diff --git a/docs/zh/Model_Details/FLUX.md b/docs/zh/Model_Details/FLUX.md index f8a310c..71576dc 100644 --- a/docs/zh/Model_Details/FLUX.md +++ b/docs/zh/Model_Details/FLUX.md @@ -43,20 +43,11 @@ pipe = FluxImagePipeline.from_pretrained( ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder_2/*.safetensors", **vram_config), ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="ae.safetensors", **vram_config), ], - vram_limit=torch.cuda.mem_get_info("cuda")[1] / (1024 ** 3) - 0.5, + vram_limit=torch.cuda.mem_get_info("cuda")[1] / (1024 ** 3) - 1, ) - prompt = "CG, masterpiece, best quality, solo, long hair, wavy hair, silver hair, blue eyes, blue dress, medium breasts, dress, underwater, air bubble, floating hair, refraction, portrait. The girl's flowing silver hair shimmers with every color of the rainbow and cascades down, merging with the floating flora around her." -negative_prompt = "worst quality, low quality, monochrome, zombie, interlocked fingers, Aissist, cleavage, nsfw," - image = pipe(prompt=prompt, seed=0) -image.save("flux.jpg") - -image = pipe( - prompt=prompt, negative_prompt=negative_prompt, - seed=0, cfg_scale=2, num_inference_steps=50, -) -image.save("flux_cfg.jpg") +image.save("image.jpg") ``` ## 模型总览 diff --git a/docs/zh/Model_Details/FLUX2.md b/docs/zh/Model_Details/FLUX2.md index e62168e..ad4df27 100644 --- a/docs/zh/Model_Details/FLUX2.md +++ b/docs/zh/Model_Details/FLUX2.md @@ -16,7 +16,7 @@ pip install -e . ## 快速开始 -运行以下代码可以快速加载 [black-forest-labs/FLUX.2-dev](https://www.modelscope.cn/models/black-forest-labs/FLUX.2-dev) 模型并进行推理。显存管理已启动，框架会自动根据剩余显存控制模型参数的加载，最低 8G 显存即可运行。 +运行以下代码可以快速加载 [black-forest-labs/FLUX.2-dev](https://www.modelscope.cn/models/black-forest-labs/FLUX.2-dev) 模型并进行推理。显存管理已启动，框架会自动根据剩余显存控制模型参数的加载，最低 10G 显存即可运行。 ```python from diffsynth.pipelines.flux2_image import Flux2ImagePipeline, ModelConfig @@ -43,9 +43,9 @@ pipe = Flux2ImagePipeline.from_pretrained( tokenizer_config=ModelConfig(model_id="black-forest-labs/FLUX.2-dev", origin_file_pattern="tokenizer/"), vram_limit=torch.cuda.mem_get_info("cuda")[1] / (1024 ** 3) - 0.5, ) -prompt = "Realistic macro photograph of a hermit crab using a soda can as its shell, partially emerging from the can, captured with sharp detail and natural colors, on a sunlit beach with soft shadows and a shallow depth of field, with blurred ocean waves in the background. The can has the text `BFL Diffusers` on it and it has a color gradient that start with #FF5733 at the top and transitions to #33FF57 at the bottom." +prompt = "High resolution. A dreamy underwater portrait of a serene young woman in a flowing blue dress. Her hair floats softly around her face, strands delicately suspended in the water. Clear, shimmering light filters through, casting gentle highlights, while tiny bubbles rise around her. Her expression is calm, her features finely detailed—creating a tranquil, ethereal scene." image = pipe(prompt, seed=42, rand_device="cuda", num_inference_steps=50) -image.save("image_FLUX.2-dev.jpg") +image.save("image.jpg") ``` ## 模型总览 diff --git a/docs/zh/Model_Details/Wan.md b/docs/zh/Model_Details/Wan.md index 8b9e446..b8c3032 100644 --- a/docs/zh/Model_Details/Wan.md +++ b/docs/zh/Model_Details/Wan.md @@ -25,7 +25,6 @@ import torch from diffsynth.utils.data import save_video, VideoData from diffsynth.pipelines.wan_video import WanVideoPipeline, ModelConfig - vram_config = { "offload_dtype": "disk", "offload_device": "disk", diff --git a/docs/zh/Model_Details/Z-Image.md b/docs/zh/Model_Details/Z-Image.md index 2aea18b..ad2818e 100644 --- a/docs/zh/Model_Details/Z-Image.md +++ b/docs/zh/Model_Details/Z-Image.md @@ -16,22 +16,32 @@ pip install -e . ## 快速开始 -运行以下代码可以快速加载 [Tongyi-MAI/Z-Image-Turbo](https://www.modelscope.cn/models/Tongyi-MAI/Z-Image-Turbo) 模型并进行推理。 +运行以下代码可以快速加载 [Tongyi-MAI/Z-Image-Turbo](https://www.modelscope.cn/models/Tongyi-MAI/Z-Image-Turbo) 模型并进行推理。FP8 精度量化会导致明显的图像质量劣化，因此不建议在 Z-Image Turbo 模型上开启任何量化，仅建议开启 CPU Offload，最低 8G 显存即可运行。 ```python from diffsynth.pipelines.z_image import ZImagePipeline, ModelConfig import torch - +vram_config = { + "offload_dtype": torch.bfloat16, + "offload_device": "cpu", + "onload_dtype": torch.bfloat16, + "onload_device": "cpu", + "preparing_dtype": torch.bfloat16, + "preparing_device": "cuda", + "computation_dtype": torch.bfloat16, + "computation_device": "cuda", +} pipe = ZImagePipeline.from_pretrained( torch_dtype=torch.bfloat16, device="cuda", model_configs=[ - ModelConfig(model_id="Tongyi-MAI/Z-Image-Turbo", origin_file_pattern="transformer/*.safetensors"), - ModelConfig(model_id="Tongyi-MAI/Z-Image-Turbo", origin_file_pattern="text_encoder/*.safetensors"), - ModelConfig(model_id="Tongyi-MAI/Z-Image-Turbo", origin_file_pattern="vae/diffusion_pytorch_model.safetensors"), + ModelConfig(model_id="Tongyi-MAI/Z-Image-Turbo", origin_file_pattern="transformer/*.safetensors", **vram_config), + ModelConfig(model_id="Tongyi-MAI/Z-Image-Turbo", origin_file_pattern="text_encoder/*.safetensors", **vram_config), + ModelConfig(model_id="Tongyi-MAI/Z-Image-Turbo", origin_file_pattern="vae/diffusion_pytorch_model.safetensors", **vram_config), ], tokenizer_config=ModelConfig(model_id="Tongyi-MAI/Z-Image-Turbo", origin_file_pattern="tokenizer/"), + vram_limit=torch.cuda.mem_get_info("cuda")[1] / (1024 ** 3) - 0.5, ) prompt = "Young Chinese woman in red Hanfu, intricate embroidery. Impeccable makeup, red floral forehead pattern. Elaborate high bun, golden phoenix headdress, red flowers, beads. Holds round folding fan with lady, trees, bird. Neon lightning-bolt lamp (⚡️), bright yellow glow, above extended left palm. Soft-lit outdoor night background, silhouetted tiered pagoda (西安大雁塔), blurred colorful distant lights." image = pipe(prompt=prompt, seed=42, rand_device="cuda")