theluyuan/DiffSynth-Studio
1
0
Fork 0
mirror of https://github.com/modelscope/DiffSynth-Studio.git synced 2026-03-25 02:38:10 +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

21
examples/qwen_image/model_inference_low_vram/Qwen-Image-EliGen-V2.py
View File

@@ -4,7 +4,6 @@ from PIL import Image, ImageDraw, ImageFont
from modelscope import dataset_snapshot_download, snapshot_download
from diffsynth.pipelines.qwen_image import QwenImagePipeline, ModelConfig
def visualize_masks(image, masks, mask_prompts, output_path, font_size=35, use_random_colors=False):
# Create a blank image for overlays
overlay = Image.new('RGBA', image.size, (0, 0, 0, 0))
@@ -83,19 +82,29 @@ def example(pipe, seeds, example_id, global_prompt, entity_prompts):
visualize_masks(image, masks, entity_prompts, f"eligen_example_{example_id}_mask_{seed}.png")
vram_config = {
"offload_dtype": "disk",
"offload_device": "disk",
"onload_dtype": torch.float8_e4m3fn,
"onload_device": "cpu",
"preparing_dtype": torch.float8_e4m3fn,
"preparing_device": "cuda",
"computation_dtype": torch.bfloat16,
"computation_device": "cuda",
}
pipe = QwenImagePipeline.from_pretrained(
torch_dtype=torch.bfloat16,
device="cuda",
model_configs=[
ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="transformer/diffusion_pytorch_model*.safetensors", offload_dtype=torch.float8_e4m3fn),
ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="text_encoder/model*.safetensors", offload_dtype=torch.float8_e4m3fn),
ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="vae/diffusion_pytorch_model.safetensors", offload_dtype=torch.float8_e4m3fn),
ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="transformer/diffusion_pytorch_model*.safetensors", **vram_config),
ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="text_encoder/model*.safetensors", **vram_config),
ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="vae/diffusion_pytorch_model.safetensors", **vram_config),
],
tokenizer_config=ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="tokenizer/"),
vram_limit=torch.cuda.mem_get_info("cuda")[1] / (1024 ** 3) - 0.5,
)
pipe.enable_vram_management()
snapshot_download("DiffSynth-Studio/Qwen-Image-EliGen-V2", local_dir="models/DiffSynth-Studio/Qwen-Image-EliGen-V2", allow_file_pattern="model.safetensors")
pipe.load_lora(pipe.dit, "models/DiffSynth-Studio/Qwen-Image-EliGen-V2/model.safetensors")
pipe.load_lora(pipe.dit, "models/DiffSynth-Studio/Qwen-Image-EliGen-V2/model.safetensors", hotload=True)
seeds = [0]