From 64542598534529b58e737bf1caf1382d59533690 Mon Sep 17 00:00:00 2001 From: Artiprocher Date: Tue, 30 Dec 2025 16:43:41 +0800 Subject: [PATCH] support qwen-image-2512 --- README.md | 1 + README_zh.md | 1 + docs/en/Model_Details/Qwen-Image.md | 1 + docs/zh/Model_Details/Qwen-Image.md | 1 + .../model_inference/Qwen-Image-2512.py | 17 +++++++++++ .../Qwen-Image-2512.py | 28 +++++++++++++++++++ .../model_training/full/Qwen-Image-2512.sh | 13 +++++++++ .../model_training/lora/Qwen-Image-2512.sh | 16 +++++++++++ .../validate_full/Qwen-Image-2512.py | 20 +++++++++++++ .../validate_lora/Qwen-Image-2512.py | 18 ++++++++++++ 10 files changed, 116 insertions(+) create mode 100644 examples/qwen_image/model_inference/Qwen-Image-2512.py create mode 100644 examples/qwen_image/model_inference_low_vram/Qwen-Image-2512.py create mode 100644 examples/qwen_image/model_training/full/Qwen-Image-2512.sh create mode 100644 examples/qwen_image/model_training/lora/Qwen-Image-2512.sh create mode 100644 examples/qwen_image/model_training/validate_full/Qwen-Image-2512.py create mode 100644 examples/qwen_image/model_training/validate_lora/Qwen-Image-2512.py diff --git a/README.md b/README.md index 6e398d3..2e4a41a 100644 --- a/README.md +++ b/README.md @@ -396,6 +396,7 @@ Example code for Qwen-Image is available at: [/examples/qwen_image/](/examples/q | Model ID | Inference | Low-VRAM Inference | Full Training | Full Training Validation | LoRA Training | LoRA Training Validation | |-|-|-|-|-|-|-| |[Qwen/Qwen-Image](https://www.modelscope.cn/models/Qwen/Qwen-Image)|[code](/examples/qwen_image/model_inference/Qwen-Image.py)|[code](/examples/qwen_image/model_inference_low_vram/Qwen-Image.py)|[code](/examples/qwen_image/model_training/full/Qwen-Image.sh)|[code](/examples/qwen_image/model_training/validate_full/Qwen-Image.py)|[code](/examples/qwen_image/model_training/lora/Qwen-Image.sh)|[code](/examples/qwen_image/model_training/validate_lora/Qwen-Image.py)| +|[Qwen/Qwen-Image-2512](https://www.modelscope.cn/models/Qwen/Qwen-Image-2512)|[code](/examples/qwen_image/model_inference/Qwen-Image-2512.py)|[code](/examples/qwen_image/model_inference_low_vram/Qwen-Image-2512.py)|[code](/examples/qwen_image/model_training/full/Qwen-Image-2512.sh)|[code](/examples/qwen_image/model_training/validate_full/Qwen-Image-2512.py)|[code](/examples/qwen_image/model_training/lora/Qwen-Image-2512.sh)|[code](/examples/qwen_image/model_training/validate_lora/Qwen-Image-2512.py)| |[Qwen/Qwen-Image-Edit](https://www.modelscope.cn/models/Qwen/Qwen-Image-Edit)|[code](/examples/qwen_image/model_inference/Qwen-Image-Edit.py)|[code](/examples/qwen_image/model_inference_low_vram/Qwen-Image-Edit.py)|[code](/examples/qwen_image/model_training/full/Qwen-Image-Edit.sh)|[code](/examples/qwen_image/model_training/validate_full/Qwen-Image-Edit.py)|[code](/examples/qwen_image/model_training/lora/Qwen-Image-Edit.sh)|[code](/examples/qwen_image/model_training/validate_lora/Qwen-Image-Edit.py)| |[Qwen/Qwen-Image-Edit-2509](https://www.modelscope.cn/models/Qwen/Qwen-Image-Edit-2509)|[code](/examples/qwen_image/model_inference/Qwen-Image-Edit-2509.py)|[code](/examples/qwen_image/model_inference_low_vram/Qwen-Image-Edit-2509.py)|[code](/examples/qwen_image/model_training/full/Qwen-Image-Edit-2509.sh)|[code](/examples/qwen_image/model_training/validate_full/Qwen-Image-Edit-2509.py)|[code](/examples/qwen_image/model_training/lora/Qwen-Image-Edit-2509.sh)|[code](/examples/qwen_image/model_training/validate_lora/Qwen-Image-Edit-2509.py)| |[Qwen/Qwen-Image-Edit-2511](https://www.modelscope.cn/models/Qwen/Qwen-Image-Edit-2511)|[code](/examples/qwen_image/model_inference/Qwen-Image-Edit-2511.py)|[code](/examples/qwen_image/model_inference_low_vram/Qwen-Image-Edit-2511.py)|[code](/examples/qwen_image/model_training/full/Qwen-Image-Edit-2511.sh)|[code](/examples/qwen_image/model_training/validate_full/Qwen-Image-Edit-2511.py)|[code](/examples/qwen_image/model_training/lora/Qwen-Image-Edit-2511.sh)|[code](/examples/qwen_image/model_training/validate_lora/Qwen-Image-Edit-2511.py)| diff --git a/README_zh.md b/README_zh.md index 13799b5..8deb8bf 100644 --- a/README_zh.md +++ b/README_zh.md @@ -396,6 +396,7 @@ Qwen-Image 的示例代码位于：[/examples/qwen_image/](/examples/qwen_image/ |模型 ID|推理|低显存推理|全量训练|全量训练后验证|LoRA 训练|LoRA 训练后验证| |-|-|-|-|-|-|-| |[Qwen/Qwen-Image](https://www.modelscope.cn/models/Qwen/Qwen-Image)|[code](/examples/qwen_image/model_inference/Qwen-Image.py)|[code](/examples/qwen_image/model_inference_low_vram/Qwen-Image.py)|[code](/examples/qwen_image/model_training/full/Qwen-Image.sh)|[code](/examples/qwen_image/model_training/validate_full/Qwen-Image.py)|[code](/examples/qwen_image/model_training/lora/Qwen-Image.sh)|[code](/examples/qwen_image/model_training/validate_lora/Qwen-Image.py)| +|[Qwen/Qwen-Image-2512](https://www.modelscope.cn/models/Qwen/Qwen-Image-2512)|[code](/examples/qwen_image/model_inference/Qwen-Image-2512.py)|[code](/examples/qwen_image/model_inference_low_vram/Qwen-Image-2512.py)|[code](/examples/qwen_image/model_training/full/Qwen-Image-2512.sh)|[code](/examples/qwen_image/model_training/validate_full/Qwen-Image-2512.py)|[code](/examples/qwen_image/model_training/lora/Qwen-Image-2512.sh)|[code](/examples/qwen_image/model_training/validate_lora/Qwen-Image-2512.py)| |[Qwen/Qwen-Image-Edit](https://www.modelscope.cn/models/Qwen/Qwen-Image-Edit)|[code](/examples/qwen_image/model_inference/Qwen-Image-Edit.py)|[code](/examples/qwen_image/model_inference_low_vram/Qwen-Image-Edit.py)|[code](/examples/qwen_image/model_training/full/Qwen-Image-Edit.sh)|[code](/examples/qwen_image/model_training/validate_full/Qwen-Image-Edit.py)|[code](/examples/qwen_image/model_training/lora/Qwen-Image-Edit.sh)|[code](/examples/qwen_image/model_training/validate_lora/Qwen-Image-Edit.py)| |[Qwen/Qwen-Image-Edit-2509](https://www.modelscope.cn/models/Qwen/Qwen-Image-Edit-2509)|[code](/examples/qwen_image/model_inference/Qwen-Image-Edit-2509.py)|[code](/examples/qwen_image/model_inference_low_vram/Qwen-Image-Edit-2509.py)|[code](/examples/qwen_image/model_training/full/Qwen-Image-Edit-2509.sh)|[code](/examples/qwen_image/model_training/validate_full/Qwen-Image-Edit-2509.py)|[code](/examples/qwen_image/model_training/lora/Qwen-Image-Edit-2509.sh)|[code](/examples/qwen_image/model_training/validate_lora/Qwen-Image-Edit-2509.py)| |[Qwen/Qwen-Image-Edit-2511](https://www.modelscope.cn/models/Qwen/Qwen-Image-Edit-2511)|[code](/examples/qwen_image/model_inference/Qwen-Image-Edit-2511.py)|[code](/examples/qwen_image/model_inference_low_vram/Qwen-Image-Edit-2511.py)|[code](/examples/qwen_image/model_training/full/Qwen-Image-Edit-2511.sh)|[code](/examples/qwen_image/model_training/validate_full/Qwen-Image-Edit-2511.py)|[code](/examples/qwen_image/model_training/lora/Qwen-Image-Edit-2511.sh)|[code](/examples/qwen_image/model_training/validate_lora/Qwen-Image-Edit-2511.py)| diff --git a/docs/en/Model_Details/Qwen-Image.md b/docs/en/Model_Details/Qwen-Image.md index 9062d2a..3a7c1e6 100644 --- a/docs/en/Model_Details/Qwen-Image.md +++ b/docs/en/Model_Details/Qwen-Image.md @@ -81,6 +81,7 @@ graph LR; | Model ID | Inference | Low VRAM Inference | Full Training | Validation After Full Training | LoRA Training | Validation After LoRA Training | | - | - | - | - | - | - | - | | [Qwen/Qwen-Image](https://www.modelscope.cn/models/Qwen/Qwen-Image) | [code](/examples/qwen_image/model_inference/Qwen-Image.py) | [code](/examples/qwen_image/model_inference_low_vram/Qwen-Image.py) | [code](/examples/qwen_image/model_training/full/Qwen-Image.sh) | [code](/examples/qwen_image/model_training/validate_full/Qwen-Image.py) | [code](/examples/qwen_image/model_training/lora/Qwen-Image.sh) | [code](/examples/qwen_image/model_training/validate_lora/Qwen-Image.py) | +|[Qwen/Qwen-Image-2512](https://www.modelscope.cn/models/Qwen/Qwen-Image-2512)|[code](/examples/qwen_image/model_inference/Qwen-Image-2512.py)|[code](/examples/qwen_image/model_inference_low_vram/Qwen-Image-2512.py)|[code](/examples/qwen_image/model_training/full/Qwen-Image-2512.sh)|[code](/examples/qwen_image/model_training/validate_full/Qwen-Image-2512.py)|[code](/examples/qwen_image/model_training/lora/Qwen-Image-2512.sh)|[code](/examples/qwen_image/model_training/validate_lora/Qwen-Image-2512.py)| | [Qwen/Qwen-Image-Edit](https://www.modelscope.cn/models/Qwen/Qwen-Image-Edit) | [code](/examples/qwen_image/model_inference/Qwen-Image-Edit.py) | [code](/examples/qwen_image/model_inference_low_vram/Qwen-Image-Edit.py) | [code](/examples/qwen_image/model_training/full/Qwen-Image-Edit.sh) | [code](/examples/qwen_image/model_training/validate_full/Qwen-Image-Edit.py) | [code](/examples/qwen_image/model_training/lora/Qwen-Image-Edit.sh) | [code](/examples/qwen_image/model_training/validate_lora/Qwen-Image-Edit.py) | | [Qwen/Qwen-Image-Edit-2509](https://www.modelscope.cn/models/Qwen/Qwen-Image-Edit-2509) | [code](/examples/qwen_image/model_inference/Qwen-Image-Edit-2509.py) | [code](/examples/qwen_image/model_inference_low_vram/Qwen-Image-Edit-2509.py) | [code](/examples/qwen_image/model_training/full/Qwen-Image-Edit-2509.sh) | [code](/examples/qwen_image/model_training/validate_full/Qwen-Image-Edit-2509.py) | [code](/examples/qwen_image/model_training/lora/Qwen-Image-Edit-2509.sh) | [code](/examples/qwen_image/model_training/validate_lora/Qwen-Image-Edit-2509.py) | |[Qwen/Qwen-Image-Edit-2511](https://www.modelscope.cn/models/Qwen/Qwen-Image-Edit-2511)|[code](/examples/qwen_image/model_inference/Qwen-Image-Edit-2511.py)|[code](/examples/qwen_image/model_inference_low_vram/Qwen-Image-Edit-2511.py)|[code](/examples/qwen_image/model_training/full/Qwen-Image-Edit-2511.sh)|[code](/examples/qwen_image/model_training/validate_full/Qwen-Image-Edit-2511.py)|[code](/examples/qwen_image/model_training/lora/Qwen-Image-Edit-2511.sh)|[code](/examples/qwen_image/model_training/validate_lora/Qwen-Image-Edit-2511.py)| diff --git a/docs/zh/Model_Details/Qwen-Image.md b/docs/zh/Model_Details/Qwen-Image.md index 87ccba0..8fe9de4 100644 --- a/docs/zh/Model_Details/Qwen-Image.md +++ b/docs/zh/Model_Details/Qwen-Image.md @@ -81,6 +81,7 @@ graph LR; |模型 ID|推理|低显存推理|全量训练|全量训练后验证|LoRA 训练|LoRA 训练后验证| |-|-|-|-|-|-|-| |[Qwen/Qwen-Image](https://www.modelscope.cn/models/Qwen/Qwen-Image)|[code](/examples/qwen_image/model_inference/Qwen-Image.py)|[code](/examples/qwen_image/model_inference_low_vram/Qwen-Image.py)|[code](/examples/qwen_image/model_training/full/Qwen-Image.sh)|[code](/examples/qwen_image/model_training/validate_full/Qwen-Image.py)|[code](/examples/qwen_image/model_training/lora/Qwen-Image.sh)|[code](/examples/qwen_image/model_training/validate_lora/Qwen-Image.py)| +|[Qwen/Qwen-Image-2512](https://www.modelscope.cn/models/Qwen/Qwen-Image-2512)|[code](/examples/qwen_image/model_inference/Qwen-Image-2512.py)|[code](/examples/qwen_image/model_inference_low_vram/Qwen-Image-2512.py)|[code](/examples/qwen_image/model_training/full/Qwen-Image-2512.sh)|[code](/examples/qwen_image/model_training/validate_full/Qwen-Image-2512.py)|[code](/examples/qwen_image/model_training/lora/Qwen-Image-2512.sh)|[code](/examples/qwen_image/model_training/validate_lora/Qwen-Image-2512.py)| |[Qwen/Qwen-Image-Edit](https://www.modelscope.cn/models/Qwen/Qwen-Image-Edit)|[code](/examples/qwen_image/model_inference/Qwen-Image-Edit.py)|[code](/examples/qwen_image/model_inference_low_vram/Qwen-Image-Edit.py)|[code](/examples/qwen_image/model_training/full/Qwen-Image-Edit.sh)|[code](/examples/qwen_image/model_training/validate_full/Qwen-Image-Edit.py)|[code](/examples/qwen_image/model_training/lora/Qwen-Image-Edit.sh)|[code](/examples/qwen_image/model_training/validate_lora/Qwen-Image-Edit.py)| |[Qwen/Qwen-Image-Edit-2509](https://www.modelscope.cn/models/Qwen/Qwen-Image-Edit-2509)|[code](/examples/qwen_image/model_inference/Qwen-Image-Edit-2509.py)|[code](/examples/qwen_image/model_inference_low_vram/Qwen-Image-Edit-2509.py)|[code](/examples/qwen_image/model_training/full/Qwen-Image-Edit-2509.sh)|[code](/examples/qwen_image/model_training/validate_full/Qwen-Image-Edit-2509.py)|[code](/examples/qwen_image/model_training/lora/Qwen-Image-Edit-2509.sh)|[code](/examples/qwen_image/model_training/validate_lora/Qwen-Image-Edit-2509.py)| |[Qwen/Qwen-Image-Edit-2511](https://www.modelscope.cn/models/Qwen/Qwen-Image-Edit-2511)|[code](/examples/qwen_image/model_inference/Qwen-Image-Edit-2511.py)|[code](/examples/qwen_image/model_inference_low_vram/Qwen-Image-Edit-2511.py)|[code](/examples/qwen_image/model_training/full/Qwen-Image-Edit-2511.sh)|[code](/examples/qwen_image/model_training/validate_full/Qwen-Image-Edit-2511.py)|[code](/examples/qwen_image/model_training/lora/Qwen-Image-Edit-2511.sh)|[code](/examples/qwen_image/model_training/validate_lora/Qwen-Image-Edit-2511.py)| diff --git a/examples/qwen_image/model_inference/Qwen-Image-2512.py b/examples/qwen_image/model_inference/Qwen-Image-2512.py new file mode 100644 index 0000000..d00cf96 --- /dev/null +++ b/examples/qwen_image/model_inference/Qwen-Image-2512.py @@ -0,0 +1,17 @@ +from diffsynth.pipelines.qwen_image import QwenImagePipeline, ModelConfig +import torch + + +pipe = QwenImagePipeline.from_pretrained( + torch_dtype=torch.bfloat16, + device="cuda", + model_configs=[ + ModelConfig(model_id="Qwen/Qwen-Image-2512", origin_file_pattern="transformer/diffusion_pytorch_model*.safetensors"), + ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="text_encoder/model*.safetensors"), + ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="vae/diffusion_pytorch_model.safetensors"), + ], + tokenizer_config=ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="tokenizer/"), +) +prompt = "精致肖像，水下少女，蓝裙飘逸，发丝轻扬，光影透澈，气泡环绕，面容恬静，细节精致，梦幻唯美。" +image = pipe(prompt, seed=0, num_inference_steps=40) +image.save("image.jpg") diff --git a/examples/qwen_image/model_inference_low_vram/Qwen-Image-2512.py b/examples/qwen_image/model_inference_low_vram/Qwen-Image-2512.py new file mode 100644 index 0000000..63229cd --- /dev/null +++ b/examples/qwen_image/model_inference_low_vram/Qwen-Image-2512.py @@ -0,0 +1,28 @@ +from diffsynth.pipelines.qwen_image import QwenImagePipeline, ModelConfig +import torch + + +vram_config = { + "offload_dtype": "disk", + "offload_device": "disk", + "onload_dtype": torch.float8_e4m3fn, + "onload_device": "cpu", + "preparing_dtype": torch.float8_e4m3fn, + "preparing_device": "cuda", + "computation_dtype": torch.bfloat16, + "computation_device": "cuda", +} +pipe = QwenImagePipeline.from_pretrained( + torch_dtype=torch.bfloat16, + device="cuda", + model_configs=[ + ModelConfig(model_id="Qwen/Qwen-Image-2512", origin_file_pattern="transformer/diffusion_pytorch_model*.safetensors", **vram_config), + ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="text_encoder/model*.safetensors", **vram_config), + ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="vae/diffusion_pytorch_model.safetensors", **vram_config), + ], + tokenizer_config=ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="tokenizer/"), + vram_limit=torch.cuda.mem_get_info("cuda")[1] / (1024 ** 3) - 0.5, +) +prompt = "精致肖像，水下少女，蓝裙飘逸，发丝轻扬，光影透澈，气泡环绕，面容恬静，细节精致，梦幻唯美。" +image = pipe(prompt, seed=0, num_inference_steps=40) +image.save("image.jpg") diff --git a/examples/qwen_image/model_training/full/Qwen-Image-2512.sh b/examples/qwen_image/model_training/full/Qwen-Image-2512.sh new file mode 100644 index 0000000..1ce0798 --- /dev/null +++ b/examples/qwen_image/model_training/full/Qwen-Image-2512.sh @@ -0,0 +1,13 @@ +accelerate launch --config_file examples/qwen_image/model_training/full/accelerate_config_zero2offload.yaml examples/qwen_image/model_training/train.py \ + --dataset_base_path data/example_image_dataset \ + --dataset_metadata_path data/example_image_dataset/metadata.csv \ + --max_pixels 1048576 \ + --dataset_repeat 50 \ + --model_id_with_origin_paths "Qwen/Qwen-Image-2512:transformer/diffusion_pytorch_model*.safetensors,Qwen/Qwen-Image:text_encoder/model*.safetensors,Qwen/Qwen-Image:vae/diffusion_pytorch_model.safetensors" \ + --learning_rate 1e-5 \ + --num_epochs 2 \ + --remove_prefix_in_ckpt "pipe.dit." \ + --output_path "./models/train/Qwen-Image-2512_full" \ + --trainable_models "dit" \ + --use_gradient_checkpointing \ + --find_unused_parameters diff --git a/examples/qwen_image/model_training/lora/Qwen-Image-2512.sh b/examples/qwen_image/model_training/lora/Qwen-Image-2512.sh new file mode 100644 index 0000000..00ff802 --- /dev/null +++ b/examples/qwen_image/model_training/lora/Qwen-Image-2512.sh @@ -0,0 +1,16 @@ +accelerate launch examples/qwen_image/model_training/train.py \ + --dataset_base_path data/example_image_dataset \ + --dataset_metadata_path data/example_image_dataset/metadata.csv \ + --max_pixels 1048576 \ + --dataset_repeat 50 \ + --model_id_with_origin_paths "Qwen/Qwen-Image-2512:transformer/diffusion_pytorch_model*.safetensors,Qwen/Qwen-Image:text_encoder/model*.safetensors,Qwen/Qwen-Image:vae/diffusion_pytorch_model.safetensors" \ + --learning_rate 1e-4 \ + --num_epochs 5 \ + --remove_prefix_in_ckpt "pipe.dit." \ + --output_path "./models/train/Qwen-Image-2512_lora" \ + --lora_base_model "dit" \ + --lora_target_modules "to_q,to_k,to_v,add_q_proj,add_k_proj,add_v_proj,to_out.0,to_add_out,img_mlp.net.2,img_mod.1,txt_mlp.net.2,txt_mod.1" \ + --lora_rank 32 \ + --use_gradient_checkpointing \ + --dataset_num_workers 8 \ + --find_unused_parameters diff --git a/examples/qwen_image/model_training/validate_full/Qwen-Image-2512.py b/examples/qwen_image/model_training/validate_full/Qwen-Image-2512.py new file mode 100644 index 0000000..9dea6b7 --- /dev/null +++ b/examples/qwen_image/model_training/validate_full/Qwen-Image-2512.py @@ -0,0 +1,20 @@ +from diffsynth.pipelines.qwen_image import QwenImagePipeline, ModelConfig +from diffsynth import load_state_dict +import torch + + +pipe = QwenImagePipeline.from_pretrained( + torch_dtype=torch.bfloat16, + device="cuda", + model_configs=[ + ModelConfig(model_id="Qwen/Qwen-Image-2512", origin_file_pattern="transformer/diffusion_pytorch_model*.safetensors"), + ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="text_encoder/model*.safetensors"), + ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="vae/diffusion_pytorch_model.safetensors"), + ], + tokenizer_config=ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="tokenizer/"), +) +state_dict = load_state_dict("models/train/Qwen-Image-2512_full/epoch-1.safetensors") +pipe.dit.load_state_dict(state_dict) +prompt = "a dog" +image = pipe(prompt, seed=0) +image.save("image.jpg") diff --git a/examples/qwen_image/model_training/validate_lora/Qwen-Image-2512.py b/examples/qwen_image/model_training/validate_lora/Qwen-Image-2512.py new file mode 100644 index 0000000..ee829d8 --- /dev/null +++ b/examples/qwen_image/model_training/validate_lora/Qwen-Image-2512.py @@ -0,0 +1,18 @@ +from diffsynth.pipelines.qwen_image import QwenImagePipeline, ModelConfig +import torch + + +pipe = QwenImagePipeline.from_pretrained( + torch_dtype=torch.bfloat16, + device="cuda", + model_configs=[ + ModelConfig(model_id="Qwen/Qwen-Image-2512", origin_file_pattern="transformer/diffusion_pytorch_model*.safetensors"), + ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="text_encoder/model*.safetensors"), + ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="vae/diffusion_pytorch_model.safetensors"), + ], + tokenizer_config=ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="tokenizer/"), +) +pipe.load_lora(pipe.dit, "models/train/Qwen-Image-2512_lora/epoch-4.safetensors") +prompt = "a dog" +image = pipe(prompt, seed=0) +image.save("image.jpg")