mirror of
https://git.datalinker.icu/comfyanonymous/ComfyUI
synced 2026-11-21 17:17:04 +08:00
Merge branch 'comfyanonymous:master' into master
This commit is contained in:
commit
6ab659e6e7
@ -357,7 +357,14 @@ def unet_config_from_diffusers_unet(state_dict, dtype=None):
|
|||||||
'context_dim': 1024, 'num_head_channels': 64, 'transformer_depth_output': [1, 1, 1, 1, 1, 1],
|
'context_dim': 1024, 'num_head_channels': 64, 'transformer_depth_output': [1, 1, 1, 1, 1, 1],
|
||||||
'use_temporal_attention': False, 'use_temporal_resblock': False, 'disable_self_attentions': [True, False, False]}
|
'use_temporal_attention': False, 'use_temporal_resblock': False, 'disable_self_attentions': [True, False, False]}
|
||||||
|
|
||||||
supported_models = [SDXL, SDXL_refiner, SD21, SD15, SD21_uncliph, SD21_unclipl, SDXL_mid_cnet, SDXL_small_cnet, SDXL_diffusers_inpaint, SSD_1B, Segmind_Vega, KOALA_700M, KOALA_1B, SD09_XS, SDXL_diffusers_ip2p]
|
SD_XS = {'use_checkpoint': False, 'image_size': 32, 'out_channels': 4, 'use_spatial_transformer': True, 'legacy': False,
|
||||||
|
'adm_in_channels': None, 'dtype': dtype, 'in_channels': 4, 'model_channels': 320, 'num_res_blocks': [1, 1, 1],
|
||||||
|
'transformer_depth': [0, 1, 1], 'channel_mult': [1, 2, 4], 'transformer_depth_middle': -2, 'use_linear_in_transformer': False,
|
||||||
|
'context_dim': 768, 'num_head_channels': 64, 'transformer_depth_output': [0, 0, 1, 1, 1, 1],
|
||||||
|
'use_temporal_attention': False, 'use_temporal_resblock': False}
|
||||||
|
|
||||||
|
|
||||||
|
supported_models = [SDXL, SDXL_refiner, SD21, SD15, SD21_uncliph, SD21_unclipl, SDXL_mid_cnet, SDXL_small_cnet, SDXL_diffusers_inpaint, SSD_1B, Segmind_Vega, KOALA_700M, KOALA_1B, SD09_XS, SD_XS, SDXL_diffusers_ip2p]
|
||||||
|
|
||||||
for unet_config in supported_models:
|
for unet_config in supported_models:
|
||||||
matches = True
|
matches = True
|
||||||
|
|||||||
@ -617,7 +617,8 @@ def supports_dtype(device, dtype): #TODO
|
|||||||
def device_supports_non_blocking(device):
|
def device_supports_non_blocking(device):
|
||||||
if is_device_mps(device):
|
if is_device_mps(device):
|
||||||
return False #pytorch bug? mps doesn't support non blocking
|
return False #pytorch bug? mps doesn't support non blocking
|
||||||
return True
|
return False
|
||||||
|
# return True #TODO: figure out why this causes issues
|
||||||
|
|
||||||
def cast_to_device(tensor, device, dtype, copy=False):
|
def cast_to_device(tensor, device, dtype, copy=False):
|
||||||
device_supports_cast = False
|
device_supports_cast = False
|
||||||
|
|||||||
@ -18,6 +18,26 @@ def apply_weight_decompose(dora_scale, weight):
|
|||||||
|
|
||||||
return weight * (dora_scale / weight_norm)
|
return weight * (dora_scale / weight_norm)
|
||||||
|
|
||||||
|
def set_model_options_patch_replace(model_options, patch, name, block_name, number, transformer_index=None):
|
||||||
|
to = model_options["transformer_options"].copy()
|
||||||
|
|
||||||
|
if "patches_replace" not in to:
|
||||||
|
to["patches_replace"] = {}
|
||||||
|
else:
|
||||||
|
to["patches_replace"] = to["patches_replace"].copy()
|
||||||
|
|
||||||
|
if name not in to["patches_replace"]:
|
||||||
|
to["patches_replace"][name] = {}
|
||||||
|
else:
|
||||||
|
to["patches_replace"][name] = to["patches_replace"][name].copy()
|
||||||
|
|
||||||
|
if transformer_index is not None:
|
||||||
|
block = (block_name, number, transformer_index)
|
||||||
|
else:
|
||||||
|
block = (block_name, number)
|
||||||
|
to["patches_replace"][name][block] = patch
|
||||||
|
model_options["transformer_options"] = to
|
||||||
|
return model_options
|
||||||
|
|
||||||
class ModelPatcher:
|
class ModelPatcher:
|
||||||
def __init__(self, model, load_device, offload_device, size=0, current_device=None, weight_inplace_update=False):
|
def __init__(self, model, load_device, offload_device, size=0, current_device=None, weight_inplace_update=False):
|
||||||
@ -109,16 +129,7 @@ class ModelPatcher:
|
|||||||
to["patches"][name] = to["patches"].get(name, []) + [patch]
|
to["patches"][name] = to["patches"].get(name, []) + [patch]
|
||||||
|
|
||||||
def set_model_patch_replace(self, patch, name, block_name, number, transformer_index=None):
|
def set_model_patch_replace(self, patch, name, block_name, number, transformer_index=None):
|
||||||
to = self.model_options["transformer_options"]
|
self.model_options = set_model_options_patch_replace(self.model_options, patch, name, block_name, number, transformer_index=transformer_index)
|
||||||
if "patches_replace" not in to:
|
|
||||||
to["patches_replace"] = {}
|
|
||||||
if name not in to["patches_replace"]:
|
|
||||||
to["patches_replace"][name] = {}
|
|
||||||
if transformer_index is not None:
|
|
||||||
block = (block_name, number, transformer_index)
|
|
||||||
else:
|
|
||||||
block = (block_name, number)
|
|
||||||
to["patches_replace"][name][block] = patch
|
|
||||||
|
|
||||||
def set_model_attn1_patch(self, patch):
|
def set_model_attn1_patch(self, patch):
|
||||||
self.set_model_patch(patch, "attn1_patch")
|
self.set_model_patch(patch, "attn1_patch")
|
||||||
|
|||||||
@ -8,7 +8,7 @@ class CLIPTextEncodeSDXLRefiner:
|
|||||||
"ascore": ("FLOAT", {"default": 6.0, "min": 0.0, "max": 1000.0, "step": 0.01}),
|
"ascore": ("FLOAT", {"default": 6.0, "min": 0.0, "max": 1000.0, "step": 0.01}),
|
||||||
"width": ("INT", {"default": 1024.0, "min": 0, "max": MAX_RESOLUTION}),
|
"width": ("INT", {"default": 1024.0, "min": 0, "max": MAX_RESOLUTION}),
|
||||||
"height": ("INT", {"default": 1024.0, "min": 0, "max": MAX_RESOLUTION}),
|
"height": ("INT", {"default": 1024.0, "min": 0, "max": MAX_RESOLUTION}),
|
||||||
"text": ("STRING", {"multiline": True}), "clip": ("CLIP", ),
|
"text": ("STRING", {"multiline": True, "dynamicPrompts": True}), "clip": ("CLIP", ),
|
||||||
}}
|
}}
|
||||||
RETURN_TYPES = ("CONDITIONING",)
|
RETURN_TYPES = ("CONDITIONING",)
|
||||||
FUNCTION = "encode"
|
FUNCTION = "encode"
|
||||||
@ -30,8 +30,8 @@ class CLIPTextEncodeSDXL:
|
|||||||
"crop_h": ("INT", {"default": 0, "min": 0, "max": MAX_RESOLUTION}),
|
"crop_h": ("INT", {"default": 0, "min": 0, "max": MAX_RESOLUTION}),
|
||||||
"target_width": ("INT", {"default": 1024.0, "min": 0, "max": MAX_RESOLUTION}),
|
"target_width": ("INT", {"default": 1024.0, "min": 0, "max": MAX_RESOLUTION}),
|
||||||
"target_height": ("INT", {"default": 1024.0, "min": 0, "max": MAX_RESOLUTION}),
|
"target_height": ("INT", {"default": 1024.0, "min": 0, "max": MAX_RESOLUTION}),
|
||||||
"text_g": ("STRING", {"multiline": True, "default": "CLIP_G"}), "clip": ("CLIP", ),
|
"text_g": ("STRING", {"multiline": True, "dynamicPrompts": True}), "clip": ("CLIP", ),
|
||||||
"text_l": ("STRING", {"multiline": True, "default": "CLIP_L"}), "clip": ("CLIP", ),
|
"text_l": ("STRING", {"multiline": True, "dynamicPrompts": True}), "clip": ("CLIP", ),
|
||||||
}}
|
}}
|
||||||
RETURN_TYPES = ("CONDITIONING",)
|
RETURN_TYPES = ("CONDITIONING",)
|
||||||
FUNCTION = "encode"
|
FUNCTION = "encode"
|
||||||
|
|||||||
@ -3,7 +3,7 @@
|
|||||||
class CLIPTextEncodeControlnet:
|
class CLIPTextEncodeControlnet:
|
||||||
@classmethod
|
@classmethod
|
||||||
def INPUT_TYPES(s):
|
def INPUT_TYPES(s):
|
||||||
return {"required": {"clip": ("CLIP", ), "conditioning": ("CONDITIONING", ), "text": ("STRING", {"multiline": True})}}
|
return {"required": {"clip": ("CLIP", ), "conditioning": ("CONDITIONING", ), "text": ("STRING", {"multiline": True, "dynamicPrompts": True})}}
|
||||||
RETURN_TYPES = ("CONDITIONING",)
|
RETURN_TYPES = ("CONDITIONING",)
|
||||||
FUNCTION = "encode"
|
FUNCTION = "encode"
|
||||||
|
|
||||||
|
|||||||
56
comfy_extras/nodes_pag.py
Normal file
56
comfy_extras/nodes_pag.py
Normal file
@ -0,0 +1,56 @@
|
|||||||
|
#Modified/simplified version of the node from: https://github.com/pamparamm/sd-perturbed-attention
|
||||||
|
#If you want the one with more options see the above repo.
|
||||||
|
|
||||||
|
#My modified one here is more basic but has less chances of breaking with ComfyUI updates.
|
||||||
|
|
||||||
|
import comfy.model_patcher
|
||||||
|
import comfy.samplers
|
||||||
|
|
||||||
|
class PerturbedAttentionGuidance:
|
||||||
|
@classmethod
|
||||||
|
def INPUT_TYPES(s):
|
||||||
|
return {
|
||||||
|
"required": {
|
||||||
|
"model": ("MODEL",),
|
||||||
|
"scale": ("FLOAT", {"default": 3.0, "min": 0.0, "max": 100.0, "step": 0.1, "round": 0.01}),
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
RETURN_TYPES = ("MODEL",)
|
||||||
|
FUNCTION = "patch"
|
||||||
|
|
||||||
|
CATEGORY = "_for_testing"
|
||||||
|
|
||||||
|
def patch(self, model, scale):
|
||||||
|
unet_block = "middle"
|
||||||
|
unet_block_id = 0
|
||||||
|
m = model.clone()
|
||||||
|
|
||||||
|
def perturbed_attention(q, k, v, extra_options, mask=None):
|
||||||
|
return v
|
||||||
|
|
||||||
|
def post_cfg_function(args):
|
||||||
|
model = args["model"]
|
||||||
|
cond_pred = args["cond_denoised"]
|
||||||
|
cond = args["cond"]
|
||||||
|
cfg_result = args["denoised"]
|
||||||
|
sigma = args["sigma"]
|
||||||
|
model_options = args["model_options"].copy()
|
||||||
|
x = args["input"]
|
||||||
|
|
||||||
|
if scale == 0:
|
||||||
|
return cfg_result
|
||||||
|
|
||||||
|
# Replace Self-attention with PAG
|
||||||
|
model_options = comfy.model_patcher.set_model_options_patch_replace(model_options, perturbed_attention, "attn1", unet_block, unet_block_id)
|
||||||
|
(pag,) = comfy.samplers.calc_cond_batch(model, [cond], x, sigma, model_options)
|
||||||
|
|
||||||
|
return cfg_result + (cond_pred - pag) * scale
|
||||||
|
|
||||||
|
m.set_model_sampler_post_cfg_function(post_cfg_function, disable_cfg1_optimization=True)
|
||||||
|
|
||||||
|
return (m,)
|
||||||
|
|
||||||
|
NODE_CLASS_MAPPINGS = {
|
||||||
|
"PerturbedAttentionGuidance": PerturbedAttentionGuidance,
|
||||||
|
}
|
||||||
@ -141,7 +141,7 @@ class PhotoMakerEncode:
|
|||||||
return {"required": { "photomaker": ("PHOTOMAKER",),
|
return {"required": { "photomaker": ("PHOTOMAKER",),
|
||||||
"image": ("IMAGE",),
|
"image": ("IMAGE",),
|
||||||
"clip": ("CLIP", ),
|
"clip": ("CLIP", ),
|
||||||
"text": ("STRING", {"multiline": True, "default": "photograph of photomaker"}),
|
"text": ("STRING", {"multiline": True, "dynamicPrompts": True, "default": "photograph of photomaker"}),
|
||||||
}}
|
}}
|
||||||
|
|
||||||
RETURN_TYPES = ("CONDITIONING",)
|
RETURN_TYPES = ("CONDITIONING",)
|
||||||
|
|||||||
5
nodes.py
5
nodes.py
@ -47,7 +47,7 @@ MAX_RESOLUTION=16384
|
|||||||
class CLIPTextEncode:
|
class CLIPTextEncode:
|
||||||
@classmethod
|
@classmethod
|
||||||
def INPUT_TYPES(s):
|
def INPUT_TYPES(s):
|
||||||
return {"required": {"text": ("STRING", {"multiline": True}), "clip": ("CLIP", )}}
|
return {"required": {"text": ("STRING", {"multiline": True, "dynamicPrompts": True}), "clip": ("CLIP", )}}
|
||||||
RETURN_TYPES = ("CONDITIONING",)
|
RETURN_TYPES = ("CONDITIONING",)
|
||||||
FUNCTION = "encode"
|
FUNCTION = "encode"
|
||||||
|
|
||||||
@ -966,7 +966,7 @@ class GLIGENTextBoxApply:
|
|||||||
return {"required": {"conditioning_to": ("CONDITIONING", ),
|
return {"required": {"conditioning_to": ("CONDITIONING", ),
|
||||||
"clip": ("CLIP", ),
|
"clip": ("CLIP", ),
|
||||||
"gligen_textbox_model": ("GLIGEN", ),
|
"gligen_textbox_model": ("GLIGEN", ),
|
||||||
"text": ("STRING", {"multiline": True}),
|
"text": ("STRING", {"multiline": True, "dynamicPrompts": True}),
|
||||||
"width": ("INT", {"default": 64, "min": 8, "max": MAX_RESOLUTION, "step": 8}),
|
"width": ("INT", {"default": 64, "min": 8, "max": MAX_RESOLUTION, "step": 8}),
|
||||||
"height": ("INT", {"default": 64, "min": 8, "max": MAX_RESOLUTION, "step": 8}),
|
"height": ("INT", {"default": 64, "min": 8, "max": MAX_RESOLUTION, "step": 8}),
|
||||||
"x": ("INT", {"default": 0, "min": 0, "max": MAX_RESOLUTION, "step": 8}),
|
"x": ("INT", {"default": 0, "min": 0, "max": MAX_RESOLUTION, "step": 8}),
|
||||||
@ -1942,6 +1942,7 @@ def init_custom_nodes():
|
|||||||
"nodes_differential_diffusion.py",
|
"nodes_differential_diffusion.py",
|
||||||
"nodes_ip2p.py",
|
"nodes_ip2p.py",
|
||||||
"nodes_model_merging_model_specific.py",
|
"nodes_model_merging_model_specific.py",
|
||||||
|
"nodes_pag.py",
|
||||||
]
|
]
|
||||||
|
|
||||||
import_failed = []
|
import_failed = []
|
||||||
|
|||||||
@ -17,7 +17,7 @@ app.registerExtension({
|
|||||||
// Locate dynamic prompt text widgets
|
// Locate dynamic prompt text widgets
|
||||||
// Include any widgets with dynamicPrompts set to true, and customtext
|
// Include any widgets with dynamicPrompts set to true, and customtext
|
||||||
const widgets = node.widgets.filter(
|
const widgets = node.widgets.filter(
|
||||||
(n) => (n.type === "customtext" && n.dynamicPrompts !== false) || n.dynamicPrompts
|
(n) => n.dynamicPrompts
|
||||||
);
|
);
|
||||||
for (const widget of widgets) {
|
for (const widget of widgets) {
|
||||||
// Override the serialization of the value to resolve dynamic prompts for all widgets supporting it in this node
|
// Override the serialization of the value to resolve dynamic prompts for all widgets supporting it in this node
|
||||||
|
|||||||
Loading…
x
Reference in New Issue
Block a user