| --- |
| license: apache-2.0 |
| datasets: |
| - LucidityAI/meisho-sft |
| tags: |
| - image-generation |
| --- |
| # Meisho-S1-Preview |
|
|
| A Meisho S1 Preview is a generalist image-generation model based on [Tongyi-MAI/Z-Image](https://huggingface.co/Tongyi-MAI/Z-Image), finetuned on our [LucidityAI/meisho-sft dataset](https://huggingface.co/LucidityAI/meisho-sft) |
|
|
| Compared to it's base model, Meisho-S1-Preview handles areas like typography better, while having regressions in other places (see limitations), which we aim to resolve and surpass the base-model at in a later version, whether it be in a second version of a preview or the final S1 version, among the possibility of splitting Meisho into flash and pro versions, like our Synth 2.5 family. |
|
|
|
|
| ## Usage |
|
|
| You may use Meisho S1 Preview like so: |
|
|
| ```python |
| import torch |
| from diffsynth.pipelines.z_image import ZImagePipeline, ModelConfig |
| |
| pipe = ZImagePipeline.from_pretrained( |
| torch_dtype=torch.bfloat16, |
| device="cuda", |
| model_configs=[ |
| ModelConfig(path=["<repo>/transformer/diffusion_pytorch_model-00001-of-00002.safetensors", |
| "<repo>/transformer/diffusion_pytorch_model-00002-of-00002.safetensors"]), |
| ModelConfig(path=["<repo>/text_encoder/model-0000{}-of-00003.safetensors".format(i) for i in (1,2,3)]), |
| ModelConfig(path="<repo>/vae/diffusion_pytorch_model.safetensors"), |
| ], |
| tokenizer_config=ModelConfig(path="LucidityAI/Meisho-S1-Preview/tokenizer"), |
| ) |
| |
| image = pipe( |
| prompt="...", |
| seed=1234, rand_device="cuda", |
| num_inference_steps=50, cfg_scale=4.0, |
| height=1024, width=1024, |
| ) |
| ``` |
|
|
| Recommended settings: `num_inference_steps=50`, `cfg_scale=4.0`, 1024×1024. This is a |
| non-distilled base model, so it needs the full step count, unlike Z-Image-Turbo. |
|
|
| ## Examples |
|
|
| <img style="height: 350px;" src="https://huggingface.co/LucidityAI/Meisho-S1-Preview/resolve/main/samples/compare_05_character_sheet.jpg"> |
| <img style="height: 350px;" src="https://huggingface.co/LucidityAI/Meisho-S1-Preview/resolve/main/samples/compare_10_type_poster.jpg"> |
| <img style="height: 350px;" src="https://huggingface.co/LucidityAI/Meisho-S1-Preview/resolve/main/samples/compare_12_food_flatlay.jpg"> |
| <img style="height: 350px;" src="https://huggingface.co/LucidityAI/Meisho-S1-Preview/resolve/main/samples/compare_11_color_palette.jpg"> |
|
|
| ## Limitations |
|
|
| The preview version of Meisho-S1 struggles with: |
|
|
| - Detail |
| - Clothing |
| - Photorealistic people |
|
|
| ## Examples of Limitations |
|
|
| <img style="height: 350px;" src="https://huggingface.co/LucidityAI/Meisho-S1-Preview/resolve/main/samples/compare_02_cafe_girl.jpg"> |
| <img style="height: 350px;" src="https://huggingface.co/LucidityAI/Meisho-S1-Preview/resolve/main/samples/compare_14_sprinter_bw.jpg"> |
| <img style="height: 350px;" src="https://huggingface.co/LucidityAI/Meisho-S1-Preview/resolve/main/samples/compare_04_magic_study.jpg"> |
| <img style="height: 350px;" src="https://huggingface.co/LucidityAI/Meisho-S1-Preview/resolve/main/samples/compare_15_knit_macro.jpg"> |
|
|
