import torch from diffsynth.pipelines.minimax_h3_image import MiniMaxH3ImagePipeline, ModelConfig from diffsynth.core.quant import QuantizeConfig from PIL import Image pipe = MiniMaxH3ImagePipeline.from_pretrained( torch_dtype=torch.bfloat16, device="cuda", model_configs=[ ModelConfig(model_id="MiniMax/MiniMax-H3", origin_file_pattern="FL2VA/text_encoder/model*.safetensors"), ModelConfig(model_id="MiniMax/MiniMax-H3-Image", origin_file_pattern="transformer/model*.safetensors"), ModelConfig(model_id="MiniMax/MiniMax-H3-Image", origin_file_pattern="pdd_fused_heads.safetensors"), ModelConfig(model_id="MiniMax/MiniMax-H3-Image", origin_file_pattern="vae/diffusion_pytorch_model.safetensors"), ], processor_config=ModelConfig(model_id="MiniMax/MiniMax-H3-Image", origin_file_pattern="processor/"), vram_limit=torch.cuda.mem_get_info("cuda")[1] / (1024 ** 3) - 2, ) prompt = ( "An overhead photograph of a rustic farm-to-table spread on a weathered wooden table: a round loaf of sourdough " "on burlap, wedges of cheese on a dark board, a copper bowl of vegetables, vine tomatoes, olives and walnuts, " "warm afternoon light raking across the grain of the wood." ) image = pipe(prompt=prompt, height=4096, width=4096, seed=42) image.save("MiniMax-H3-Image.jpg") prompt = "Change the color of the tomato in to green." image = pipe( prompt=prompt, height=4096, width=4096, seed=43, edit_image=[Image.open("MiniMax-H3-Image.jpg")], ) image.save("MiniMax-H3-Image-Edit.jpg")