theluyuan/DiffSynth-Studio
1
0
Fork 0
mirror of https://github.com/modelscope/DiffSynth-Studio.git synced 2026-03-18 22:08:13 +00:00
Code Issues Packages Projects Releases Wiki Activity

DiffSynth-Studio 2.0 major update

Browse Source
This commit is contained in:
root
2025-12-04 16:33:07 +08:00
parent afd101f345
commit 72af7122b3
758 changed files with 26462 additions and 2221398 deletions
Download Patch File Download Diff File Expand all files Collapse all files

24
examples/flux/model_inference_low_vram/Nexus-Gen-Editing.py
View File

@@ -1,7 +1,7 @@
import importlib
import torch
from PIL import Image
from diffsynth.pipelines.flux_image_new import FluxImagePipeline, ModelConfig
from diffsynth.pipelines.flux_image import FluxImagePipeline, ModelConfig
from modelscope import dataset_snapshot_download
@@ -12,19 +12,29 @@ else:
assert transformers.__version__ == "4.49.0", "Nexus-GenV2 requires transformers==4.49.0, please install it with `pip install transformers==4.49.0`."
vram_config = {
"offload_dtype": torch.float8_e4m3fn,
"offload_device": "cpu",
"onload_dtype": torch.float8_e4m3fn,
"onload_device": "cpu",
"preparing_dtype": torch.float8_e4m3fn,
"preparing_device": "cuda",
"computation_dtype": torch.bfloat16,
"computation_device": "cuda",
}
pipe = FluxImagePipeline.from_pretrained(
torch_dtype=torch.bfloat16,
device="cuda",
model_configs=[
ModelConfig(model_id="DiffSynth-Studio/Nexus-GenV2", origin_file_pattern="model*.safetensors", offload_device="cpu"),
ModelConfig(model_id="DiffSynth-Studio/Nexus-GenV2", origin_file_pattern="edit_decoder.bin", offload_device="cpu"),
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder/model.safetensors", offload_device="cpu"),
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder_2/", offload_device="cpu"),
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="ae.safetensors", offload_device="cpu"),
ModelConfig(model_id="DiffSynth-Studio/Nexus-GenV2", origin_file_pattern="model*.safetensors", **vram_config),
ModelConfig(model_id="DiffSynth-Studio/Nexus-GenV2", origin_file_pattern="edit_decoder.bin", **vram_config),
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder/model.safetensors", **vram_config),
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),
],
nexus_gen_processor_config=ModelConfig(model_id="DiffSynth-Studio/Nexus-GenV2", origin_file_pattern="processor/"),
vram_limit=torch.cuda.mem_get_info("cuda")[1] / (1024 ** 3) - 0.5,
)
pipe.enable_vram_management()
dataset_snapshot_download(dataset_id="DiffSynth-Studio/examples_in_diffsynth", local_dir="./", allow_file_pattern=f"data/examples/nexusgen/cat.jpg")
ref_image = Image.open("data/examples/nexusgen/cat.jpg").convert("RGB")