theluyuan/DiffSynth-Studio
1
0
Fork 0
mirror of https://github.com/modelscope/DiffSynth-Studio.git synced 2026-03-22 00:38:11 +00:00
Code Issues Packages Projects Releases Wiki Activity

bugfix & update doc

Browse Source
This commit is contained in:
Artiprocher
2025-12-04 10:35:14 +08:00
parent 4a15618080
commit 7747f38561
6 changed files with 768 additions and 23 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
examples/flux2/model_inference_low_vram/FLUX.2-dev.py
View File

@@ -1,7 +1,6 @@
from diffsynth.pipelines.flux2_image import Flux2ImagePipeline, ModelConfig
import torch
vram_config = {
"offload_dtype": "disk",
"offload_device": "disk",
@@ -23,6 +22,6 @@ 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")

21
examples/z_image/model_inference_low_vram/Z-Image-Turbo.py
View File

@@ -1,23 +1,12 @@
from diffsynth.pipelines.z_image import ZImagePipeline, ModelConfig
import torch
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",
}
vram_config_cpu_offload = {
"offload_dtype": torch.float8_e4m3fn,
"offload_dtype": torch.bfloat16,
"offload_device": "cpu",
"onload_dtype": torch.float8_e4m3fn,
"onload_dtype": torch.bfloat16,
"onload_device": "cpu",
"preparing_dtype": torch.float8_e4m3fn,
"preparing_dtype": torch.bfloat16,
"preparing_device": "cuda",
"computation_dtype": torch.bfloat16,
"computation_device": "cuda",
@@ -27,7 +16,7 @@ pipe = ZImagePipeline.from_pretrained(
device="cuda",
model_configs=[
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_cpu_offload),
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/"),
@@ -35,4 +24,4 @@ pipe = ZImagePipeline.from_pretrained(
)
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")
image.save("image_Z-Image-Turbo.jpg")
image.save("image.jpg")