--- title: MOSS-Image-SFT-TurboLoRA canonical_url: "https://www.modelscope.cn/models/DiffSynth-Studio/MOSS-Image-SFT-TurboLoRA" md_url: "https://www.modelscope.cn/models/DiffSynth-Studio/MOSS-Image-SFT-TurboLoRA.md" repository: DiffSynth-Studio/MOSS-Image-SFT-TurboLoRA chinese_name: "MOSS-Image-SFT 加速 LoRA" last_updated: 2026-10-20 license: "Apache License 2.0" pipeline_tag: text-to-image-synthesis tasks: - text-to-image-synthesis base_model_relation: finetune parameters: 155.3M tensor_type: - F32 library_name: - pytorch - safetensors downloads: 9 stars: 0 --- # MOSS-Image-SFT-TurboLoRA > MOSS-Image-SFT-TurboLoRA - DiffSynth-Studio 在 ModelScope 开源的模型。MOSS-Image-SFT Distillation-Accelerated LoRA DiffSynth-Studio/MOSS-Image-SFT-TurboLoRA 是 ModelScope 魔搭社区上的 155.3M 参数text-to-image-synthesis模型，采用 Apache License 2.0 许可。 - **Repository**: DiffSynth-Studio/MOSS-Image-SFT-TurboLoRA - **License**: Apache License 2.0 - **Tasks**: text-to-image-synthesis - **Parameters**: 155.3M - **Downloads**: 9 - **Stars**: 0 - **Last updated**: 2026-10-20 Source: https://www.modelscope.cn/models/DiffSynth-Studio/MOSS-Image-SFT-TurboLoRA --- # MOSS-Image-SFT Distillation-Accelerated LoRA This model is trained using OPD (On-Policy Distillation) distillation acceleration based on [DiffSynth-Studio](https://github.com/modelscope/DiffSynth-Studio), providing inference acceleration for [MOSS-Image-SFT](https://www.modelscope.cn/models/openmoss/MOSS-Image-SFT). * Training framework: [DiffSynth-Studio](https://github.com/modelscope/DiffSynth-Studio) * Base model: [MOSS-Image-SFT](https://www.modelscope.cn/models/openmoss/MOSS-Image-SFT) * Dataset: [ImagePulseV2](https://modelscope.cn/collections/DiffSynth-Studio/ImagePulseV2) * Training resources: 8 ZW810 PPUs * Training steps: 6000 steps ## Showcase [model-8steps.safetensors](./model-8steps.safetensors): An 8-step accelerated LoRA based on [MOSS-Image-SFT](https://www.modelscope.cn/models/openmoss/MOSS-Image-SFT). It distills the 50-step sampling trajectory into 8 steps, greatly reducing the inference cost while preserving the capabilities of the base model. ||This model (8 steps)|MOSS-Image-SFT (8 steps)|MOSS-Image-SFT (50 steps)| |-|-|-|-| |Example 1: Complex composition|![](./assets/example1/image_lora_8steps.png)|![](./assets/example1/image_base_8steps.png)|![](./assets/example1/image_base_50steps.png)| |Example 2: Text rendering|![](./assets/example2/image_lora_8steps.png)|![](./assets/example2/image_base_8steps.png)|![](./assets/example2/image_base_50steps.png)| |Example 3: Chinese text rendering|![](./assets/example3/image_lora_8steps.png)|![](./assets/example3/image_base_8steps.png)|![](./assets/example3/image_base_50steps.png)|
Prompts * Anime style. A sweet girl with twin tails and a flower crown sits on a park bench, smiling at the viewer while holding a black camera. She wears a red T-shirt and a white tennis skirt. Beside her, an orange kitten rests calmly. The background is a soft blur of sunset colors, keeping the focus entirely on the character and the cat. * A cinematic movie poster featuring a breathtaking, wide-angle landscape. The background showcases a vast, crystal-clear azure sky stretching upward, dotted with soft, volumetric white cumulus clouds drifting gently. Below the sky rises a majestic range of towering snow-capped mountains, their jagged peaks gleaming bright white against the deep blue atmosphere, rendered with crisp, photorealistic detail and dramatic lighting. In the center foreground, a magnificent eagle soars dynamically through the air, its wings fully extended in mid-flight, feathers catching the sunlight as it glides effortlessly above the alpine scenery. The composition evokes a sense of epic scale, freedom, and adventure, styled like a high-budget Hollywood blockbuster poster. At the bottom of the image, elegantly integrated into the lower third over the mountain base or sky gradient, is the text "DiffSynth-Studio". The typography is bold, modern, and cinematic, using a clean sans-serif font in crisp white or metallic silver, ensuring high legibility and a professional film-title aesthetic. * In a bright, modern classroom, a young woman dressed in a traditional Japanese-style school uniform (JK uniform) is focused on explaining a technical concept. She holds a marker firmly, her posture poised as she writes '基于DiffSynth-Studio的\nOPD加速训练' across the pristine whiteboard. The lighting highlights the neatness of her script and the professional yet youthful atmosphere of the academic setting.
## Inference Code Install [DiffSynth-Studio](https://github.com/modelscope/DiffSynth-Studio): ```shell git clone https://github.com/modelscope/DiffSynth-Studio.git cd DiffSynth-Studio pip install -e . ``` Run 8-step accelerated LoRA for [MOSS-Image-SFT](https://www.modelscope.cn/models/openmoss/MOSS-Image-SFT): ```python import torch from diffsynth.pipelines.moss_image import MOSSImagePipeline, ModelConfig pipe = MOSSImagePipeline.from_pretrained( torch_dtype=torch.bfloat16, device="cuda", model_configs=[ ModelConfig(model_id="openmoss/MOSS-Image-SFT", origin_file_pattern="transformer/diffusion_pytorch_model*.safetensors"), ModelConfig(model_id="openmoss/MOSS-Image-SFT", origin_file_pattern="text_encoder/model*.safetensors"), ModelConfig(model_id="openmoss/MOSS-Image-SFT", origin_file_pattern="vae/diffusion_pytorch_model.safetensors", computation_dtype=torch.float32), ], tokenizer_config=ModelConfig(model_id="openmoss/MOSS-Image-SFT", origin_file_pattern="tokenizer/"), ) pipe.load_lora(pipe.dit, ModelConfig(model_id="DiffSynth-Studio/MOSS-Image-SFT-TurboLoRA", origin_file_pattern="model-8steps.safetensors")) prompt = """A cinematic movie poster featuring a breathtaking, wide-angle landscape. The background showcases a vast, crystal-clear azure sky stretching upward, dotted with soft, volumetric white cumulus clouds drifting gently. Below the sky rises a majestic range of towering snow-capped mountains, their jagged peaks gleaming bright white against the deep blue atmosphere, rendered with crisp, photorealistic detail and dramatic lighting. In the center foreground, a magnificent eagle soars dynamically through the air, its wings fully extended in mid-flight, feathers catching the sunlight as it glides effortlessly above the alpine scenery. The composition evokes a sense of epic scale, freedom, and adventure, styled like a high-budget Hollywood blockbuster poster. At the bottom of the image, elegantly integrated into the lower third over the mountain base or sky gradient, is the text "DiffSynth-Studio". The typography is bold, modern, and cinematic, using a clean sans-serif font in crisp white or metallic silver, ensuring high legibility and a professional film-title aesthetic.""" image = pipe(prompt, height=1024, width=1024, seed=0, num_inference_steps=8, cfg_scale=1.0) image.save("image_lora_8steps.png") ``` The training code is also released. Please refer to our [documents](https://diffsynth-studio-doc.readthedocs.io/en/latest/Training/Distillation.html).