| { |
| "_class_name": "FluxPipeline", |
| "_diffusers_version": "0.19.0", |
| "force_zeros_for_empty_prompt": true, |
| "add_watermarker": false, |
| "feature_extractor": [ |
| "transformers", |
| "CLIPImageProcessor" |
| ], |
| "text_encoder": [ |
| "transformers", |
| "CLIPTextModel" |
| ], |
| "text_encoder_2": [ |
| "transformers", |
| "CLIPTextModelWithProjection" |
| ], |
| "tokenizer": [ |
| "transformers", |
| "CLIPTokenizer" |
| ], |
| "tokenizer_2": [ |
| "transformers", |
| "CLIPTokenizer" |
| ], |
| "transformer": [ |
| "diffusers", |
| "FluxTransformerModel" |
| ], |
| "vae": [ |
| "diffusers", |
| "AutoencoderKL" |
| ], |
| "model_type": "flux-rectified-flow", |
| "architecture": "rectified-flow-transformer", |
| "parameters": 12000000000, |
| "prediction_type": "flow", |
| "max_sequence_length": 256, |
| "requires_safety_checker": false, |
| "safety_checker": null, |
| "original_model": "black-forest-labs/FLUX.1-dev", |
| "model_description": "A development version of the 12 billion parameter rectified flow transformer capable of generating images from text descriptions using a hybrid architecture of multimodal and parallel diffusion transformer blocks", |
| "quantization": { |
| "method": "mflux", |
| "version": "0.6.2", |
| "bits": 8, |
| "original_dtype": "float16" |
| }, |
| "memory_requirements": { |
| "original_fp16": "~57 GB", |
| "quantized_8bit": "~18 GB" |
| }, |
| "recommended_inference_parameters": { |
| "steps": 25, |
| "guidance_scale": 0.0, |
| "max_sequence_length": 256 |
| }, |
| "license": "apache-2.0" |
| } |
|
|
