theluyuan/DiffSynth-Studio
1
0
Fork 0
mirror of https://github.com/modelscope/DiffSynth-Studio.git synced 2026-03-23 00:58:11 +00:00
Code Issues Packages Projects Releases Wiki Activity

support z-image controlnet

Browse Source
This commit is contained in:
Artiprocher
2026-01-07 15:56:53 +08:00
parent 32449a6aa0
commit bac39b1cd2
28 changed files with 868 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
examples/z_image/model_training/validate_full/Z-Image-Omni-Base.py
View File

@@ -14,8 +14,20 @@ pipe = ZImagePipeline.from_pretrained(
],
tokenizer_config=ModelConfig(model_id="Tongyi-MAI/Z-Image-Turbo", origin_file_pattern="tokenizer/"),
)
state_dict = load_state_dict("./models/train/Z-Image-Omni-Base_full/epoch-1.safetensors", torch_dtype=torch.bfloat16)
pipe.dit.load_state_dict(state_dict)
prompt = "a dog"
image = pipe(prompt=prompt, seed=42, rand_device="cuda", num_inference_steps=40, cfg_scale=4)
image.save("image.jpg")
# Edit
# state_dict = load_state_dict("./models/train/Z-Image-Omni-Base_full_edit/epoch-1.safetensors", torch_dtype=torch.bfloat16)
# pipe.dit.load_state_dict(state_dict)
# prompt = "Change the color of the dress in Figure 1 to the color shown in Figure 2."
# images = [
# Image.open("data/example_image_dataset/edit/image1.jpg").resize((1024, 1024)),
# Image.open("data/example_image_dataset/edit/image_color.jpg").resize((1024, 1024)),
# ]
# image = pipe(prompt=prompt, seed=42, rand_device="cuda", num_inference_steps=40, cfg_scale=4, edit_image=images)
# image.save("image.jpg")

24
examples/z_image/model_training/validate_full/Z-Image-Turbo-Fun-Controlnet-Tile-2.1-8steps.py Normal file
View File

@@ -0,0 +1,24 @@
from diffsynth.pipelines.z_image import ZImagePipeline, ModelConfig, ControlNetInput
from diffsynth import load_state_dict
from PIL import Image
import torch
pipe = ZImagePipeline.from_pretrained(
torch_dtype=torch.bfloat16,
device="cuda",
model_configs=[
ModelConfig(model_id="PAI/Z-Image-Turbo-Fun-Controlnet-Union-2.1", origin_file_pattern="Z-Image-Turbo-Fun-Controlnet-Tile-2.1-8steps.safetensors"),
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"),
],
tokenizer_config=ModelConfig(model_id="Tongyi-MAI/Z-Image-Turbo", origin_file_pattern="tokenizer/"),
)
state_dict = load_state_dict("./models/train/Z-Image-Turbo-Fun-Controlnet-Tile-2.1-8steps_full/epoch-1.safetensors")
pipe.controlnet.load_state_dict(state_dict)
controlnet_image = Image.open("data/example_image_dataset/upscale/image_1.jpg").resize((1024, 1024))
prompt = "a dog"
image = pipe(prompt=prompt, seed=0, height=1024, width=1024, controlnet_inputs=[ControlNetInput(image=controlnet_image, scale=1)])
image.save("image_tile.jpg")

24
examples/z_image/model_training/validate_full/Z-Image-Turbo-Fun-Controlnet-Union-2.1-8steps.py Normal file
View File

@@ -0,0 +1,24 @@
from diffsynth.pipelines.z_image import ZImagePipeline, ModelConfig, ControlNetInput
from diffsynth import load_state_dict
from PIL import Image
import torch
pipe = ZImagePipeline.from_pretrained(
torch_dtype=torch.bfloat16,
device="cuda",
model_configs=[
ModelConfig(model_id="PAI/Z-Image-Turbo-Fun-Controlnet-Union-2.1", origin_file_pattern="Z-Image-Turbo-Fun-Controlnet-Union-2.1-8steps.safetensors"),
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"),
],
tokenizer_config=ModelConfig(model_id="Tongyi-MAI/Z-Image-Turbo", origin_file_pattern="tokenizer/"),
)
state_dict = load_state_dict("./models/train/Z-Image-Turbo-Fun-Controlnet-Union-2.1-8steps_full/epoch-1.safetensors")
pipe.controlnet.load_state_dict(state_dict)
controlnet_image = Image.open("data/example_image_dataset/canny/image_1.jpg").resize((1024, 1024))
prompt = "a dog"
image = pipe(prompt=prompt, seed=0, height=1024, width=1024, controlnet_inputs=[ControlNetInput(image=controlnet_image, scale=0.7)])
image.save("image_control.jpg")

24
examples/z_image/model_training/validate_full/Z-Image-Turbo-Fun-Controlnet-Union-2.1.py Normal file
View File

@@ -0,0 +1,24 @@
from diffsynth.pipelines.z_image import ZImagePipeline, ModelConfig, ControlNetInput
from diffsynth import load_state_dict
from PIL import Image
import torch
pipe = ZImagePipeline.from_pretrained(
torch_dtype=torch.bfloat16,
device="cuda",
model_configs=[
ModelConfig(model_id="PAI/Z-Image-Turbo-Fun-Controlnet-Union-2.1", origin_file_pattern="Z-Image-Turbo-Fun-Controlnet-Union-2.1.safetensors"),
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"),
],
tokenizer_config=ModelConfig(model_id="Tongyi-MAI/Z-Image-Turbo", origin_file_pattern="tokenizer/"),
)
state_dict = load_state_dict("./models/train/Z-Image-Turbo-Fun-Controlnet-Union-2.1_full/epoch-1.safetensors")
pipe.controlnet.load_state_dict(state_dict)
controlnet_image = Image.open("data/example_image_dataset/canny/image_1.jpg").resize((1024, 1024))
prompt = "a dog"
image = pipe(prompt=prompt, seed=0, height=1024, width=1024, controlnet_inputs=[ControlNetInput(image=controlnet_image, scale=0.7)])
image.save("image_control.jpg")