theluyuan/DiffSynth-Studio
1
0
Fork 0
mirror of https://github.com/modelscope/DiffSynth-Studio.git synced 2026-03-19 06:48:12 +00:00
Code Issues Packages Projects Releases Wiki Activity

update docs

Browse Source
This commit is contained in:
Artiprocher
2025-12-04 14:04:20 +08:00
parent 17600eda0f
commit 41e2b47e1d
4 changed files with 20 additions and 20 deletions
Download Patch File Download Diff File Expand all files Collapse all files

13
docs/en/Model_Details/FLUX.md
View File

@@ -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")
```
## Model Overview

6
docs/en/Model_Details/FLUX2.md
View File

@@ -16,7 +16,7 @@ For more information about installation, please refer to [Install Dependencies](
## Quick Start
Run the following code to quickly load the [black-forest-labs/FLUX.2-dev](https://www.modelscope.cn/models/black-forest-labs/FLUX.2-dev) model and perform inference. VRAM management is enabled, and the framework will automatically control model parameter loading based on remaining VRAM. Minimum 8GB VRAM is required to run.
Run the following code to quickly load the [black-forest-labs/FLUX.2-dev](https://www.modelscope.cn/models/black-forest-labs/FLUX.2-dev) model and perform inference. VRAM management is enabled, and the framework will automatically control model parameter loading based on remaining VRAM. Minimum 10GB VRAM is required to run.
```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")
```
## Model Overview

1
docs/en/Model_Details/Wan.md
View File

@@ -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",

20
docs/en/Model_Details/Z-Image.md
View File

@@ -16,22 +16,32 @@ For more information about installation, please refer to [Install Dependencies](
## Quick Start
Run the following code to quickly load the [Tongyi-MAI/Z-Image-Turbo](https://www.modelscope.cn/models/Tongyi-MAI/Z-Image-Turbo) model and perform inference.
Run the following code to quickly load the [Tongyi-MAI/Z-Image-Turbo](https://www.modelscope.cn/models/Tongyi-MAI/Z-Image-Turbo) model and perform inference. FP8 precision quantization causes noticeable image quality degradation, so it is not recommended to enable any quantization on the Z-Image Turbo model. Only CPU Offload is recommended, minimum 8GB VRAM is required to run.
```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")