assuming the quantized models are in this local directory 18 | 19 | # It's good practice to have a function to load the models to keep the global namespace clean. 20 | def load_pipeline(): 21 | scheduler = FlowMatchEulerDiscreteScheduler.from_pretrained(bfl_repo, subfolder="scheduler", revision=revision) 22 | text_encoder = CLIPTextModel.from_pretrained("openai/clip-vit-large-patch14", torch_dtype=dtype) 23 | tokenizer = CLIPTokenizer.from_pretrained("openai/clip-vit-large-patch14") # Removed torch_dtype for tokenizer 24 | text_encoder_2 = torch.load(local_path + '/text_encoder_2.pt') 25 | tokenizer_2 = T5TokenizerFast.from_pretrained(bfl_repo, subfolder="tokenizer_2", revision=revision) # Removed torch_dtype for tokenizer 26 | vae = AutoencoderKL.from_pretrained(bfl_repo, subfolder="vae", torch_dtype=dtype, revision=revision) 27 | transformer = torch.load(local_path + '/transformer.pt') 28 | 29 | pipe = FluxPipeline( 30 | scheduler=scheduler, 31 | text_encoder=text_encoder, 32 | tokenizer=tokenizer, 33 | text_encoder_2=None, 34 | tokenizer_2=tokenizer_2, 35 | vae=vae, 36 | transformer=None, 37 | ) 38 | pipe.text_encoder_2 = text_encoder_2 39 | pipe.transformer = transformer 40 | pipe.to('cuda') 41 | return pipe 42 | 43 | # Load the pipeline 44 | pipe = load_pipeline() 45 | print('Pipeline loaded successfully.') 46 | 47 | @spaces.GPU 48 | # --- Gradio Inference Function --- 49 | def generate_image(prompt, guidance_scale, num_inference_steps, seed): 50 | """ 51 | Function to generate an image based on the prompt and other parameters. 52 | This function will be used by the Gradio interface. 53 | """ 54 | generator = torch.Generator("cuda").manual_seed(int(seed)) 55 | image = pipe( 56 | prompt, 57 | guidance_scale=guidance_scale, 58 | num_inference_steps=int(num_inference_steps), 59 | max_sequence_length=256, 60 | generator=generator 61 | ).images[0] 62 | return image 63 | 64 | # --- Gradio Interface --- 65 | with gr.Blocks(theme="bethecloud/storj_theme") as demo: 66 | gr.Markdown("# FLUX.1 Image Generation(4bit)") 67 | with gr.Row(): 68 | with gr.Column(): 69 | prompt_input = gr.Textbox(label="Prompt", value="a cute apple smiling") 70 | guidance_scale_slider = gr.Slider(minimum=0.0, maximum=10.0, step=0.1, value=0.0, label="Guidance Scale") 71 | steps_slider = gr.Slider(minimum=1, maximum=50, step=1, value=4, label="Number of Inference Steps") 72 | seed_input = gr.Number(label="Seed", value=12345) 73 | generate_button = gr.Button("Generate Image") 74 | with gr.Column(): 75 | output_image = gr.Image(label="Generated Image") 76 | 77 | generate_button.click( 78 | fn=generate_image, 79 | inputs=[prompt_input, guidance_scale_slider, steps_slider, seed_input], 80 | outputs=output_image 81 | ) 82 | 83 | # --- Launch the Gradio App --- 84 | if __name__ == "__main__": 85 | demo.launch() -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # **Flux.1-dev-4bit** 2 | 3 | A quantized version of FLUX.1-dev optimized for efficient image generation with reduced memory footprint through 4-bit quantization. This application provides a Gradio-based interface for generating high-quality images using the FLUX.1-dev model with 4-bit quantization. The quantized model maintains image quality while significantly reducing GPU memory requirements, making it accessible for users with limited hardware resources. 4 | 5 | ## Features 6 | 7 | - **4-bit Quantized Model**: Reduced memory usage while maintaining image quality 8 | - **Interactive Web Interface**: User-friendly Gradio interface for easy image generation 9 | - **Customizable Parameters**: Control guidance scale, inference steps, and random seed 10 | - **GPU Acceleration**: Optimized for CUDA-enabled GPUs 11 | - **Efficient Pipeline**: Streamlined inference process for faster generation 12 | 13 | ## Requirements 14 | 15 | ### Hardware 16 | - NVIDIA GPU with CUDA support 17 | - Minimum 8GB GPU memory (4-bit quantization reduces requirements significantly) 18 | 19 | ### Software Dependencies 20 | ``` 21 | torch 22 | gradio 23 | spaces 24 | optimum[quanto] 25 | diffusers 26 | transformers 27 | ``` 28 | 29 | ## Installation 30 | 31 | 1. Clone the repository: 32 | ```bash 33 | git clone https://github.com/PRITHIVSAKTHIUR/Flux.1-dev-4bit.git 34 | cd Flux.1-dev-4bit 35 | ``` 36 | 37 | 2. Install required dependencies: 38 | ```bash 39 | pip install torch gradio spaces optimum[quanto] diffusers transformers 40 | ``` 41 | 42 | 3. Ensure you have the quantized model files in the `FLUX.1-dev-4bit` directory: 43 | - `text_encoder_2.pt` 44 | - `transformer.pt` 45 | 46 | ## Usage 47 | 48 | ### Running the Application 49 | 50 | Start the Gradio interface: 51 | ```bash 52 | python app.py 53 | ``` 54 | 55 | The application will launch a web interface where you can: 56 | 57 | 1. **Enter a Prompt**: Describe the image you want to generate 58 | 2. **Adjust Guidance Scale**: Control how closely the model follows your prompt (0.0-10.0) 59 | 3. **Set Inference Steps**: Number of denoising steps (1-50, higher values may improve quality) 60 | 4. **Specify Seed**: For reproducible results 61 | 62 | ### Parameters 63 | 64 | - **Prompt**: Text description of the desired image 65 | - **Guidance Scale**: Controls prompt adherence (default: 0.0) 66 | - **Number of Inference Steps**: Denoising iterations (default: 4) 67 | - **Seed**: Random seed for reproducible generation (default: 12345) 68 | 69 | ## Model Details 70 | 71 | This implementation uses: 72 | - **Base Model**: black-forest-labs/FLUX.1-dev 73 | - **Text Encoder**: OpenAI CLIP ViT-Large-Patch14 74 | - **Secondary Text Encoder**: T5 (quantized to 4-bit) 75 | - **Transformer**: FLUX Transformer2D (quantized to 4-bit) 76 | - **VAE**: AutoencoderKL from FLUX.1-dev 77 | - **Scheduler**: FlowMatchEulerDiscreteScheduler 78 | 79 | ## Quantization Benefits 80 | 81 | The 4-bit quantization provides: 82 | - **Reduced Memory Usage**: Approximately 4x reduction in model size 83 | - **Faster Loading**: Quicker model initialization 84 | - **Lower Hardware Requirements**: Accessible on consumer GPUs 85 | - **Maintained Quality**: Minimal impact on generation quality 86 | 87 | ## Technical Implementation 88 | 89 | The application loads pre-quantized model components and constructs a custom FLUX pipeline. Key optimizations include: 90 | 91 | - Selective quantization of memory-intensive components (transformer and text_encoder_2) 92 | - Efficient model loading with torch.load for quantized components 93 | - GPU memory optimization through proper dtype handling 94 | 95 | ## Limitations 96 | 97 | - Requires CUDA-compatible GPU 98 | - Quantized models may have slight quality differences compared to full precision 99 | - Initial model loading time depends on storage speed 100 | - Limited to single image generation per inference 101 | 102 | ## License 103 | 104 | This project is licensed under the Apache License 2.0. See the LICENSE file for details. 105 | 106 | ## Contributing 107 | 108 | Contributions are welcome! Please feel free to submit issues, feature requests, or pull requests to improve the application. 109 | 110 | ## Acknowledgments 111 | 112 | - Black Forest Labs for the original FLUX.1-dev model 113 | - Hugging Face for the diffusers and transformers libraries 114 | - Gradio team for the interface framework 115 | - Optimum team for quantization tools 116 | -------------------------------------------------------------------------------- /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 | --------------------------------------------------------------------------------