theluyuan/DiffSynth-Studio
1
0
Fork 0
mirror of https://github.com/modelscope/DiffSynth-Studio.git synced 2026-03-19 06:39:43 +00:00
Code Issues Packages Projects Releases Wiki Activity

qwen-image controlnet

Browse Source
This commit is contained in:
Artiprocher
2025-08-08 11:29:23 +08:00
parent 32cf5d32ce
commit 6e13deb6de
6 changed files with 284 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
diffsynth/configs/model_config.py
View File

@@ -75,6 +75,7 @@ from ..models.nexus_gen import NexusGenAutoregressiveModel
from ..models.qwen_image_dit import QwenImageDiT
from ..models.qwen_image_text_encoder import QwenImageTextEncoder
from ..models.qwen_image_vae import QwenImageVAE
from ..models.qwen_image_controlnet import QwenImageControlNet
model_loader_configs = [
# These configs are provided for detecting model type automatically.
@@ -167,6 +168,7 @@ model_loader_configs = [
(None, "0319a1cb19835fb510907dd3367c95ff", ["qwen_image_dit"], [QwenImageDiT], "civitai"),
(None, "8004730443f55db63092006dd9f7110e", ["qwen_image_text_encoder"], [QwenImageTextEncoder], "diffusers"),
(None, "ed4ea5824d55ec3107b09815e318123a", ["qwen_image_vae"], [QwenImageVAE], "diffusers"),
(None, "be2500a62936a43d5367a70ea001e25d", ["qwen_image_controlnet"], [QwenImageControlNet], "civitai"),
]
huggingface_model_loader_configs = [
# These configs are provided for detecting model type automatically.

95
diffsynth/models/qwen_image_controlnet.py Normal file
View File

@@ -0,0 +1,95 @@
import torch
import torch.nn as nn
from .qwen_image_dit import QwenEmbedRope, QwenImageTransformerBlock
from ..vram_management import gradient_checkpoint_forward
from einops import rearrange
from .sd3_dit import TimestepEmbeddings, RMSNorm
class QwenImageControlNet(torch.nn.Module):
def __init__(
self,
num_layers: int = 60,
num_controlnet_layers: int = 6,
):
super().__init__()
self.pos_embed = QwenEmbedRope(theta=10000, axes_dim=[16,56,56], scale_rope=True)
self.time_text_embed = TimestepEmbeddings(256, 3072, diffusers_compatible_format=True, scale=1000, align_dtype_to_timestep=True)
self.txt_norm = RMSNorm(3584, eps=1e-6)
self.img_in = nn.Linear(64 * 2, 3072)
self.txt_in = nn.Linear(3584, 3072)
self.transformer_blocks = nn.ModuleList(
[
QwenImageTransformerBlock(
dim=3072,
num_attention_heads=24,
attention_head_dim=128,
)
for _ in range(num_controlnet_layers)
]
)
self.proj_out = torch.nn.ModuleList([torch.nn.Linear(3072, 3072) for i in range(num_layers)])
self.num_layers = num_layers
self.num_controlnet_layers = num_controlnet_layers
self.align_map = {i: i // (num_layers // num_controlnet_layers) for i in range(num_layers)}
def forward(
self,
latents=None,
timestep=None,
prompt_emb=None,
prompt_emb_mask=None,
height=None,
width=None,
controlnet_conditioning=None,
use_gradient_checkpointing=False,
use_gradient_checkpointing_offload=False,
**kwargs,
):
img_shapes = [(latents.shape[0], latents.shape[2]//2, latents.shape[3]//2)]
txt_seq_lens = prompt_emb_mask.sum(dim=1).tolist()
image = rearrange(latents, "B C (H P) (W Q) -> B (H W) (P Q C)", H=height//16, W=width//16, P=2, Q=2)
controlnet_conditioning = rearrange(controlnet_conditioning, "B C (H P) (W Q) -> B (H W) (P Q C)", H=height//16, W=width//16, P=2, Q=2)
image = torch.concat([image, controlnet_conditioning], dim=-1)
image = self.img_in(image)
text = self.txt_in(self.txt_norm(prompt_emb))
conditioning = self.time_text_embed(timestep, image.dtype)
image_rotary_emb = self.pos_embed(img_shapes, txt_seq_lens, device=latents.device)
outputs = []
for block in self.transformer_blocks:
text, image = gradient_checkpoint_forward(
block,
use_gradient_checkpointing,
use_gradient_checkpointing_offload,
image=image,
text=text,
temb=conditioning,
image_rotary_emb=image_rotary_emb,
)
outputs.append(image)
outputs_aligned = [self.proj_out[i](outputs[self.align_map[i]]) for i in range(self.num_layers)]
return outputs_aligned
@staticmethod
def state_dict_converter():
return QwenImageControlNetStateDictConverter()
class QwenImageControlNetStateDictConverter():
def __init__(self):
pass
def from_civitai(self, state_dict):
return state_dict

112
diffsynth/pipelines/qwen_image.py
View File

@@ -4,19 +4,55 @@ from typing import Union
from PIL import Image
from tqdm import tqdm
from einops import rearrange
import numpy as np
from ..models import ModelManager, load_state_dict
from ..models.qwen_image_dit import QwenImageDiT
from ..models.qwen_image_text_encoder import QwenImageTextEncoder
from ..models.qwen_image_vae import QwenImageVAE
from ..models.qwen_image_controlnet import QwenImageControlNet
from ..schedulers import FlowMatchScheduler
from ..utils import BasePipeline, ModelConfig, PipelineUnitRunner, PipelineUnit
from ..lora import GeneralLoRALoader
from .flux_image_new import ControlNetInput
from ..vram_management import gradient_checkpoint_forward, enable_vram_management, AutoWrappedModule, AutoWrappedLinear
class QwenImageMultiControlNet(torch.nn.Module):
def __init__(self, models: list[QwenImageControlNet]):
super().__init__()
if not isinstance(models, list):
models = [models]
self.models = torch.nn.ModuleList(models)
def process_single_controlnet(self, controlnet_input: ControlNetInput, conditioning: torch.Tensor, **kwargs):
model = self.models[controlnet_input.controlnet_id]
res_stack = model(
controlnet_conditioning=conditioning,
processor_id=controlnet_input.processor_id,
**kwargs
)
res_stack = [res * controlnet_input.scale for res in res_stack]
return res_stack
def forward(self, conditionings: list[torch.Tensor], controlnet_inputs: list[ControlNetInput], progress_id, num_inference_steps, **kwargs):
res_stack = None
for controlnet_input, conditioning in zip(controlnet_inputs, conditionings):
progress = (num_inference_steps - 1 - progress_id) / max(num_inference_steps - 1, 1)
if progress > controlnet_input.start + (1e-4) or progress < controlnet_input.end - (1e-4):
continue
res_stack_ = self.process_single_controlnet(controlnet_input, conditioning, **kwargs)
if res_stack is None:
res_stack = res_stack_
else:
res_stack = [i + j for i, j in zip(res_stack, res_stack_)]
return res_stack
class QwenImagePipeline(BasePipeline):
def __init__(self, device="cuda", torch_dtype=torch.bfloat16):
@@ -30,15 +66,17 @@ class QwenImagePipeline(BasePipeline):
self.text_encoder: QwenImageTextEncoder = None
self.dit: QwenImageDiT = None
self.vae: QwenImageVAE = None
self.controlnet: QwenImageMultiControlNet = None
self.tokenizer: Qwen2Tokenizer = None
self.unit_runner = PipelineUnitRunner()
self.in_iteration_models = ("dit",)
self.in_iteration_models = ("dit", "controlnet")
self.units = [
QwenImageUnit_ShapeChecker(),
QwenImageUnit_NoiseInitializer(),
QwenImageUnit_InputImageEmbedder(),
QwenImageUnit_PromptEmbedder(),
QwenImageUnit_EntityControl(),
QwenImageUnit_ControlNet(),
]
self.model_fn = model_fn_qwen_image
@@ -187,6 +225,7 @@ class QwenImagePipeline(BasePipeline):
pipe.text_encoder = model_manager.fetch_model("qwen_image_text_encoder")
pipe.dit = model_manager.fetch_model("qwen_image_dit")
pipe.vae = model_manager.fetch_model("qwen_image_vae")
pipe.controlnet = QwenImageMultiControlNet(model_manager.fetch_model("qwen_image_controlnet", index="all"))
if tokenizer_config is not None and pipe.text_encoder is not None:
tokenizer_config.download_if_necessary()
from transformers import Qwen2Tokenizer
@@ -212,6 +251,8 @@ class QwenImagePipeline(BasePipeline):
rand_device: str = "cpu",
# Steps
num_inference_steps: int = 30,
# ControlNet
controlnet_inputs: list[ControlNetInput] = None,
# EliGen
eligen_entity_prompts: list[str] = None,
eligen_entity_masks: list[Image.Image] = None,
@@ -241,6 +282,8 @@ class QwenImagePipeline(BasePipeline):
"height": height, "width": width,
"seed": seed, "rand_device": rand_device,
"enable_fp8_attention": enable_fp8_attention,
"num_inference_steps": num_inference_steps,
"controlnet_inputs": controlnet_inputs,
"tiled": tiled, "tile_size": tile_size, "tile_stride": tile_stride,
"eligen_entity_prompts": eligen_entity_prompts, "eligen_entity_masks": eligen_entity_masks, "eligen_enable_on_negative": eligen_enable_on_negative,
}
@@ -431,14 +474,60 @@ class QwenImageUnit_EntityControl(PipelineUnit):
return inputs_shared, inputs_posi, inputs_nega
class QwenImageUnit_ControlNet(PipelineUnit):
def __init__(self):
super().__init__(
input_params=("controlnet_inputs", "tiled", "tile_size", "tile_stride"),
onload_model_names=("vae",)
)
def apply_controlnet_mask_on_latents(self, pipe, latents, mask):
mask = (pipe.preprocess_image(mask) + 1) / 2
mask = mask.mean(dim=1, keepdim=True)
mask = 1 - torch.nn.functional.interpolate(mask, size=latents.shape[-2:])
latents = torch.concat([latents, mask], dim=1)
return latents
def apply_controlnet_mask_on_image(self, pipe, image, mask):
mask = mask.resize(image.size)
mask = pipe.preprocess_image(mask).mean(dim=[0, 1]).cpu()
image = np.array(image)
image[mask > 0] = 0
image = Image.fromarray(image)
return image
def process(self, pipe: QwenImagePipeline, controlnet_inputs: list[ControlNetInput], tiled, tile_size, tile_stride):
if controlnet_inputs is None:
return {}
pipe.load_models_to_device(self.onload_model_names)
conditionings = []
for controlnet_input in controlnet_inputs:
image = controlnet_input.image
if controlnet_input.inpaint_mask is not None:
image = self.apply_controlnet_mask_on_image(pipe, image, controlnet_input.inpaint_mask)
image = pipe.preprocess_image(image).to(device=pipe.device, dtype=pipe.torch_dtype)
image = pipe.vae.encode(image, tiled=tiled, tile_size=tile_size, tile_stride=tile_stride)
if controlnet_input.inpaint_mask is not None:
image = self.apply_controlnet_mask_on_latents(pipe, image, controlnet_input.inpaint_mask)
conditionings.append(image)
return {"controlnet_conditionings": conditionings}
def model_fn_qwen_image(
dit: QwenImageDiT = None,
controlnet: QwenImageMultiControlNet = None,
latents=None,
timestep=None,
prompt_emb=None,
prompt_emb_mask=None,
height=None,
width=None,
controlnet_inputs=None,
controlnet_conditionings=None,
progress_id=0,
num_inference_steps=1,
entity_prompt_emb=None,
entity_prompt_emb_mask=None,
entity_masks=None,
@@ -447,6 +536,23 @@ def model_fn_qwen_image(
use_gradient_checkpointing_offload=False,
**kwargs
):
# ControlNet
if controlnet_conditionings is not None:
controlnet_extra_kwargs = {
"latents": latents,
"timestep": timestep,
"prompt_emb": prompt_emb,
"prompt_emb_mask": prompt_emb_mask,
"height": height,
"width": width,
"use_gradient_checkpointing": use_gradient_checkpointing,
"use_gradient_checkpointing_offload": use_gradient_checkpointing_offload,
}
res_stack = controlnet(
controlnet_conditionings, controlnet_inputs, progress_id, num_inference_steps,
**controlnet_extra_kwargs
)
img_shapes = [(latents.shape[0], latents.shape[2]//2, latents.shape[3]//2)]
txt_seq_lens = prompt_emb_mask.sum(dim=1).tolist()
timestep = timestep / 1000
@@ -466,7 +572,7 @@ def model_fn_qwen_image(
image_rotary_emb = dit.pos_embed(img_shapes, txt_seq_lens, device=latents.device)
attention_mask = None
for block in dit.transformer_blocks:
for block_id, block in enumerate(dit.transformer_blocks):
text, image = gradient_checkpoint_forward(
block,
use_gradient_checkpointing,
@@ -478,6 +584,8 @@ def model_fn_qwen_image(
attention_mask=attention_mask,
enable_fp8_attention=enable_fp8_attention,
)
if controlnet_inputs is not None:
image = image + res_stack[block_id]
image = dit.norm_out(image, conditioning)
image = dit.proj_out(image)