nodes/cubiq-ComfyUI_IPAdapter_plus
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

tentatively remove autocast

Browse Source
This commit is contained in:
matt3o
2023-12-17 15:27:49 +01:00
parent 186b76eb58
commit 6a7e085efd
9 changed files with 982 additions and 942 deletions
Download Patch File Download Diff File Expand all files Collapse all files
IPAdapterPlus.py
+120 -134
View File
@@ -20,9 +20,10 @@ from .resampler import Resampler
GLOBAL_MODELS_DIR = os.path.join(folder_paths.models_dir, "ipadapter")
MODELS_DIR = GLOBAL_MODELS_DIR if os.path.isdir(GLOBAL_MODELS_DIR) else os.path.join(os.path.dirname(os.path.realpath(__file__)), "models")
if "ipadapter" not in folder_paths.folder_names_and_paths:
folder_paths.folder_names_and_paths["ipadapter"] = ([MODELS_DIR], folder_paths.supported_pt_extensions)
current_paths = [MODELS_DIR]
else:
folder_paths.folder_names_and_paths["ipadapter"][1].update(folder_paths.supported_pt_extensions)
current_paths, _ = folder_paths.folder_names_and_paths["ipadapter"]
folder_paths.folder_names_and_paths["ipadapter"] = (current_paths, folder_paths.supported_pt_extensions)
class MLPProjModel(torch.nn.Module):
"""SD model with image prompt"""
@@ -94,19 +95,10 @@ def image_add_noise(image, noise):
def zeroed_hidden_states(clip_vision, batch_size):
image = torch.zeros([batch_size, 224, 224, 3])
comfy.model_management.load_model_gpu(clip_vision.patcher)
pixel_values = clip_preprocess(image.to(clip_vision.load_device))
if clip_vision.dtype != torch.float32:
precision_scope = torch.autocast
else:
precision_scope = lambda a, b: contextlib.nullcontext(a)
with precision_scope(comfy.model_management.get_autocast_device(clip_vision.load_device), torch.float32):
outputs = clip_vision.model(pixel_values, intermediate_output=-2)
pixel_values = clip_preprocess(image.to(clip_vision.load_device)).float()
outputs = clip_vision.model(pixel_values=pixel_values, intermediate_output=-2)
# we only need the penultimate hidden states
outputs = outputs[1].to(comfy.model_management.intermediate_device())
return outputs
def min_(tensor_list):
@@ -211,13 +203,11 @@ class IPAdapter(nn.Module):
class CrossAttentionPatch:
# forward for patching
def __init__(self, weight, ipadapter, device, dtype, number, cond, uncond, weight_type, mask=None, sigma_start=0.0, sigma_end=1.0, unfold_batch=False):
def __init__(self, weight, ipadapter, number, cond, uncond, weight_type, mask=None, sigma_start=0.0, sigma_end=1.0, unfold_batch=False):
self.weights = [weight]
self.ipadapters = [ipadapter]
self.conds = [cond]
self.unconds = [uncond]
self.device = 'cuda' if 'cuda' in device.type else 'cpu'
self.dtype = dtype if 'cuda' in self.device else torch.bfloat16
self.number = number
self.weight_type = [weight_type]
self.masks = [mask]
@@ -228,14 +218,12 @@ class CrossAttentionPatch:
self.k_key = str(self.number*2+1) + "_to_k_ip"
self.v_key = str(self.number*2+1) + "_to_v_ip"
def set_new_condition(self, weight, ipadapter, device, dtype, number, cond, uncond, weight_type, mask=None, sigma_start=0.0, sigma_end=1.0, unfold_batch=False):
def set_new_condition(self, weight, ipadapter, number, cond, uncond, weight_type, mask=None, sigma_start=0.0, sigma_end=1.0, unfold_batch=False):
self.weights.append(weight)
self.ipadapters.append(ipadapter)
self.conds.append(cond)
self.unconds.append(uncond)
self.masks.append(mask)
self.device = 'cuda' if 'cuda' in device.type else 'cpu'
self.dtype = dtype if 'cuda' in self.device else torch.bfloat16
self.weight_type.append(weight_type)
self.sigma_start.append(sigma_start)
self.sigma_end.append(sigma_end)
@@ -249,122 +237,121 @@ class CrossAttentionPatch:
# extra options for AnimateDiff
ad_params = extra_options['ad_params'] if "ad_params" in extra_options else None
with torch.autocast(device_type=self.device, dtype=self.dtype):
q = n
k = context_attn2
v = value_attn2
b = q.shape[0]
qs = q.shape[1]
batch_prompt = b // len(cond_or_uncond)
out = optimized_attention(q, k, v, extra_options["n_heads"])
_, _, lh, lw = extra_options["original_shape"]
for weight, cond, uncond, ipadapter, mask, weight_type, sigma_start, sigma_end, unfold_batch in zip(self.weights, self.conds, self.unconds, self.ipadapters, self.masks, self.weight_type, self.sigma_start, self.sigma_end, self.unfold_batch):
if sigma > sigma_start or sigma < sigma_end:
continue
q = n
k = context_attn2
v = value_attn2
b = q.shape[0]
qs = q.shape[1]
batch_prompt = b // len(cond_or_uncond)
out = optimized_attention(q, k, v, extra_options["n_heads"])
_, _, lh, lw = extra_options["original_shape"]
for weight, cond, uncond, ipadapter, mask, weight_type, sigma_start, sigma_end, unfold_batch in zip(self.weights, self.conds, self.unconds, self.ipadapters, self.masks, self.weight_type, self.sigma_start, self.sigma_end, self.unfold_batch):
if sigma > sigma_start or sigma < sigma_end:
continue
if unfold_batch and cond.shape[0] > 1:
# Check AnimateDiff context window
if ad_params is not None and ad_params["sub_idxs"] is not None:
# if images length matches or exceeds full_length get sub_idx images
if cond.shape[0] >= ad_params["full_length"]:
cond = torch.Tensor(cond[ad_params["sub_idxs"]])
uncond = torch.Tensor(uncond[ad_params["sub_idxs"]])
# otherwise, need to do more to get proper sub_idxs masks
else:
# check if images length matches full_length - if not, make it match
if cond.shape[0] < ad_params["full_length"]:
cond = torch.cat((cond, cond[-1:].repeat((ad_params["full_length"]-cond.shape[0], 1, 1))), dim=0)
uncond = torch.cat((uncond, uncond[-1:].repeat((ad_params["full_length"]-uncond.shape[0], 1, 1))), dim=0)
# if we have too many remove the excess (should not happen, but just in case)
if cond.shape[0] > ad_params["full_length"]:
cond = cond[:ad_params["full_length"]]
uncond = uncond[:ad_params["full_length"]]
cond = cond[ad_params["sub_idxs"]]
uncond = uncond[ad_params["sub_idxs"]]
# if we don't have enough reference images repeat the last one until we reach the right size
if cond.shape[0] < batch_prompt:
cond = torch.cat((cond, cond[-1:].repeat((batch_prompt-cond.shape[0], 1, 1))), dim=0)
uncond = torch.cat((uncond, uncond[-1:].repeat((batch_prompt-uncond.shape[0], 1, 1))), dim=0)
# if we have too many remove the exceeding
elif cond.shape[0] > batch_prompt:
cond = cond[:batch_prompt]
uncond = uncond[:batch_prompt]
k_cond = ipadapter.ip_layers.to_kvs[self.k_key](cond)
k_uncond = ipadapter.ip_layers.to_kvs[self.k_key](uncond)
v_cond = ipadapter.ip_layers.to_kvs[self.v_key](cond)
v_uncond = ipadapter.ip_layers.to_kvs[self.v_key](uncond)
else:
k_cond = ipadapter.ip_layers.to_kvs[self.k_key](cond).repeat(batch_prompt, 1, 1)
k_uncond = ipadapter.ip_layers.to_kvs[self.k_key](uncond).repeat(batch_prompt, 1, 1)
v_cond = ipadapter.ip_layers.to_kvs[self.v_key](cond).repeat(batch_prompt, 1, 1)
v_uncond = ipadapter.ip_layers.to_kvs[self.v_key](uncond).repeat(batch_prompt, 1, 1)
if weight_type.startswith("linear"):
ip_k = torch.cat([(k_cond, k_uncond)[i] for i in cond_or_uncond], dim=0) * weight
ip_v = torch.cat([(v_cond, v_uncond)[i] for i in cond_or_uncond], dim=0) * weight
else:
ip_k = torch.cat([(k_cond, k_uncond)[i] for i in cond_or_uncond], dim=0)
ip_v = torch.cat([(v_cond, v_uncond)[i] for i in cond_or_uncond], dim=0)
if weight_type.startswith("channel"):
# code by Lvmin Zhang at Stanford University as also seen on Fooocus IPAdapter implementation
# please read licensing notes https://github.com/lllyasviel/Fooocus/blob/main/fooocus_extras/ip_adapter.py#L225
ip_v_mean = torch.mean(ip_v, dim=1, keepdim=True)
ip_v_offset = ip_v - ip_v_mean
_, _, C = ip_k.shape
channel_penalty = float(C) / 1280.0
W = weight * channel_penalty
ip_k = ip_k * W
ip_v = ip_v_offset + ip_v_mean * W
out_ip = optimized_attention(q, ip_k, ip_v, extra_options["n_heads"])
if weight_type.startswith("original"):
out_ip = out_ip * weight
if mask is not None:
# TODO: needs checking
mask_h = max(1, round(lh / math.sqrt(lh * lw / qs)))
mask_w = qs // mask_h
# check if using AnimateDiff and sliding context window
if (mask.shape[0] > 1 and ad_params is not None and ad_params["sub_idxs"] is not None):
# if mask length matches or exceeds full_length, just get sub_idx masks, resize, and continue
if mask.shape[0] >= ad_params["full_length"]:
mask_downsample = torch.Tensor(mask[ad_params["sub_idxs"]])
mask_downsample = F.interpolate(mask_downsample.unsqueeze(1), size=(mask_h, mask_w), mode="bicubic").squeeze(1)
# otherwise, need to do more to get proper sub_idxs masks
else:
# resize to needed attention size (to save on memory)
mask_downsample = F.interpolate(mask.unsqueeze(1), size=(mask_h, mask_w), mode="bicubic").squeeze(1)
# check if mask length matches full_length - if not, make it match
if mask_downsample.shape[0] < ad_params["full_length"]:
mask_downsample = torch.cat((mask_downsample, mask_downsample[-1:].repeat((ad_params["full_length"]-mask_downsample.shape[0], 1, 1))), dim=0)
# if we have too many remove the excess (should not happen, but just in case)
if mask_downsample.shape[0] > ad_params["full_length"]:
mask_downsample = mask_downsample[:ad_params["full_length"]]
# now, select sub_idxs masks
mask_downsample = mask_downsample[ad_params["sub_idxs"]]
# otherwise, perform usual mask interpolation
if unfold_batch and cond.shape[0] > 1:
# Check AnimateDiff context window
if ad_params is not None and ad_params["sub_idxs"] is not None:
# if images length matches or exceeds full_length get sub_idx images
if cond.shape[0] >= ad_params["full_length"]:
cond = torch.Tensor(cond[ad_params["sub_idxs"]])
uncond = torch.Tensor(uncond[ad_params["sub_idxs"]])
# otherwise, need to do more to get proper sub_idxs masks
else:
# check if images length matches full_length - if not, make it match
if cond.shape[0] < ad_params["full_length"]:
cond = torch.cat((cond, cond[-1:].repeat((ad_params["full_length"]-cond.shape[0], 1, 1))), dim=0)
uncond = torch.cat((uncond, uncond[-1:].repeat((ad_params["full_length"]-uncond.shape[0], 1, 1))), dim=0)
# if we have too many remove the excess (should not happen, but just in case)
if cond.shape[0] > ad_params["full_length"]:
cond = cond[:ad_params["full_length"]]
uncond = uncond[:ad_params["full_length"]]
cond = cond[ad_params["sub_idxs"]]
uncond = uncond[ad_params["sub_idxs"]]
# if we don't have enough reference images repeat the last one until we reach the right size
if cond.shape[0] < batch_prompt:
cond = torch.cat((cond, cond[-1:].repeat((batch_prompt-cond.shape[0], 1, 1))), dim=0)
uncond = torch.cat((uncond, uncond[-1:].repeat((batch_prompt-uncond.shape[0], 1, 1))), dim=0)
# if we have too many remove the exceeding
elif cond.shape[0] > batch_prompt:
cond = cond[:batch_prompt]
uncond = uncond[:batch_prompt]
k_cond = ipadapter.ip_layers.to_kvs[self.k_key](cond)
k_uncond = ipadapter.ip_layers.to_kvs[self.k_key](uncond)
v_cond = ipadapter.ip_layers.to_kvs[self.v_key](cond)
v_uncond = ipadapter.ip_layers.to_kvs[self.v_key](uncond)
else:
k_cond = ipadapter.ip_layers.to_kvs[self.k_key](cond).repeat(batch_prompt, 1, 1)
k_uncond = ipadapter.ip_layers.to_kvs[self.k_key](uncond).repeat(batch_prompt, 1, 1)
v_cond = ipadapter.ip_layers.to_kvs[self.v_key](cond).repeat(batch_prompt, 1, 1)
v_uncond = ipadapter.ip_layers.to_kvs[self.v_key](uncond).repeat(batch_prompt, 1, 1)
if weight_type.startswith("linear"):
ip_k = torch.cat([(k_cond, k_uncond)[i] for i in cond_or_uncond], dim=0) * weight
ip_v = torch.cat([(v_cond, v_uncond)[i] for i in cond_or_uncond], dim=0) * weight
else:
ip_k = torch.cat([(k_cond, k_uncond)[i] for i in cond_or_uncond], dim=0)
ip_v = torch.cat([(v_cond, v_uncond)[i] for i in cond_or_uncond], dim=0)
if weight_type.startswith("channel"):
# code by Lvmin Zhang at Stanford University as also seen on Fooocus IPAdapter implementation
# please read licensing notes https://github.com/lllyasviel/Fooocus/blob/69a23c4d60c9e627409d0cb0f8862cdb015488eb/extras/ip_adapter.py#L234
ip_v_mean = torch.mean(ip_v, dim=1, keepdim=True)
ip_v_offset = ip_v - ip_v_mean
_, _, C = ip_k.shape
channel_penalty = float(C) / 1280.0
W = weight * channel_penalty
ip_k = ip_k * W
ip_v = ip_v_offset + ip_v_mean * W
out_ip = optimized_attention(q, ip_k, ip_v, extra_options["n_heads"])
if weight_type.startswith("original"):
out_ip = out_ip * weight
if mask is not None:
# TODO: needs checking
mask_h = max(1, round(lh / math.sqrt(lh * lw / qs)))
mask_w = qs // mask_h
# check if using AnimateDiff and sliding context window
if (mask.shape[0] > 1 and ad_params is not None and ad_params["sub_idxs"] is not None):
# if mask length matches or exceeds full_length, just get sub_idx masks, resize, and continue
if mask.shape[0] >= ad_params["full_length"]:
mask_downsample = torch.Tensor(mask[ad_params["sub_idxs"]])
mask_downsample = F.interpolate(mask_downsample.unsqueeze(1), size=(mask_h, mask_w), mode="bicubic").squeeze(1)
# otherwise, need to do more to get proper sub_idxs masks
else:
# resize to needed attention size (to save on memory)
mask_downsample = F.interpolate(mask.unsqueeze(1), size=(mask_h, mask_w), mode="bicubic").squeeze(1)
# check if mask length matches full_length - if not, make it match
if mask_downsample.shape[0] < ad_params["full_length"]:
mask_downsample = torch.cat((mask_downsample, mask_downsample[-1:].repeat((ad_params["full_length"]-mask_downsample.shape[0], 1, 1))), dim=0)
# if we have too many remove the excess (should not happen, but just in case)
if mask_downsample.shape[0] > ad_params["full_length"]:
mask_downsample = mask_downsample[:ad_params["full_length"]]
# now, select sub_idxs masks
mask_downsample = mask_downsample[ad_params["sub_idxs"]]
# otherwise, perform usual mask interpolation
else:
mask_downsample = F.interpolate(mask.unsqueeze(1), size=(mask_h, mask_w), mode="bicubic").squeeze(1)
# if we don't have enough masks repeat the last one until we reach the right size
if mask_downsample.shape[0] < batch_prompt:
mask_downsample = torch.cat((mask_downsample, mask_downsample[-1:, :, :].repeat((batch_prompt-mask_downsample.shape[0], 1, 1))), dim=0)
# if we have too many remove the exceeding
elif mask_downsample.shape[0] > batch_prompt:
mask_downsample = mask_downsample[:batch_prompt, :, :]
# repeat the masks
mask_downsample = mask_downsample.repeat(len(cond_or_uncond), 1, 1)
mask_downsample = mask_downsample.view(mask_downsample.shape[0], -1, 1).repeat(1, 1, out.shape[2])
# if we don't have enough masks repeat the last one until we reach the right size
if mask_downsample.shape[0] < batch_prompt:
mask_downsample = torch.cat((mask_downsample, mask_downsample[-1:, :, :].repeat((batch_prompt-mask_downsample.shape[0], 1, 1))), dim=0)
# if we have too many remove the exceeding
elif mask_downsample.shape[0] > batch_prompt:
mask_downsample = mask_downsample[:batch_prompt, :, :]
# repeat the masks
mask_downsample = mask_downsample.repeat(len(cond_or_uncond), 1, 1)
mask_downsample = mask_downsample.view(mask_downsample.shape[0], -1, 1).repeat(1, 1, out.shape[2])
out_ip = out_ip * mask_downsample
out_ip = out_ip * mask_downsample
out = out + out_ip
out = out + out_ip
return out.to(dtype=org_dtype)
@@ -424,6 +411,7 @@ class IPAdapterApply:
def apply_ipadapter(self, ipadapter, model, weight, clip_vision=None, image=None, weight_type="original", noise=None, embeds=None, attn_mask=None, start_at=0.0, end_at=1.0, unfold_batch=False):
self.dtype = model.model.diffusion_model.dtype
self.embeds_dtype = comfy.model_management.text_encoder_dtype(comfy.model_management.text_encoder_device()) # text and image embeds should have the same dtype
self.device = comfy.model_management.get_torch_device()
self.weight = weight
self.is_full = "proj.0.weight" in ipadapter["image_proj"]
@@ -473,9 +461,9 @@ class IPAdapterApply:
self.ipadapter.to(self.device, dtype=self.dtype)
image_prompt_embeds, uncond_image_prompt_embeds = self.ipadapter.get_image_embeds(clip_embed.to(self.device, self.dtype), clip_embed_zeroed.to(self.device, self.dtype))
image_prompt_embeds = image_prompt_embeds.to(self.device, dtype=self.dtype)
uncond_image_prompt_embeds = uncond_image_prompt_embeds.to(self.device, dtype=self.dtype)
image_prompt_embeds, uncond_image_prompt_embeds = self.ipadapter.get_image_embeds(clip_embed.to(self.device, dtype=self.embeds_dtype), clip_embed_zeroed.to(self.device, dtype=self.embeds_dtype))
image_prompt_embeds = image_prompt_embeds.to(self.device, dtype=self.embeds_dtype)
uncond_image_prompt_embeds = uncond_image_prompt_embeds.to(self.device, dtype=self.embeds_dtype)
work_model = model.clone()
@@ -489,8 +477,6 @@ class IPAdapterApply:
"number": 0,
"weight": self.weight,
"ipadapter": self.ipadapter,
"device": self.device,
"dtype": self.dtype,
"cond": image_prompt_embeds,
"uncond": uncond_image_prompt_embeds,
"weight_type": weight_type,
examples/IPAdapter_2_masks.json
+132 -126
View File
@@ -331,69 +331,6 @@
"Node name for S&R": "PreviewImage"
}
},
{
"id": 50,
"type": "IPAdapterApply",
"pos": [
1030,
-220
],
"size": {
"0": 210,
"1": 190
},
"flags": {},
"order": 19,
"mode": 0,
"inputs": [
{
"name": "ipadapter",
"type": "IPADAPTER",
"link": 79
},
{
"name": "clip_vision",
"type": "CLIP_VISION",
"link": 80
},
{
"name": "image",
"type": "IMAGE",
"link": 92
},
{
"name": "model",
"type": "MODEL",
"link": 90
},
{
"name": "attn_mask",
"type": "MASK",
"link": 83
}
],
"outputs": [
{
"name": "MODEL",
"type": "MODEL",
"links": [
84
],
"shape": 3,
"slot_index": 0
}
],
"properties": {
"Node name for S&R": "IPAdapterApply"
},
"widgets_values": [
0.7000000000000001,
0.5,
"channel penalty"
],
"color": "#223",
"bgcolor": "#335"
},
{
"id": 52,
"type": "PrepImageForClipVision",
@@ -777,69 +714,6 @@
"color": "#232",
"bgcolor": "#353"
},
{
"id": 51,
"type": "IPAdapterApply",
"pos": [
468,
-169
],
"size": {
"0": 210,
"1": 190
},
"flags": {},
"order": 18,
"mode": 0,
"inputs": [
{
"name": "ipadapter",
"type": "IPADAPTER",
"link": 85
},
{
"name": "clip_vision",
"type": "CLIP_VISION",
"link": 86
},
{
"name": "image",
"type": "IMAGE",
"link": 87
},
{
"name": "model",
"type": "MODEL",
"link": 88
},
{
"name": "attn_mask",
"type": "MASK",
"link": 89
}
],
"outputs": [
{
"name": "MODEL",
"type": "MODEL",
"links": [
90
],
"shape": 3,
"slot_index": 0
}
],
"properties": {
"Node name for S&R": "IPAdapterApply"
},
"widgets_values": [
0.7000000000000001,
0.5,
"channel penalty"
],
"color": "#223",
"bgcolor": "#335"
},
{
"id": 27,
"type": "LoadImage",
@@ -975,6 +849,138 @@
"karras",
1
]
},
{
"id": 51,
"type": "IPAdapterApply",
"pos": [
523,
-214
],
"size": {
"0": 210,
"1": 258
},
"flags": {},
"order": 18,
"mode": 0,
"inputs": [
{
"name": "ipadapter",
"type": "IPADAPTER",
"link": 85
},
{
"name": "clip_vision",
"type": "CLIP_VISION",
"link": 86
},
{
"name": "image",
"type": "IMAGE",
"link": 87
},
{
"name": "model",
"type": "MODEL",
"link": 88
},
{
"name": "attn_mask",
"type": "MASK",
"link": 89
}
],
"outputs": [
{
"name": "MODEL",
"type": "MODEL",
"links": [
90
],
"shape": 3,
"slot_index": 0
}
],
"properties": {
"Node name for S&R": "IPAdapterApply"
},
"widgets_values": [
0.7000000000000001,
0.5,
"channel penalty",
0,
1,
false
],
"color": "#223",
"bgcolor": "#335"
},
{
"id": 50,
"type": "IPAdapterApply",
"pos": [
1030,
-220
],
"size": {
"0": 210,
"1": 258
},
"flags": {},
"order": 19,
"mode": 0,
"inputs": [
{
"name": "ipadapter",
"type": "IPADAPTER",
"link": 79
},
{
"name": "clip_vision",
"type": "CLIP_VISION",
"link": 80
},
{
"name": "image",
"type": "IMAGE",
"link": 92
},
{
"name": "model",
"type": "MODEL",
"link": 90
},
{
"name": "attn_mask",
"type": "MASK",
"link": 83
}
],
"outputs": [
{
"name": "MODEL",
"type": "MODEL",
"links": [
84
],
"shape": 3,
"slot_index": 0
}
],
"properties": {
"Node name for S&R": "IPAdapterApply"
},
"widgets_values": [
0.7000000000000001,
0.5,
"channel penalty",
0,
1,
false
],
"color": "#223",
"bgcolor": "#335"
}
],
"links": [
examples/IPAdapter_batch_images.json
+132 -123
View File
@@ -36,38 +36,6 @@
1
]
},
{
"id": 3,
"type": "IPAdapterModelLoader",
"pos": [
290,
60
],
"size": {
"0": 300,
"1": 60
},
"flags": {},
"order": 1,
"mode": 0,
"outputs": [
{
"name": "IPADAPTER",
"type": "IPADAPTER",
"links": [
1
],
"shape": 3,
"slot_index": 0
}
],
"properties": {
"Node name for S&R": "IPAdapterModelLoader"
},
"widgets_values": [
"ip-adapter_sd15.bin"
]
},
{
"id": 8,
"type": "CLIPTextEncode",
@@ -203,7 +171,7 @@
"1": 60
},
"flags": {},
"order": 2,
"order": 1,
"mode": 0,
"outputs": [
{
@@ -249,61 +217,6 @@
"IPAdapter"
]
},
{
"id": 5,
"type": "IPAdapterApply",
"pos": [
650,
60
],
"size": {
"0": 210,
"1": 142
},
"flags": {},
"order": 10,
"mode": 0,
"inputs": [
{
"name": "ipadapter",
"type": "IPADAPTER",
"link": 1
},
{
"name": "clip_vision",
"type": "CLIP_VISION",
"link": 2
},
{
"name": "image",
"type": "IMAGE",
"link": 23
},
{
"name": "model",
"type": "MODEL",
"link": 4
}
],
"outputs": [
{
"name": "MODEL",
"type": "MODEL",
"links": [
7
],
"shape": 3,
"slot_index": 0
}
],
"properties": {
"Node name for S&R": "IPAdapterApply"
},
"widgets_values": [
1,
0
]
},
{
"id": 9,
"type": "KSampler",
@@ -364,38 +277,6 @@
1
]
},
{
"id": 4,
"type": "CLIPVisionLoader",
"pos": [
290,
170
],
"size": {
"0": 300,
"1": 60
},
"flags": {},
"order": 3,
"mode": 0,
"outputs": [
{
"name": "CLIP_VISION",
"type": "CLIP_VISION",
"links": [
2
],
"shape": 3,
"slot_index": 0
}
],
"properties": {
"Node name for S&R": "CLIPVisionLoader"
},
"widgets_values": [
"IPAdapter_image_encoder_sd15.safetensors"
]
},
{
"id": 6,
"type": "LoadImage",
@@ -408,7 +289,7 @@
"1": 320
},
"flags": {},
"order": 4,
"order": 2,
"mode": 0,
"outputs": [
{
@@ -447,7 +328,7 @@
"1": 320
},
"flags": {},
"order": 5,
"order": 3,
"mode": 0,
"outputs": [
{
@@ -527,7 +408,7 @@
"1": 100
},
"flags": {},
"order": 6,
"order": 4,
"mode": 0,
"outputs": [
{
@@ -562,6 +443,134 @@
"widgets_values": [
"sd15/absolutereality_v181.safetensors"
]
},
{
"id": 5,
"type": "IPAdapterApply",
"pos": [
649,
-62
],
"size": {
"0": 210,
"1": 258
},
"flags": {},
"order": 10,
"mode": 0,
"inputs": [
{
"name": "ipadapter",
"type": "IPADAPTER",
"link": 1
},
{
"name": "clip_vision",
"type": "CLIP_VISION",
"link": 2
},
{
"name": "image",
"type": "IMAGE",
"link": 23
},
{
"name": "model",
"type": "MODEL",
"link": 4
},
{
"name": "attn_mask",
"type": "MASK",
"link": null
}
],
"outputs": [
{
"name": "MODEL",
"type": "MODEL",
"links": [
7
],
"shape": 3,
"slot_index": 0
}
],
"properties": {
"Node name for S&R": "IPAdapterApply"
},
"widgets_values": [
1,
0,
"original",
0,
1,
false
]
},
{
"id": 3,
"type": "IPAdapterModelLoader",
"pos": [
291,
-35
],
"size": {
"0": 300,
"1": 60
},
"flags": {},
"order": 5,
"mode": 0,
"outputs": [
{
"name": "IPADAPTER",
"type": "IPADAPTER",
"links": [
1
],
"shape": 3,
"slot_index": 0
}
],
"properties": {
"Node name for S&R": "IPAdapterModelLoader"
},
"widgets_values": [
"ip-adapter_sd15.safetensors"
]
},
{
"id": 4,
"type": "CLIPVisionLoader",
"pos": [
297,
82
],
"size": {
"0": 300,
"1": 60
},
"flags": {},
"order": 6,
"mode": 0,
"outputs": [
{
"name": "CLIP_VISION",
"type": "CLIP_VISION",
"links": [
2
],
"shape": 3,
"slot_index": 0
}
],
"properties": {
"Node name for S&R": "CLIPVisionLoader"
},
"widgets_values": [
"IPAdapter_image_encoder_sd15.safetensors"
]
}
],
"links": [
examples/IPAdapter_face.json
+190 -181
View File
@@ -2,47 +2,6 @@
"last_node_id": 18,
"last_link_id": 28,
"nodes": [
{
"id": 8,
"type": "CLIPTextEncode",
"pos": [
650,
420
],
"size": {
"0": 210,
"1": 120
},
"flags": {},
"order": 7,
"mode": 0,
"inputs": [
{
"name": "clip",
"type": "CLIP",
"link": 6
}
],
"outputs": [
{
"name": "CONDITIONING",
"type": "CONDITIONING",
"links": [
9
],
"shape": 3,
"slot_index": 0
}
],
"properties": {
"Node name for S&R": "CLIPTextEncode"
},
"widgets_values": [
"blurry, horror"
],
"color": "#322",
"bgcolor": "#533"
},
{
"id": 11,
"type": "VAEDecode",
@@ -110,86 +69,6 @@
"IPAdapter"
]
},
{
"id": 1,
"type": "CheckpointLoaderSimple",
"pos": [
290,
280
],
"size": {
"0": 300,
"1": 100
},
"flags": {},
"order": 0,
"mode": 0,
"outputs": [
{
"name": "MODEL",
"type": "MODEL",
"links": [
4
],
"shape": 3,
"slot_index": 0
},
{
"name": "CLIP",
"type": "CLIP",
"links": [
5,
6
],
"shape": 3,
"slot_index": 1
},
{
"name": "VAE",
"type": "VAE",
"links": null,
"shape": 3
}
],
"properties": {
"Node name for S&R": "CheckpointLoaderSimple"
},
"widgets_values": [
"realisticVisionV51_v51VAE.safetensors"
]
},
{
"id": 3,
"type": "IPAdapterModelLoader",
"pos": [
290,
60
],
"size": {
"0": 300,
"1": 60
},
"flags": {},
"order": 1,
"mode": 0,
"outputs": [
{
"name": "IPADAPTER",
"type": "IPADAPTER",
"links": [
1
],
"shape": 3,
"slot_index": 0
}
],
"properties": {
"Node name for S&R": "IPAdapterModelLoader"
},
"widgets_values": [
"ip-adapter-plus-face_sd15.bin"
]
},
{
"id": 2,
"type": "VAELoader",
@@ -202,7 +81,7 @@
"1": 60
},
"flags": {},
"order": 2,
"order": 0,
"mode": 0,
"outputs": [
{
@@ -234,7 +113,7 @@
"1": 120
},
"flags": {},
"order": 6,
"order": 7,
"mode": 0,
"inputs": [
{
@@ -275,7 +154,7 @@
"1": 110
},
"flags": {},
"order": 3,
"order": 1,
"mode": 0,
"outputs": [
{
@@ -309,7 +188,7 @@
"1": 320
},
"flags": {},
"order": 4,
"order": 2,
"mode": 0,
"outputs": [
{
@@ -348,7 +227,7 @@
"1": 60
},
"flags": {},
"order": 5,
"order": 3,
"mode": 0,
"outputs": [
{
@@ -368,61 +247,6 @@
"IPAdapter_image_encoder_sd15.safetensors"
]
},
{
"id": 5,
"type": "IPAdapterApply",
"pos": [
650,
60
],
"size": {
"0": 210,
"1": 142
},
"flags": {},
"order": 8,
"mode": 0,
"inputs": [
{
"name": "ipadapter",
"type": "IPADAPTER",
"link": 1
},
{
"name": "clip_vision",
"type": "CLIP_VISION",
"link": 2
},
{
"name": "image",
"type": "IMAGE",
"link": 28
},
{
"name": "model",
"type": "MODEL",
"link": 4
}
],
"outputs": [
{
"name": "MODEL",
"type": "MODEL",
"links": [
7
],
"shape": 3,
"slot_index": 0
}
],
"properties": {
"Node name for S&R": "IPAdapterApply"
},
"widgets_values": [
0.6000000000000001,
0.3
]
},
{
"id": 9,
"type": "KSampler",
@@ -482,6 +306,191 @@
"ddim_uniform",
1
]
},
{
"id": 5,
"type": "IPAdapterApply",
"pos": [
654,
-52
],
"size": {
"0": 210,
"1": 258
},
"flags": {},
"order": 6,
"mode": 0,
"inputs": [
{
"name": "ipadapter",
"type": "IPADAPTER",
"link": 1
},
{
"name": "clip_vision",
"type": "CLIP_VISION",
"link": 2
},
{
"name": "image",
"type": "IMAGE",
"link": 28
},
{
"name": "model",
"type": "MODEL",
"link": 4
},
{
"name": "attn_mask",
"type": "MASK",
"link": null
}
],
"outputs": [
{
"name": "MODEL",
"type": "MODEL",
"links": [
7
],
"shape": 3,
"slot_index": 0
}
],
"properties": {
"Node name for S&R": "IPAdapterApply"
},
"widgets_values": [
0.6000000000000001,
0.3,
"original",
0,
1,
false
]
},
{
"id": 3,
"type": "IPAdapterModelLoader",
"pos": [
290,
60
],
"size": {
"0": 300,
"1": 60
},
"flags": {},
"order": 4,
"mode": 0,
"outputs": [
{
"name": "IPADAPTER",
"type": "IPADAPTER",
"links": [
1
],
"shape": 3,
"slot_index": 0
}
],
"properties": {
"Node name for S&R": "IPAdapterModelLoader"
},
"widgets_values": [
"ip-adapter-plus-face_sd15.safetensors"
]
},
{
"id": 8,
"type": "CLIPTextEncode",
"pos": [
650,
420
],
"size": {
"0": 210,
"1": 120
},
"flags": {},
"order": 8,
"mode": 0,
"inputs": [
{
"name": "clip",
"type": "CLIP",
"link": 6
}
],
"outputs": [
{
"name": "CONDITIONING",
"type": "CONDITIONING",
"links": [
9
],
"shape": 3,
"slot_index": 0
}
],
"properties": {
"Node name for S&R": "CLIPTextEncode"
},
"widgets_values": [
"blurry, horror, distorted, malformed, monochrome"
],
"color": "#322",
"bgcolor": "#533"
},
{
"id": 1,
"type": "CheckpointLoaderSimple",
"pos": [
290,
280
],
"size": {
"0": 300,
"1": 100
},
"flags": {},
"order": 5,
"mode": 0,
"outputs": [
{
"name": "MODEL",
"type": "MODEL",
"links": [
4
],
"shape": 3,
"slot_index": 0
},
{
"name": "CLIP",
"type": "CLIP",
"links": [
5,
6
],
"shape": 3,
"slot_index": 1
},
{
"name": "VAE",
"type": "VAE",
"links": null,
"shape": 3
}
],
"properties": {
"Node name for S&R": "CheckpointLoaderSimple"
},
"widgets_values": [
"sd15/realisticVisionV51_v51VAE.safetensors"
]
}
],
"links": [
examples/IPAdapter_inpaint.json
+143 -134
View File
@@ -14,7 +14,7 @@
"1": 120
},
"flags": {},
"order": 9,
"order": 7,
"mode": 0,
"inputs": [
{
@@ -122,7 +122,7 @@
"1": 120
},
"flags": {},
"order": 8,
"order": 6,
"mode": 0,
"inputs": [
{
@@ -190,61 +190,6 @@
"image"
]
},
{
"id": 5,
"type": "IPAdapterApply",
"pos": [
650,
60
],
"size": {
"0": 210,
"1": 142
},
"flags": {},
"order": 7,
"mode": 0,
"inputs": [
{
"name": "ipadapter",
"type": "IPADAPTER",
"link": 1
},
{
"name": "clip_vision",
"type": "CLIP_VISION",
"link": 2
},
{
"name": "image",
"type": "IMAGE",
"link": 28
},
{
"name": "model",
"type": "MODEL",
"link": 4
}
],
"outputs": [
{
"name": "MODEL",
"type": "MODEL",
"links": [
7
],
"shape": 3,
"slot_index": 0
}
],
"properties": {
"Node name for S&R": "IPAdapterApply"
},
"widgets_values": [
0.8,
0
]
},
{
"id": 2,
"type": "VAELoader",
@@ -338,38 +283,6 @@
1
]
},
{
"id": 3,
"type": "IPAdapterModelLoader",
"pos": [
290,
60
],
"size": {
"0": 300,
"1": 60
},
"flags": {},
"order": 2,
"mode": 0,
"outputs": [
{
"name": "IPADAPTER",
"type": "IPADAPTER",
"links": [
1
],
"shape": 3,
"slot_index": 0
}
],
"properties": {
"Node name for S&R": "IPAdapterModelLoader"
},
"widgets_values": [
"ip-adapter-plus_sd15.bin"
]
},
{
"id": 20,
"type": "VAEEncodeForInpaint",
@@ -382,7 +295,7 @@
"1": 100
},
"flags": {},
"order": 6,
"order": 9,
"mode": 0,
"inputs": [
{
@@ -419,48 +332,6 @@
12
]
},
{
"id": 19,
"type": "LoadImage",
"pos": [
370,
600
],
"size": {
"0": 220,
"1": 320
},
"flags": {},
"order": 3,
"mode": 0,
"outputs": [
{
"name": "IMAGE",
"type": "IMAGE",
"links": [
29
],
"shape": 3,
"slot_index": 0
},
{
"name": "MASK",
"type": "MASK",
"links": [
37
],
"shape": 3,
"slot_index": 1
}
],
"properties": {
"Node name for S&R": "LoadImage"
},
"widgets_values": [
"clipspace/clipspace-mask-8127362.png [input]",
"image"
]
},
{
"id": 4,
"type": "CLIPVisionLoader",
@@ -473,7 +344,7 @@
"1": 60
},
"flags": {},
"order": 4,
"order": 2,
"mode": 0,
"outputs": [
{
@@ -505,7 +376,7 @@
"1": 100
},
"flags": {},
"order": 5,
"order": 3,
"mode": 0,
"outputs": [
{
@@ -540,6 +411,144 @@
"widgets_values": [
"sd15/absolutereality_v181INPAINTING.safetensors"
]
},
{
"id": 5,
"type": "IPAdapterApply",
"pos": [
654,
-60
],
"size": {
"0": 210,
"1": 258
},
"flags": {},
"order": 8,
"mode": 0,
"inputs": [
{
"name": "ipadapter",
"type": "IPADAPTER",
"link": 1
},
{
"name": "clip_vision",
"type": "CLIP_VISION",
"link": 2
},
{
"name": "image",
"type": "IMAGE",
"link": 28
},
{
"name": "model",
"type": "MODEL",
"link": 4
},
{
"name": "attn_mask",
"type": "MASK",
"link": null
}
],
"outputs": [
{
"name": "MODEL",
"type": "MODEL",
"links": [
7
],
"shape": 3,
"slot_index": 0
}
],
"properties": {
"Node name for S&R": "IPAdapterApply"
},
"widgets_values": [
0.8,
0,
"original",
0,
1,
false
]
},
{
"id": 3,
"type": "IPAdapterModelLoader",
"pos": [
290,
60
],
"size": {
"0": 300,
"1": 60
},
"flags": {},
"order": 4,
"mode": 0,
"outputs": [
{
"name": "IPADAPTER",
"type": "IPADAPTER",
"links": [
1
],
"shape": 3,
"slot_index": 0
}
],
"properties": {
"Node name for S&R": "IPAdapterModelLoader"
},
"widgets_values": [
"ip-adapter-plus_sd15.safetensors"
]
},
{
"id": 19,
"type": "LoadImage",
"pos": [
370,
600
],
"size": {
"0": 220,
"1": 320
},
"flags": {},
"order": 5,
"mode": 0,
"outputs": [
{
"name": "IMAGE",
"type": "IMAGE",
"links": [
29
],
"shape": 3,
"slot_index": 0
},
{
"name": "MASK",
"type": "MASK",
"links": [
37
],
"shape": 3,
"slot_index": 1
}
],
"properties": {
"Node name for S&R": "LoadImage"
},
"widgets_values": [
"clipspace/clipspace-mask-1375556.png [input]",
"image"
]
}
],
"links": [
examples/IPAdapter_mask.json
+61 -58
View File
@@ -369,40 +369,6 @@
1
]
},
{
"id": 10,
"type": "IPAdapterModelLoader",
"pos": [
490,
-80
],
"size": {
"0": 300,
"1": 60
},
"flags": {},
"order": 4,
"mode": 0,
"outputs": [
{
"name": "IPADAPTER",
"type": "IPADAPTER",
"links": [
85
],
"shape": 3,
"slot_index": 0
}
],
"properties": {
"Node name for S&R": "IPAdapterModelLoader"
},
"widgets_values": [
"ip-adapter-plus_sd15.bin"
],
"color": "#223",
"bgcolor": "#335"
},
{
"id": 12,
"type": "LoadImage",
@@ -410,12 +376,12 @@
230,
-80
],
"size": [
230,
320
],
"size": {
"0": 230,
"1": 320
},
"flags": {},
"order": 5,
"order": 4,
"mode": 0,
"outputs": [
{
@@ -447,16 +413,41 @@
"color": "#223",
"bgcolor": "#335"
},
{
"id": 8,
"type": "PreviewImage",
"pos": [
1365,
369
],
"size": {
"0": 675.9465942382812,
"1": 480.1444091796875
},
"flags": {},
"order": 12,
"mode": 0,
"inputs": [
{
"name": "images",
"type": "IMAGE",
"link": 9
}
],
"properties": {
"Node name for S&R": "PreviewImage"
}
},
{
"id": 51,
"type": "IPAdapterApply",
"pos": [
830,
40
829,
-23
],
"size": [
210,
190
258
],
"flags": {},
"order": 9,
@@ -505,35 +496,47 @@
"widgets_values": [
0.7000000000000001,
0,
"linear"
"linear",
0,
1,
false
],
"color": "#223",
"bgcolor": "#335"
},
{
"id": 8,
"type": "PreviewImage",
"id": 10,
"type": "IPAdapterModelLoader",
"pos": [
1365,
369
],
"size": [
675.9466064453127,
480.1444152832032
490,
-80
],
"size": {
"0": 300,
"1": 60
},
"flags": {},
"order": 12,
"order": 5,
"mode": 0,
"inputs": [
"outputs": [
{
"name": "images",
"type": "IMAGE",
"link": 9
"name": "IPADAPTER",
"type": "IPADAPTER",
"links": [
85
],
"shape": 3,
"slot_index": 0
}
],
"properties": {
"Node name for S&R": "PreviewImage"
}
"Node name for S&R": "IPAdapterModelLoader"
},
"widgets_values": [
"ip-adapter-plus_sd15.safetensors"
],
"color": "#223",
"bgcolor": "#335"
}
],
"links": [
examples/IPAdapter_prepped.json
+109 -100
View File
@@ -243,93 +243,6 @@
1
]
},
{
"id": 5,
"type": "IPAdapterApply",
"pos": [
650,
60
],
"size": {
"0": 210,
"1": 142
},
"flags": {},
"order": 12,
"mode": 0,
"inputs": [
{
"name": "ipadapter",
"type": "IPADAPTER",
"link": 1
},
{
"name": "clip_vision",
"type": "CLIP_VISION",
"link": 2
},
{
"name": "image",
"type": "IMAGE",
"link": 45
},
{
"name": "model",
"type": "MODEL",
"link": 4
}
],
"outputs": [
{
"name": "MODEL",
"type": "MODEL",
"links": [
7
],
"shape": 3,
"slot_index": 0
}
],
"properties": {
"Node name for S&R": "IPAdapterApply"
},
"widgets_values": [
1,
0
]
},
{
"id": 3,
"type": "IPAdapterModelLoader",
"pos": [
290,
60
],
"size": {
"0": 300,
"1": 60
},
"flags": {},
"order": 1,
"mode": 0,
"outputs": [
{
"name": "IPADAPTER",
"type": "IPADAPTER",
"links": [
1
],
"shape": 3,
"slot_index": 0
}
],
"properties": {
"Node name for S&R": "IPAdapterModelLoader"
},
"widgets_values": [
"ip-adapter_sdxl_vit-h.bin"
]
},
{
"id": 1,
"type": "CheckpointLoaderSimple",
@@ -342,7 +255,7 @@
"1": 100
},
"flags": {},
"order": 2,
"order": 1,
"mode": 0,
"outputs": [
{
@@ -390,7 +303,7 @@
"1": 110
},
"flags": {},
"order": 3,
"order": 2,
"mode": 0,
"outputs": [
{
@@ -424,7 +337,7 @@
"1": 60
},
"flags": {},
"order": 4,
"order": 3,
"mode": 0,
"outputs": [
{
@@ -456,7 +369,7 @@
"1": 320
},
"flags": {},
"order": 5,
"order": 4,
"mode": 0,
"outputs": [
{
@@ -495,7 +408,7 @@
"1": 320
},
"flags": {},
"order": 6,
"order": 5,
"mode": 0,
"outputs": [
{
@@ -570,10 +483,10 @@
350,
510
],
"size": [
240,
110
],
"size": {
"0": 243.60000610351562,
"1": 110
},
"flags": {},
"order": 9,
"mode": 0,
@@ -611,10 +524,10 @@
350,
660
],
"size": [
240,
110
],
"size": {
"0": 243.60000610351562,
"1": 110
},
"flags": {},
"order": 10,
"mode": 0,
@@ -644,6 +557,102 @@
"top",
0
]
},
{
"id": 5,
"type": "IPAdapterApply",
"pos": [
653,
-60
],
"size": {
"0": 210,
"1": 258
},
"flags": {},
"order": 12,
"mode": 0,
"inputs": [
{
"name": "ipadapter",
"type": "IPADAPTER",
"link": 1
},
{
"name": "clip_vision",
"type": "CLIP_VISION",
"link": 2
},
{
"name": "image",
"type": "IMAGE",
"link": 45
},
{
"name": "model",
"type": "MODEL",
"link": 4
},
{
"name": "attn_mask",
"type": "MASK",
"link": null
}
],
"outputs": [
{
"name": "MODEL",
"type": "MODEL",
"links": [
7
],
"shape": 3,
"slot_index": 0
}
],
"properties": {
"Node name for S&R": "IPAdapterApply"
},
"widgets_values": [
1,
0,
"original",
0,
1,
false
]
},
{
"id": 3,
"type": "IPAdapterModelLoader",
"pos": [
290,
60
],
"size": {
"0": 300,
"1": 60
},
"flags": {},
"order": 6,
"mode": 0,
"outputs": [
{
"name": "IPADAPTER",
"type": "IPADAPTER",
"links": [
1
],
"shape": 3,
"slot_index": 0
}
],
"properties": {
"Node name for S&R": "IPAdapterModelLoader"
},
"widgets_values": [
"ip-adapter_sdxl_vit-h.safetensors"
]
}
],
"links": [
examples/IPAdapter_weighted.json
+95 -86
View File
@@ -343,87 +343,6 @@
"image"
]
},
{
"id": 3,
"type": "IPAdapterModelLoader",
"pos": [
450,
-210
],
"size": [
260,
60
],
"flags": {},
"order": 5,
"mode": 0,
"outputs": [
{
"name": "IPADAPTER",
"type": "IPADAPTER",
"links": [
17
],
"shape": 3,
"slot_index": 0
}
],
"properties": {
"Node name for S&R": "IPAdapterModelLoader"
},
"widgets_values": [
"ip-adapter_sd15.bin"
]
},
{
"id": 13,
"type": "IPAdapterApplyEncoded",
"pos": [
790,
30
],
"size": [
240,
100
],
"flags": {},
"order": 10,
"mode": 0,
"inputs": [
{
"name": "ipadapter",
"type": "IPADAPTER",
"link": 17
},
{
"name": "embeds",
"type": "EMBEDS",
"link": 18
},
{
"name": "model",
"type": "MODEL",
"link": 19
}
],
"outputs": [
{
"name": "MODEL",
"type": "MODEL",
"links": [
22
],
"shape": 3,
"slot_index": 0
}
],
"properties": {
"Node name for S&R": "IPAdapterApplyEncoded"
},
"widgets_values": [
1
]
},
{
"id": 2,
"type": "VAELoader",
@@ -436,7 +355,7 @@
"1": 60
},
"flags": {},
"order": 6,
"order": 5,
"mode": 0,
"outputs": [
{
@@ -463,10 +382,10 @@
500,
-100
],
"size": [
210,
260
],
"size": {
"0": 210,
"1": 260
},
"flags": {},
"order": 9,
"mode": 0,
@@ -579,6 +498,96 @@
"ddim_uniform",
1
]
},
{
"id": 3,
"type": "IPAdapterModelLoader",
"pos": [
450,
-210
],
"size": {
"0": 260,
"1": 60
},
"flags": {},
"order": 6,
"mode": 0,
"outputs": [
{
"name": "IPADAPTER",
"type": "IPADAPTER",
"links": [
17
],
"shape": 3,
"slot_index": 0
}
],
"properties": {
"Node name for S&R": "IPAdapterModelLoader"
},
"widgets_values": [
"ip-adapter_sd15.safetensors"
]
},
{
"id": 13,
"type": "IPAdapterApplyEncoded",
"pos": [
804,
-87
],
"size": [
235.1999969482422,
214
],
"flags": {},
"order": 10,
"mode": 0,
"inputs": [
{
"name": "ipadapter",
"type": "IPADAPTER",
"link": 17
},
{
"name": "embeds",
"type": "EMBEDS",
"link": 18
},
{
"name": "model",
"type": "MODEL",
"link": 19
},
{
"name": "attn_mask",
"type": "MASK",
"link": null
}
],
"outputs": [
{
"name": "MODEL",
"type": "MODEL",
"links": [
22
],
"shape": 3,
"slot_index": 0
}
],
"properties": {
"Node name for S&R": "IPAdapterApplyEncoded"
},
"widgets_values": [
1,
"original",
0,
1,
false
]
}
],
"links": [
models/put_ipadapter_models_here.txt → models/legacy_models_location.txt
View File