mirror of
https://git.datalinker.icu/comfyanonymous/ComfyUI
synced 2026-11-23 02:57:00 +08:00
Merge branch 'master' of https://github.com/RobeSantoro/ComfyUI-robe
This commit is contained in:
commit
536c6c8d45
@ -142,7 +142,7 @@ You can install ComfyUI in Apple Mac silicon (M1 or M2) with any recent macOS ve
|
|||||||
1. Install pytorch nightly. For instructions, read the [Accelerated PyTorch training on Mac](https://developer.apple.com/metal/pytorch/) Apple Developer guide (make sure to install the latest pytorch nightly).
|
1. Install pytorch nightly. For instructions, read the [Accelerated PyTorch training on Mac](https://developer.apple.com/metal/pytorch/) Apple Developer guide (make sure to install the latest pytorch nightly).
|
||||||
1. Follow the [ComfyUI manual installation](#manual-install-windows-linux) instructions for Windows and Linux.
|
1. Follow the [ComfyUI manual installation](#manual-install-windows-linux) instructions for Windows and Linux.
|
||||||
1. Install the ComfyUI [dependencies](#dependencies). If you have another Stable Diffusion UI [you might be able to reuse the dependencies](#i-already-have-another-ui-for-stable-diffusion-installed-do-i-really-have-to-install-all-of-these-dependencies).
|
1. Install the ComfyUI [dependencies](#dependencies). If you have another Stable Diffusion UI [you might be able to reuse the dependencies](#i-already-have-another-ui-for-stable-diffusion-installed-do-i-really-have-to-install-all-of-these-dependencies).
|
||||||
1. Launch ComfyUI by running `python main.py --force-fp16`. Note that --force-fp16 will only work if you installed the latest pytorch nightly.
|
1. Launch ComfyUI by running `python main.py`
|
||||||
|
|
||||||
> **Note**: Remember to add your models, VAE, LoRAs etc. to the corresponding Comfy folders, as discussed in [ComfyUI manual installation](#manual-install-windows-linux).
|
> **Note**: Remember to add your models, VAE, LoRAs etc. to the corresponding Comfy folders, as discussed in [ComfyUI manual installation](#manual-install-windows-linux).
|
||||||
|
|
||||||
|
|||||||
@ -21,6 +21,12 @@ def load_lora(lora, to_load):
|
|||||||
alpha = lora[alpha_name].item()
|
alpha = lora[alpha_name].item()
|
||||||
loaded_keys.add(alpha_name)
|
loaded_keys.add(alpha_name)
|
||||||
|
|
||||||
|
dora_scale_name = "{}.dora_scale".format(x)
|
||||||
|
dora_scale = None
|
||||||
|
if dora_scale_name in lora.keys():
|
||||||
|
dora_scale = lora[dora_scale_name]
|
||||||
|
loaded_keys.add(dora_scale_name)
|
||||||
|
|
||||||
regular_lora = "{}.lora_up.weight".format(x)
|
regular_lora = "{}.lora_up.weight".format(x)
|
||||||
diffusers_lora = "{}_lora.up.weight".format(x)
|
diffusers_lora = "{}_lora.up.weight".format(x)
|
||||||
transformers_lora = "{}.lora_linear_layer.up.weight".format(x)
|
transformers_lora = "{}.lora_linear_layer.up.weight".format(x)
|
||||||
@ -44,7 +50,7 @@ def load_lora(lora, to_load):
|
|||||||
if mid_name is not None and mid_name in lora.keys():
|
if mid_name is not None and mid_name in lora.keys():
|
||||||
mid = lora[mid_name]
|
mid = lora[mid_name]
|
||||||
loaded_keys.add(mid_name)
|
loaded_keys.add(mid_name)
|
||||||
patch_dict[to_load[x]] = ("lora", (lora[A_name], lora[B_name], alpha, mid))
|
patch_dict[to_load[x]] = ("lora", (lora[A_name], lora[B_name], alpha, mid, dora_scale))
|
||||||
loaded_keys.add(A_name)
|
loaded_keys.add(A_name)
|
||||||
loaded_keys.add(B_name)
|
loaded_keys.add(B_name)
|
||||||
|
|
||||||
@ -65,7 +71,7 @@ def load_lora(lora, to_load):
|
|||||||
loaded_keys.add(hada_t1_name)
|
loaded_keys.add(hada_t1_name)
|
||||||
loaded_keys.add(hada_t2_name)
|
loaded_keys.add(hada_t2_name)
|
||||||
|
|
||||||
patch_dict[to_load[x]] = ("loha", (lora[hada_w1_a_name], lora[hada_w1_b_name], alpha, lora[hada_w2_a_name], lora[hada_w2_b_name], hada_t1, hada_t2))
|
patch_dict[to_load[x]] = ("loha", (lora[hada_w1_a_name], lora[hada_w1_b_name], alpha, lora[hada_w2_a_name], lora[hada_w2_b_name], hada_t1, hada_t2, dora_scale))
|
||||||
loaded_keys.add(hada_w1_a_name)
|
loaded_keys.add(hada_w1_a_name)
|
||||||
loaded_keys.add(hada_w1_b_name)
|
loaded_keys.add(hada_w1_b_name)
|
||||||
loaded_keys.add(hada_w2_a_name)
|
loaded_keys.add(hada_w2_a_name)
|
||||||
@ -117,7 +123,7 @@ def load_lora(lora, to_load):
|
|||||||
loaded_keys.add(lokr_t2_name)
|
loaded_keys.add(lokr_t2_name)
|
||||||
|
|
||||||
if (lokr_w1 is not None) or (lokr_w2 is not None) or (lokr_w1_a is not None) or (lokr_w2_a is not None):
|
if (lokr_w1 is not None) or (lokr_w2 is not None) or (lokr_w1_a is not None) or (lokr_w2_a is not None):
|
||||||
patch_dict[to_load[x]] = ("lokr", (lokr_w1, lokr_w2, alpha, lokr_w1_a, lokr_w1_b, lokr_w2_a, lokr_w2_b, lokr_t2))
|
patch_dict[to_load[x]] = ("lokr", (lokr_w1, lokr_w2, alpha, lokr_w1_a, lokr_w1_b, lokr_w2_a, lokr_w2_b, lokr_t2, dora_scale))
|
||||||
|
|
||||||
#glora
|
#glora
|
||||||
a1_name = "{}.a1.weight".format(x)
|
a1_name = "{}.a1.weight".format(x)
|
||||||
@ -125,7 +131,7 @@ def load_lora(lora, to_load):
|
|||||||
b1_name = "{}.b1.weight".format(x)
|
b1_name = "{}.b1.weight".format(x)
|
||||||
b2_name = "{}.b2.weight".format(x)
|
b2_name = "{}.b2.weight".format(x)
|
||||||
if a1_name in lora:
|
if a1_name in lora:
|
||||||
patch_dict[to_load[x]] = ("glora", (lora[a1_name], lora[a2_name], lora[b1_name], lora[b2_name], alpha))
|
patch_dict[to_load[x]] = ("glora", (lora[a1_name], lora[a2_name], lora[b1_name], lora[b2_name], alpha, dora_scale))
|
||||||
loaded_keys.add(a1_name)
|
loaded_keys.add(a1_name)
|
||||||
loaded_keys.add(a2_name)
|
loaded_keys.add(a2_name)
|
||||||
loaded_keys.add(b1_name)
|
loaded_keys.add(b1_name)
|
||||||
|
|||||||
@ -66,7 +66,8 @@ class BaseModel(torch.nn.Module):
|
|||||||
self.adm_channels = unet_config.get("adm_in_channels", None)
|
self.adm_channels = unet_config.get("adm_in_channels", None)
|
||||||
if self.adm_channels is None:
|
if self.adm_channels is None:
|
||||||
self.adm_channels = 0
|
self.adm_channels = 0
|
||||||
self.inpaint_model = False
|
|
||||||
|
self.concat_keys = ()
|
||||||
logging.info("model_type {}".format(model_type.name))
|
logging.info("model_type {}".format(model_type.name))
|
||||||
logging.debug("adm {}".format(self.adm_channels))
|
logging.debug("adm {}".format(self.adm_channels))
|
||||||
|
|
||||||
@ -107,8 +108,7 @@ class BaseModel(torch.nn.Module):
|
|||||||
|
|
||||||
def extra_conds(self, **kwargs):
|
def extra_conds(self, **kwargs):
|
||||||
out = {}
|
out = {}
|
||||||
if self.inpaint_model:
|
if len(self.concat_keys) > 0:
|
||||||
concat_keys = ("mask", "masked_image")
|
|
||||||
cond_concat = []
|
cond_concat = []
|
||||||
denoise_mask = kwargs.get("concat_mask", kwargs.get("denoise_mask", None))
|
denoise_mask = kwargs.get("concat_mask", kwargs.get("denoise_mask", None))
|
||||||
concat_latent_image = kwargs.get("concat_latent_image", None)
|
concat_latent_image = kwargs.get("concat_latent_image", None)
|
||||||
@ -125,24 +125,16 @@ class BaseModel(torch.nn.Module):
|
|||||||
|
|
||||||
concat_latent_image = utils.resize_to_batch_size(concat_latent_image, noise.shape[0])
|
concat_latent_image = utils.resize_to_batch_size(concat_latent_image, noise.shape[0])
|
||||||
|
|
||||||
if len(denoise_mask.shape) == len(noise.shape):
|
if denoise_mask is not None:
|
||||||
denoise_mask = denoise_mask[:,:1]
|
if len(denoise_mask.shape) == len(noise.shape):
|
||||||
|
denoise_mask = denoise_mask[:,:1]
|
||||||
|
|
||||||
denoise_mask = denoise_mask.reshape((-1, 1, denoise_mask.shape[-2], denoise_mask.shape[-1]))
|
denoise_mask = denoise_mask.reshape((-1, 1, denoise_mask.shape[-2], denoise_mask.shape[-1]))
|
||||||
if denoise_mask.shape[-2:] != noise.shape[-2:]:
|
if denoise_mask.shape[-2:] != noise.shape[-2:]:
|
||||||
denoise_mask = utils.common_upscale(denoise_mask, noise.shape[-1], noise.shape[-2], "bilinear", "center")
|
denoise_mask = utils.common_upscale(denoise_mask, noise.shape[-1], noise.shape[-2], "bilinear", "center")
|
||||||
denoise_mask = utils.resize_to_batch_size(denoise_mask.round(), noise.shape[0])
|
denoise_mask = utils.resize_to_batch_size(denoise_mask.round(), noise.shape[0])
|
||||||
|
|
||||||
def blank_inpaint_image_like(latent_image):
|
for ck in self.concat_keys:
|
||||||
blank_image = torch.ones_like(latent_image)
|
|
||||||
# these are the values for "zero" in pixel space translated to latent space
|
|
||||||
blank_image[:,0] *= 0.8223
|
|
||||||
blank_image[:,1] *= -0.6876
|
|
||||||
blank_image[:,2] *= 0.6364
|
|
||||||
blank_image[:,3] *= 0.1380
|
|
||||||
return blank_image
|
|
||||||
|
|
||||||
for ck in concat_keys:
|
|
||||||
if denoise_mask is not None:
|
if denoise_mask is not None:
|
||||||
if ck == "mask":
|
if ck == "mask":
|
||||||
cond_concat.append(denoise_mask.to(device))
|
cond_concat.append(denoise_mask.to(device))
|
||||||
@ -152,7 +144,7 @@ class BaseModel(torch.nn.Module):
|
|||||||
if ck == "mask":
|
if ck == "mask":
|
||||||
cond_concat.append(torch.ones_like(noise)[:,:1])
|
cond_concat.append(torch.ones_like(noise)[:,:1])
|
||||||
elif ck == "masked_image":
|
elif ck == "masked_image":
|
||||||
cond_concat.append(blank_inpaint_image_like(noise))
|
cond_concat.append(self.blank_inpaint_image_like(noise))
|
||||||
data = torch.cat(cond_concat, dim=1)
|
data = torch.cat(cond_concat, dim=1)
|
||||||
out['c_concat'] = comfy.conds.CONDNoiseShape(data)
|
out['c_concat'] = comfy.conds.CONDNoiseShape(data)
|
||||||
|
|
||||||
@ -221,7 +213,16 @@ class BaseModel(torch.nn.Module):
|
|||||||
return unet_state_dict
|
return unet_state_dict
|
||||||
|
|
||||||
def set_inpaint(self):
|
def set_inpaint(self):
|
||||||
self.inpaint_model = True
|
self.concat_keys = ("mask", "masked_image")
|
||||||
|
def blank_inpaint_image_like(latent_image):
|
||||||
|
blank_image = torch.ones_like(latent_image)
|
||||||
|
# these are the values for "zero" in pixel space translated to latent space
|
||||||
|
blank_image[:,0] *= 0.8223
|
||||||
|
blank_image[:,1] *= -0.6876
|
||||||
|
blank_image[:,2] *= 0.6364
|
||||||
|
blank_image[:,3] *= 0.1380
|
||||||
|
return blank_image
|
||||||
|
self.blank_inpaint_image_like = blank_inpaint_image_like
|
||||||
|
|
||||||
def memory_required(self, input_shape):
|
def memory_required(self, input_shape):
|
||||||
if comfy.model_management.xformers_enabled() or comfy.model_management.pytorch_attention_flash_attention():
|
if comfy.model_management.xformers_enabled() or comfy.model_management.pytorch_attention_flash_attention():
|
||||||
@ -472,6 +473,40 @@ class SD_X4Upscaler(BaseModel):
|
|||||||
out['y'] = comfy.conds.CONDRegular(noise_level)
|
out['y'] = comfy.conds.CONDRegular(noise_level)
|
||||||
return out
|
return out
|
||||||
|
|
||||||
|
class IP2P:
|
||||||
|
def extra_conds(self, **kwargs):
|
||||||
|
out = {}
|
||||||
|
|
||||||
|
image = kwargs.get("concat_latent_image", None)
|
||||||
|
noise = kwargs.get("noise", None)
|
||||||
|
device = kwargs["device"]
|
||||||
|
|
||||||
|
if image is None:
|
||||||
|
image = torch.zeros_like(noise)
|
||||||
|
|
||||||
|
if image.shape[1:] != noise.shape[1:]:
|
||||||
|
image = utils.common_upscale(image.to(device), noise.shape[-1], noise.shape[-2], "bilinear", "center")
|
||||||
|
|
||||||
|
image = utils.resize_to_batch_size(image, noise.shape[0])
|
||||||
|
|
||||||
|
out['c_concat'] = comfy.conds.CONDNoiseShape(self.process_ip2p_image_in(image))
|
||||||
|
adm = self.encode_adm(**kwargs)
|
||||||
|
if adm is not None:
|
||||||
|
out['y'] = comfy.conds.CONDRegular(adm)
|
||||||
|
return out
|
||||||
|
|
||||||
|
class SD15_instructpix2pix(IP2P, BaseModel):
|
||||||
|
def __init__(self, model_config, model_type=ModelType.EPS, device=None):
|
||||||
|
super().__init__(model_config, model_type, device=device)
|
||||||
|
self.process_ip2p_image_in = lambda image: image
|
||||||
|
|
||||||
|
class SDXL_instructpix2pix(IP2P, SDXL):
|
||||||
|
def __init__(self, model_config, model_type=ModelType.EPS, device=None):
|
||||||
|
super().__init__(model_config, model_type, device=device)
|
||||||
|
# self.process_ip2p_image_in = lambda image: comfy.latent_formats.SDXL().process_in(image)
|
||||||
|
self.process_ip2p_image_in = lambda image: image
|
||||||
|
|
||||||
|
|
||||||
class StableCascade_C(BaseModel):
|
class StableCascade_C(BaseModel):
|
||||||
def __init__(self, model_config, model_type=ModelType.STABLE_CASCADE, device=None):
|
def __init__(self, model_config, model_type=ModelType.STABLE_CASCADE, device=None):
|
||||||
super().__init__(model_config, model_type, device=device, unet_model=StageC)
|
super().__init__(model_config, model_type, device=device, unet_model=StageC)
|
||||||
|
|||||||
@ -182,9 +182,9 @@ def detect_unet_config(state_dict, key_prefix):
|
|||||||
|
|
||||||
return unet_config
|
return unet_config
|
||||||
|
|
||||||
def model_config_from_unet_config(unet_config):
|
def model_config_from_unet_config(unet_config, state_dict=None):
|
||||||
for model_config in comfy.supported_models.models:
|
for model_config in comfy.supported_models.models:
|
||||||
if model_config.matches(unet_config):
|
if model_config.matches(unet_config, state_dict):
|
||||||
return model_config(unet_config)
|
return model_config(unet_config)
|
||||||
|
|
||||||
logging.error("no match {}".format(unet_config))
|
logging.error("no match {}".format(unet_config))
|
||||||
@ -192,7 +192,7 @@ def model_config_from_unet_config(unet_config):
|
|||||||
|
|
||||||
def model_config_from_unet(state_dict, unet_key_prefix, use_base_if_no_match=False):
|
def model_config_from_unet(state_dict, unet_key_prefix, use_base_if_no_match=False):
|
||||||
unet_config = detect_unet_config(state_dict, unet_key_prefix)
|
unet_config = detect_unet_config(state_dict, unet_key_prefix)
|
||||||
model_config = model_config_from_unet_config(unet_config)
|
model_config = model_config_from_unet_config(unet_config, state_dict)
|
||||||
if model_config is None and use_base_if_no_match:
|
if model_config is None and use_base_if_no_match:
|
||||||
return comfy.supported_models_base.BASE(unet_config)
|
return comfy.supported_models_base.BASE(unet_config)
|
||||||
else:
|
else:
|
||||||
@ -321,6 +321,12 @@ def unet_config_from_diffusers_unet(state_dict, dtype=None):
|
|||||||
'use_linear_in_transformer': True, 'context_dim': 2048, 'num_head_channels': 64, 'transformer_depth_output': [0, 0, 0, 2, 2, 2, 10, 10, 10],
|
'use_linear_in_transformer': True, 'context_dim': 2048, 'num_head_channels': 64, 'transformer_depth_output': [0, 0, 0, 2, 2, 2, 10, 10, 10],
|
||||||
'use_temporal_attention': False, 'use_temporal_resblock': False}
|
'use_temporal_attention': False, 'use_temporal_resblock': False}
|
||||||
|
|
||||||
|
SDXL_diffusers_ip2p = {'use_checkpoint': False, 'image_size': 32, 'out_channels': 4, 'use_spatial_transformer': True, 'legacy': False,
|
||||||
|
'num_classes': 'sequential', 'adm_in_channels': 2816, 'dtype': dtype, 'in_channels': 8, 'model_channels': 320,
|
||||||
|
'num_res_blocks': [2, 2, 2], 'transformer_depth': [0, 0, 2, 2, 10, 10], 'channel_mult': [1, 2, 4], 'transformer_depth_middle': 10,
|
||||||
|
'use_linear_in_transformer': True, 'context_dim': 2048, 'num_head_channels': 64, 'transformer_depth_output': [0, 0, 0, 2, 2, 2, 10, 10, 10],
|
||||||
|
'use_temporal_attention': False, 'use_temporal_resblock': False}
|
||||||
|
|
||||||
SSD_1B = {'use_checkpoint': False, 'image_size': 32, 'out_channels': 4, 'use_spatial_transformer': True, 'legacy': False,
|
SSD_1B = {'use_checkpoint': False, 'image_size': 32, 'out_channels': 4, 'use_spatial_transformer': True, 'legacy': False,
|
||||||
'num_classes': 'sequential', 'adm_in_channels': 2816, 'dtype': dtype, 'in_channels': 4, 'model_channels': 320,
|
'num_classes': 'sequential', 'adm_in_channels': 2816, 'dtype': dtype, 'in_channels': 4, 'model_channels': 320,
|
||||||
'num_res_blocks': [2, 2, 2], 'transformer_depth': [0, 0, 2, 2, 4, 4], 'transformer_depth_output': [0, 0, 0, 1, 1, 2, 10, 4, 4],
|
'num_res_blocks': [2, 2, 2], 'transformer_depth': [0, 0, 2, 2, 4, 4], 'transformer_depth_output': [0, 0, 0, 1, 1, 2, 10, 4, 4],
|
||||||
@ -345,7 +351,13 @@ def unet_config_from_diffusers_unet(state_dict, dtype=None):
|
|||||||
'channel_mult': [1, 2, 4], 'transformer_depth_middle': 6, 'use_linear_in_transformer': True, 'context_dim': 2048, 'num_head_channels': 64,
|
'channel_mult': [1, 2, 4], 'transformer_depth_middle': 6, 'use_linear_in_transformer': True, 'context_dim': 2048, 'num_head_channels': 64,
|
||||||
'use_temporal_attention': False, 'use_temporal_resblock': False}
|
'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 = {'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': [1, 1, 1], 'channel_mult': [1, 2, 4], 'transformer_depth_middle': -2, 'use_linear_in_transformer': True,
|
||||||
|
'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]}
|
||||||
|
|
||||||
|
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]
|
||||||
|
|
||||||
for unet_config in supported_models:
|
for unet_config in supported_models:
|
||||||
matches = True
|
matches = True
|
||||||
|
|||||||
@ -274,6 +274,7 @@ class LoadedModel:
|
|||||||
self.model = model
|
self.model = model
|
||||||
self.device = model.load_device
|
self.device = model.load_device
|
||||||
self.weights_loaded = False
|
self.weights_loaded = False
|
||||||
|
self.real_model = None
|
||||||
|
|
||||||
def model_memory(self):
|
def model_memory(self):
|
||||||
return self.model.model_size()
|
return self.model.model_size()
|
||||||
@ -312,6 +313,7 @@ class LoadedModel:
|
|||||||
self.model.unpatch_model(self.model.offload_device, unpatch_weights=unpatch_weights)
|
self.model.unpatch_model(self.model.offload_device, unpatch_weights=unpatch_weights)
|
||||||
self.model.model_patches_to(self.model.offload_device)
|
self.model.model_patches_to(self.model.offload_device)
|
||||||
self.weights_loaded = self.weights_loaded and not unpatch_weights
|
self.weights_loaded = self.weights_loaded and not unpatch_weights
|
||||||
|
self.real_model = None
|
||||||
|
|
||||||
def __eq__(self, other):
|
def __eq__(self, other):
|
||||||
return self.model is other.model
|
return self.model is other.model
|
||||||
@ -326,7 +328,7 @@ def unload_model_clones(model, unload_weights_only=True, force_unload=True):
|
|||||||
to_unload = [i] + to_unload
|
to_unload = [i] + to_unload
|
||||||
|
|
||||||
if len(to_unload) == 0:
|
if len(to_unload) == 0:
|
||||||
return None
|
return True
|
||||||
|
|
||||||
same_weights = 0
|
same_weights = 0
|
||||||
for i in to_unload:
|
for i in to_unload:
|
||||||
@ -408,8 +410,8 @@ def load_models_gpu(models, memory_required=0):
|
|||||||
|
|
||||||
total_memory_required = {}
|
total_memory_required = {}
|
||||||
for loaded_model in models_to_load:
|
for loaded_model in models_to_load:
|
||||||
unload_model_clones(loaded_model.model, unload_weights_only=True, force_unload=False) #unload clones where the weights are different
|
if unload_model_clones(loaded_model.model, unload_weights_only=True, force_unload=False) == True:#unload clones where the weights are different
|
||||||
total_memory_required[loaded_model.device] = total_memory_required.get(loaded_model.device, 0) + loaded_model.model_memory_required(loaded_model.device)
|
total_memory_required[loaded_model.device] = total_memory_required.get(loaded_model.device, 0) + loaded_model.model_memory_required(loaded_model.device)
|
||||||
|
|
||||||
for device in total_memory_required:
|
for device in total_memory_required:
|
||||||
if device != torch.device("cpu"):
|
if device != torch.device("cpu"):
|
||||||
@ -448,11 +450,15 @@ def load_models_gpu(models, memory_required=0):
|
|||||||
def load_model_gpu(model):
|
def load_model_gpu(model):
|
||||||
return load_models_gpu([model])
|
return load_models_gpu([model])
|
||||||
|
|
||||||
def cleanup_models():
|
def cleanup_models(keep_clone_weights_loaded=False):
|
||||||
to_delete = []
|
to_delete = []
|
||||||
for i in range(len(current_loaded_models)):
|
for i in range(len(current_loaded_models)):
|
||||||
if sys.getrefcount(current_loaded_models[i].model) <= 2:
|
if sys.getrefcount(current_loaded_models[i].model) <= 2:
|
||||||
to_delete = [i] + to_delete
|
if not keep_clone_weights_loaded:
|
||||||
|
to_delete = [i] + to_delete
|
||||||
|
#TODO: find a less fragile way to do this.
|
||||||
|
elif sys.getrefcount(current_loaded_models[i].real_model) <= 3: #references from .real_model + the .model
|
||||||
|
to_delete = [i] + to_delete
|
||||||
|
|
||||||
for i in to_delete:
|
for i in to_delete:
|
||||||
x = current_loaded_models.pop(i)
|
x = current_loaded_models.pop(i)
|
||||||
|
|||||||
@ -7,6 +7,18 @@ import uuid
|
|||||||
import comfy.utils
|
import comfy.utils
|
||||||
import comfy.model_management
|
import comfy.model_management
|
||||||
|
|
||||||
|
def apply_weight_decompose(dora_scale, weight):
|
||||||
|
weight_norm = (
|
||||||
|
weight.transpose(0, 1)
|
||||||
|
.reshape(weight.shape[1], -1)
|
||||||
|
.norm(dim=1, keepdim=True)
|
||||||
|
.reshape(weight.shape[1], *[1] * (weight.dim() - 1))
|
||||||
|
.transpose(0, 1)
|
||||||
|
)
|
||||||
|
|
||||||
|
return weight * (dora_scale / weight_norm)
|
||||||
|
|
||||||
|
|
||||||
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):
|
||||||
self.size = size
|
self.size = size
|
||||||
@ -309,6 +321,7 @@ class ModelPatcher:
|
|||||||
elif patch_type == "lora": #lora/locon
|
elif patch_type == "lora": #lora/locon
|
||||||
mat1 = comfy.model_management.cast_to_device(v[0], weight.device, torch.float32)
|
mat1 = comfy.model_management.cast_to_device(v[0], weight.device, torch.float32)
|
||||||
mat2 = comfy.model_management.cast_to_device(v[1], weight.device, torch.float32)
|
mat2 = comfy.model_management.cast_to_device(v[1], weight.device, torch.float32)
|
||||||
|
dora_scale = v[4]
|
||||||
if v[2] is not None:
|
if v[2] is not None:
|
||||||
alpha *= v[2] / mat2.shape[0]
|
alpha *= v[2] / mat2.shape[0]
|
||||||
if v[3] is not None:
|
if v[3] is not None:
|
||||||
@ -318,6 +331,8 @@ class ModelPatcher:
|
|||||||
mat2 = torch.mm(mat2.transpose(0, 1).flatten(start_dim=1), mat3.transpose(0, 1).flatten(start_dim=1)).reshape(final_shape).transpose(0, 1)
|
mat2 = torch.mm(mat2.transpose(0, 1).flatten(start_dim=1), mat3.transpose(0, 1).flatten(start_dim=1)).reshape(final_shape).transpose(0, 1)
|
||||||
try:
|
try:
|
||||||
weight += (alpha * torch.mm(mat1.flatten(start_dim=1), mat2.flatten(start_dim=1))).reshape(weight.shape).type(weight.dtype)
|
weight += (alpha * torch.mm(mat1.flatten(start_dim=1), mat2.flatten(start_dim=1))).reshape(weight.shape).type(weight.dtype)
|
||||||
|
if dora_scale is not None:
|
||||||
|
weight = apply_weight_decompose(comfy.model_management.cast_to_device(dora_scale, weight.device, torch.float32), weight)
|
||||||
except Exception as e:
|
except Exception as e:
|
||||||
logging.error("ERROR {} {} {}".format(patch_type, key, e))
|
logging.error("ERROR {} {} {}".format(patch_type, key, e))
|
||||||
elif patch_type == "lokr":
|
elif patch_type == "lokr":
|
||||||
@ -328,6 +343,7 @@ class ModelPatcher:
|
|||||||
w2_a = v[5]
|
w2_a = v[5]
|
||||||
w2_b = v[6]
|
w2_b = v[6]
|
||||||
t2 = v[7]
|
t2 = v[7]
|
||||||
|
dora_scale = v[8]
|
||||||
dim = None
|
dim = None
|
||||||
|
|
||||||
if w1 is None:
|
if w1 is None:
|
||||||
@ -357,6 +373,8 @@ class ModelPatcher:
|
|||||||
|
|
||||||
try:
|
try:
|
||||||
weight += alpha * torch.kron(w1, w2).reshape(weight.shape).type(weight.dtype)
|
weight += alpha * torch.kron(w1, w2).reshape(weight.shape).type(weight.dtype)
|
||||||
|
if dora_scale is not None:
|
||||||
|
weight = apply_weight_decompose(comfy.model_management.cast_to_device(dora_scale, weight.device, torch.float32), weight)
|
||||||
except Exception as e:
|
except Exception as e:
|
||||||
logging.error("ERROR {} {} {}".format(patch_type, key, e))
|
logging.error("ERROR {} {} {}".format(patch_type, key, e))
|
||||||
elif patch_type == "loha":
|
elif patch_type == "loha":
|
||||||
@ -366,6 +384,7 @@ class ModelPatcher:
|
|||||||
alpha *= v[2] / w1b.shape[0]
|
alpha *= v[2] / w1b.shape[0]
|
||||||
w2a = v[3]
|
w2a = v[3]
|
||||||
w2b = v[4]
|
w2b = v[4]
|
||||||
|
dora_scale = v[7]
|
||||||
if v[5] is not None: #cp decomposition
|
if v[5] is not None: #cp decomposition
|
||||||
t1 = v[5]
|
t1 = v[5]
|
||||||
t2 = v[6]
|
t2 = v[6]
|
||||||
@ -386,12 +405,16 @@ class ModelPatcher:
|
|||||||
|
|
||||||
try:
|
try:
|
||||||
weight += (alpha * m1 * m2).reshape(weight.shape).type(weight.dtype)
|
weight += (alpha * m1 * m2).reshape(weight.shape).type(weight.dtype)
|
||||||
|
if dora_scale is not None:
|
||||||
|
weight = apply_weight_decompose(comfy.model_management.cast_to_device(dora_scale, weight.device, torch.float32), weight)
|
||||||
except Exception as e:
|
except Exception as e:
|
||||||
logging.error("ERROR {} {} {}".format(patch_type, key, e))
|
logging.error("ERROR {} {} {}".format(patch_type, key, e))
|
||||||
elif patch_type == "glora":
|
elif patch_type == "glora":
|
||||||
if v[4] is not None:
|
if v[4] is not None:
|
||||||
alpha *= v[4] / v[0].shape[0]
|
alpha *= v[4] / v[0].shape[0]
|
||||||
|
|
||||||
|
dora_scale = v[5]
|
||||||
|
|
||||||
a1 = comfy.model_management.cast_to_device(v[0].flatten(start_dim=1), weight.device, torch.float32)
|
a1 = comfy.model_management.cast_to_device(v[0].flatten(start_dim=1), weight.device, torch.float32)
|
||||||
a2 = comfy.model_management.cast_to_device(v[1].flatten(start_dim=1), weight.device, torch.float32)
|
a2 = comfy.model_management.cast_to_device(v[1].flatten(start_dim=1), weight.device, torch.float32)
|
||||||
b1 = comfy.model_management.cast_to_device(v[2].flatten(start_dim=1), weight.device, torch.float32)
|
b1 = comfy.model_management.cast_to_device(v[2].flatten(start_dim=1), weight.device, torch.float32)
|
||||||
@ -399,6 +422,8 @@ class ModelPatcher:
|
|||||||
|
|
||||||
try:
|
try:
|
||||||
weight += ((torch.mm(b2, b1) + torch.mm(torch.mm(weight.flatten(start_dim=1), a2), a1)) * alpha).reshape(weight.shape).type(weight.dtype)
|
weight += ((torch.mm(b2, b1) + torch.mm(torch.mm(weight.flatten(start_dim=1), a2), a1)) * alpha).reshape(weight.shape).type(weight.dtype)
|
||||||
|
if dora_scale is not None:
|
||||||
|
weight = apply_weight_decompose(comfy.model_management.cast_to_device(dora_scale, weight.device, torch.float32), weight)
|
||||||
except Exception as e:
|
except Exception as e:
|
||||||
logging.error("ERROR {} {} {}".format(patch_type, key, e))
|
logging.error("ERROR {} {} {}".format(patch_type, key, e))
|
||||||
else:
|
else:
|
||||||
|
|||||||
@ -127,30 +127,23 @@ def cond_cat(c_list):
|
|||||||
|
|
||||||
return out
|
return out
|
||||||
|
|
||||||
def calc_cond_uncond_batch(model, cond, uncond, x_in, timestep, model_options):
|
def calc_cond_batch(model, conds, x_in, timestep, model_options):
|
||||||
out_cond = torch.zeros_like(x_in)
|
out_conds = []
|
||||||
out_count = torch.ones_like(x_in) * 1e-37
|
out_counts = []
|
||||||
|
|
||||||
out_uncond = torch.zeros_like(x_in)
|
|
||||||
out_uncond_count = torch.ones_like(x_in) * 1e-37
|
|
||||||
|
|
||||||
COND = 0
|
|
||||||
UNCOND = 1
|
|
||||||
|
|
||||||
to_run = []
|
to_run = []
|
||||||
for x in cond:
|
|
||||||
p = get_area_and_mult(x, x_in, timestep)
|
|
||||||
if p is None:
|
|
||||||
continue
|
|
||||||
|
|
||||||
to_run += [(p, COND)]
|
for i in range(len(conds)):
|
||||||
if uncond is not None:
|
out_conds.append(torch.zeros_like(x_in))
|
||||||
for x in uncond:
|
out_counts.append(torch.ones_like(x_in) * 1e-37)
|
||||||
p = get_area_and_mult(x, x_in, timestep)
|
|
||||||
if p is None:
|
|
||||||
continue
|
|
||||||
|
|
||||||
to_run += [(p, UNCOND)]
|
cond = conds[i]
|
||||||
|
if cond is not None:
|
||||||
|
for x in cond:
|
||||||
|
p = get_area_and_mult(x, x_in, timestep)
|
||||||
|
if p is None:
|
||||||
|
continue
|
||||||
|
|
||||||
|
to_run += [(p, i)]
|
||||||
|
|
||||||
while len(to_run) > 0:
|
while len(to_run) > 0:
|
||||||
first = to_run[0]
|
first = to_run[0]
|
||||||
@ -222,22 +215,20 @@ def calc_cond_uncond_batch(model, cond, uncond, x_in, timestep, model_options):
|
|||||||
output = model_options['model_function_wrapper'](model.apply_model, {"input": input_x, "timestep": timestep_, "c": c, "cond_or_uncond": cond_or_uncond}).chunk(batch_chunks)
|
output = model_options['model_function_wrapper'](model.apply_model, {"input": input_x, "timestep": timestep_, "c": c, "cond_or_uncond": cond_or_uncond}).chunk(batch_chunks)
|
||||||
else:
|
else:
|
||||||
output = model.apply_model(input_x, timestep_, **c).chunk(batch_chunks)
|
output = model.apply_model(input_x, timestep_, **c).chunk(batch_chunks)
|
||||||
del input_x
|
|
||||||
|
|
||||||
for o in range(batch_chunks):
|
for o in range(batch_chunks):
|
||||||
if cond_or_uncond[o] == COND:
|
cond_index = cond_or_uncond[o]
|
||||||
out_cond[:,:,area[o][2]:area[o][0] + area[o][2],area[o][3]:area[o][1] + area[o][3]] += output[o] * mult[o]
|
out_conds[cond_index][:,:,area[o][2]:area[o][0] + area[o][2],area[o][3]:area[o][1] + area[o][3]] += output[o] * mult[o]
|
||||||
out_count[:,:,area[o][2]:area[o][0] + area[o][2],area[o][3]:area[o][1] + area[o][3]] += mult[o]
|
out_counts[cond_index][:,:,area[o][2]:area[o][0] + area[o][2],area[o][3]:area[o][1] + area[o][3]] += mult[o]
|
||||||
else:
|
|
||||||
out_uncond[:,:,area[o][2]:area[o][0] + area[o][2],area[o][3]:area[o][1] + area[o][3]] += output[o] * mult[o]
|
|
||||||
out_uncond_count[:,:,area[o][2]:area[o][0] + area[o][2],area[o][3]:area[o][1] + area[o][3]] += mult[o]
|
|
||||||
del mult
|
|
||||||
|
|
||||||
out_cond /= out_count
|
for i in range(len(out_conds)):
|
||||||
del out_count
|
out_conds[i] /= out_counts[i]
|
||||||
out_uncond /= out_uncond_count
|
|
||||||
del out_uncond_count
|
return out_conds
|
||||||
return out_cond, out_uncond
|
|
||||||
|
def calc_cond_uncond_batch(model, cond, uncond, x_in, timestep, model_options): #TODO: remove
|
||||||
|
logging.warning("WARNING: The comfy.samplers.calc_cond_uncond_batch function is deprecated please use the calc_cond_batch one instead.")
|
||||||
|
return tuple(calc_cond_batch(model, [cond, uncond], x_in, timestep, model_options))
|
||||||
|
|
||||||
#The main sampling function shared by all the samplers
|
#The main sampling function shared by all the samplers
|
||||||
#Returns denoised
|
#Returns denoised
|
||||||
@ -247,7 +238,13 @@ def sampling_function(model, x, timestep, uncond, cond, cond_scale, model_option
|
|||||||
else:
|
else:
|
||||||
uncond_ = uncond
|
uncond_ = uncond
|
||||||
|
|
||||||
cond_pred, uncond_pred = calc_cond_uncond_batch(model, cond, uncond_, x, timestep, model_options)
|
|
||||||
|
conds = [cond, uncond_]
|
||||||
|
|
||||||
|
out = calc_cond_batch(model, conds, x, timestep, model_options)
|
||||||
|
cond_pred = out[0]
|
||||||
|
uncond_pred = out[1]
|
||||||
|
|
||||||
if "sampler_cfg_function" in model_options:
|
if "sampler_cfg_function" in model_options:
|
||||||
args = {"cond": x - cond_pred, "uncond": x - uncond_pred, "cond_scale": cond_scale, "timestep": timestep, "input": x, "sigma": timestep,
|
args = {"cond": x - cond_pred, "uncond": x - uncond_pred, "cond_scale": cond_scale, "timestep": timestep, "input": x, "sigma": timestep,
|
||||||
"cond_denoised": cond_pred, "uncond_denoised": uncond_pred, "model": model, "model_options": model_options}
|
"cond_denoised": cond_pred, "uncond_denoised": uncond_pred, "model": model, "model_options": model_options}
|
||||||
|
|||||||
@ -70,8 +70,8 @@ class SD20(supported_models_base.BASE):
|
|||||||
def model_type(self, state_dict, prefix=""):
|
def model_type(self, state_dict, prefix=""):
|
||||||
if self.unet_config["in_channels"] == 4: #SD2.0 inpainting models are not v prediction
|
if self.unet_config["in_channels"] == 4: #SD2.0 inpainting models are not v prediction
|
||||||
k = "{}output_blocks.11.1.transformer_blocks.0.norm1.bias".format(prefix)
|
k = "{}output_blocks.11.1.transformer_blocks.0.norm1.bias".format(prefix)
|
||||||
out = state_dict[k]
|
out = state_dict.get(k, None)
|
||||||
if torch.std(out, unbiased=False) > 0.09: # not sure how well this will actually work. I guess we will find out.
|
if out is not None and torch.std(out, unbiased=False) > 0.09: # not sure how well this will actually work. I guess we will find out.
|
||||||
return model_base.ModelType.V_PREDICTION
|
return model_base.ModelType.V_PREDICTION
|
||||||
return model_base.ModelType.EPS
|
return model_base.ModelType.EPS
|
||||||
|
|
||||||
@ -334,6 +334,11 @@ class Stable_Zero123(supported_models_base.BASE):
|
|||||||
"num_head_channels": -1,
|
"num_head_channels": -1,
|
||||||
}
|
}
|
||||||
|
|
||||||
|
required_keys = {
|
||||||
|
"cc_projection.weight": None,
|
||||||
|
"cc_projection.bias": None,
|
||||||
|
}
|
||||||
|
|
||||||
clip_vision_prefix = "cond_stage_model.model.visual."
|
clip_vision_prefix = "cond_stage_model.model.visual."
|
||||||
|
|
||||||
latent_format = latent_formats.SD15
|
latent_format = latent_formats.SD15
|
||||||
@ -439,6 +444,33 @@ class Stable_Cascade_B(Stable_Cascade_C):
|
|||||||
out = model_base.StableCascade_B(self, device=device)
|
out = model_base.StableCascade_B(self, device=device)
|
||||||
return out
|
return out
|
||||||
|
|
||||||
|
class SD15_instructpix2pix(SD15):
|
||||||
|
unet_config = {
|
||||||
|
"context_dim": 768,
|
||||||
|
"model_channels": 320,
|
||||||
|
"use_linear_in_transformer": False,
|
||||||
|
"adm_in_channels": None,
|
||||||
|
"use_temporal_attention": False,
|
||||||
|
"in_channels": 8,
|
||||||
|
}
|
||||||
|
|
||||||
|
def get_model(self, state_dict, prefix="", device=None):
|
||||||
|
return model_base.SD15_instructpix2pix(self, device=device)
|
||||||
|
|
||||||
|
class SDXL_instructpix2pix(SDXL):
|
||||||
|
unet_config = {
|
||||||
|
"model_channels": 320,
|
||||||
|
"use_linear_in_transformer": True,
|
||||||
|
"transformer_depth": [0, 0, 2, 2, 10, 10],
|
||||||
|
"context_dim": 2048,
|
||||||
|
"adm_in_channels": 2816,
|
||||||
|
"use_temporal_attention": False,
|
||||||
|
"in_channels": 8,
|
||||||
|
}
|
||||||
|
|
||||||
|
def get_model(self, state_dict, prefix="", device=None):
|
||||||
|
return model_base.SDXL_instructpix2pix(self, device=device)
|
||||||
|
|
||||||
|
models = [Stable_Zero123, SD15_instructpix2pix, SD15, SD20, SD21UnclipL, SD21UnclipH, SDXL_instructpix2pix, SDXLRefiner, SDXL, SSD1B, KOALA_700M, KOALA_1B, Segmind_Vega, SD_X4Upscaler, Stable_Cascade_C, Stable_Cascade_B, SV3D_u, SV3D_p]
|
||||||
|
|
||||||
models = [Stable_Zero123, SD15, SD20, SD21UnclipL, SD21UnclipH, SDXLRefiner, SDXL, SSD1B, KOALA_700M, KOALA_1B, Segmind_Vega, SD_X4Upscaler, Stable_Cascade_C, Stable_Cascade_B, SV3D_u, SV3D_p]
|
|
||||||
models += [SVD_img2vid]
|
models += [SVD_img2vid]
|
||||||
|
|||||||
@ -16,6 +16,8 @@ class BASE:
|
|||||||
"num_head_channels": 64,
|
"num_head_channels": 64,
|
||||||
}
|
}
|
||||||
|
|
||||||
|
required_keys = {}
|
||||||
|
|
||||||
clip_prefix = []
|
clip_prefix = []
|
||||||
clip_vision_prefix = None
|
clip_vision_prefix = None
|
||||||
noise_aug_config = None
|
noise_aug_config = None
|
||||||
@ -28,10 +30,14 @@ class BASE:
|
|||||||
manual_cast_dtype = None
|
manual_cast_dtype = None
|
||||||
|
|
||||||
@classmethod
|
@classmethod
|
||||||
def matches(s, unet_config):
|
def matches(s, unet_config, state_dict=None):
|
||||||
for k in s.unet_config:
|
for k in s.unet_config:
|
||||||
if k not in unet_config or s.unet_config[k] != unet_config[k]:
|
if k not in unet_config or s.unet_config[k] != unet_config[k]:
|
||||||
return False
|
return False
|
||||||
|
if state_dict is not None:
|
||||||
|
for k in s.required_keys:
|
||||||
|
if k not in state_dict:
|
||||||
|
return False
|
||||||
return True
|
return True
|
||||||
|
|
||||||
def model_type(self, state_dict, prefix=""):
|
def model_type(self, state_dict, prefix=""):
|
||||||
|
|||||||
@ -31,7 +31,7 @@ class PerpNeg:
|
|||||||
model_options = args["model_options"]
|
model_options = args["model_options"]
|
||||||
nocond_processed = comfy.samplers.encode_model_conds(model.extra_conds, nocond, x, x.device, "negative")
|
nocond_processed = comfy.samplers.encode_model_conds(model.extra_conds, nocond, x, x.device, "negative")
|
||||||
|
|
||||||
(noise_pred_nocond, _) = comfy.samplers.calc_cond_uncond_batch(model, nocond_processed, None, x, sigma, model_options)
|
(noise_pred_nocond,) = comfy.samplers.calc_cond_batch(model, [nocond_processed], x, sigma, model_options)
|
||||||
|
|
||||||
pos = noise_pred_pos - noise_pred_nocond
|
pos = noise_pred_pos - noise_pred_nocond
|
||||||
neg = noise_pred_neg - noise_pred_nocond
|
neg = noise_pred_neg - noise_pred_nocond
|
||||||
|
|||||||
@ -204,13 +204,13 @@ class Sharpen:
|
|||||||
"default": 1.0,
|
"default": 1.0,
|
||||||
"min": 0.1,
|
"min": 0.1,
|
||||||
"max": 10.0,
|
"max": 10.0,
|
||||||
"step": 0.1
|
"step": 0.01
|
||||||
}),
|
}),
|
||||||
"alpha": ("FLOAT", {
|
"alpha": ("FLOAT", {
|
||||||
"default": 1.0,
|
"default": 1.0,
|
||||||
"min": 0.0,
|
"min": 0.0,
|
||||||
"max": 5.0,
|
"max": 5.0,
|
||||||
"step": 0.1
|
"step": 0.01
|
||||||
}),
|
}),
|
||||||
},
|
},
|
||||||
}
|
}
|
||||||
|
|||||||
@ -150,7 +150,7 @@ class SelfAttentionGuidance:
|
|||||||
degraded = create_blur_map(uncond_pred, uncond_attn, sag_sigma, sag_threshold)
|
degraded = create_blur_map(uncond_pred, uncond_attn, sag_sigma, sag_threshold)
|
||||||
degraded_noised = degraded + x - uncond_pred
|
degraded_noised = degraded + x - uncond_pred
|
||||||
# call into the UNet
|
# call into the UNet
|
||||||
(sag, _) = comfy.samplers.calc_cond_uncond_batch(model, uncond, None, degraded_noised, sigma, model_options)
|
(sag,) = comfy.samplers.calc_cond_batch(model, [uncond], degraded_noised, sigma, model_options)
|
||||||
return cfg_result + (degraded - sag) * sag_scale
|
return cfg_result + (degraded - sag) * sag_scale
|
||||||
|
|
||||||
m.set_model_sampler_post_cfg_function(post_cfg_function, disable_cfg1_optimization=True)
|
m.set_model_sampler_post_cfg_function(post_cfg_function, disable_cfg1_optimization=True)
|
||||||
|
|||||||
@ -47,7 +47,7 @@ blacklist = {"GeForce GTX TITAN X", "GeForce GTX 980", "GeForce GTX 970", "GeFor
|
|||||||
"Quadro K1200", "Quadro K2200", "Quadro M500", "Quadro M520", "Quadro M600", "Quadro M620", "Quadro M1000",
|
"Quadro K1200", "Quadro K2200", "Quadro M500", "Quadro M520", "Quadro M600", "Quadro M620", "Quadro M1000",
|
||||||
"Quadro M1200", "Quadro M2000", "Quadro M2200", "Quadro M3000", "Quadro M4000", "Quadro M5000", "Quadro M5500", "Quadro M6000",
|
"Quadro M1200", "Quadro M2000", "Quadro M2200", "Quadro M3000", "Quadro M4000", "Quadro M5000", "Quadro M5500", "Quadro M6000",
|
||||||
"GeForce MX110", "GeForce MX130", "GeForce 830M", "GeForce 840M", "GeForce GTX 850M", "GeForce GTX 860M",
|
"GeForce MX110", "GeForce MX130", "GeForce 830M", "GeForce 840M", "GeForce GTX 850M", "GeForce GTX 860M",
|
||||||
"GeForce GTX 1650", "GeForce GTX 1630"
|
"GeForce GTX 1650", "GeForce GTX 1630", "Tesla M4", "Tesla M6", "Tesla M10", "Tesla M40", "Tesla M60"
|
||||||
}
|
}
|
||||||
|
|
||||||
def cuda_malloc_supported():
|
def cuda_malloc_supported():
|
||||||
|
|||||||
@ -368,6 +368,7 @@ class PromptExecutor:
|
|||||||
d = self.outputs_ui.pop(x)
|
d = self.outputs_ui.pop(x)
|
||||||
del d
|
del d
|
||||||
|
|
||||||
|
comfy.model_management.cleanup_models(keep_clone_weights_loaded=True)
|
||||||
self.add_message("execution_cached",
|
self.add_message("execution_cached",
|
||||||
{ "nodes": list(current_outputs) , "prompt_id": prompt_id},
|
{ "nodes": list(current_outputs) , "prompt_id": prompt_id},
|
||||||
broadcast=False)
|
broadcast=False)
|
||||||
|
|||||||
@ -1,5 +1,6 @@
|
|||||||
import os
|
import os
|
||||||
import time
|
import time
|
||||||
|
import logging
|
||||||
|
|
||||||
supported_pt_extensions = set(['.ckpt', '.pt', '.bin', '.pth', '.safetensors'])
|
supported_pt_extensions = set(['.ckpt', '.pt', '.bin', '.pth', '.safetensors'])
|
||||||
|
|
||||||
@ -44,7 +45,7 @@ if not os.path.exists(input_directory):
|
|||||||
try:
|
try:
|
||||||
os.makedirs(input_directory)
|
os.makedirs(input_directory)
|
||||||
except:
|
except:
|
||||||
print("Failed to create input directory")
|
logging.error("Failed to create input directory")
|
||||||
|
|
||||||
def set_output_directory(output_dir):
|
def set_output_directory(output_dir):
|
||||||
global output_directory
|
global output_directory
|
||||||
@ -146,8 +147,9 @@ def recursive_search(directory, excluded_dir_names=None):
|
|||||||
try:
|
try:
|
||||||
dirs[directory] = os.path.getmtime(directory)
|
dirs[directory] = os.path.getmtime(directory)
|
||||||
except FileNotFoundError:
|
except FileNotFoundError:
|
||||||
print(f"Warning: Unable to access {directory}. Skipping this path.")
|
logging.warning(f"Warning: Unable to access {directory}. Skipping this path.")
|
||||||
|
|
||||||
|
logging.debug("recursive file list on directory {}".format(directory))
|
||||||
for dirpath, subdirs, filenames in os.walk(directory, followlinks=True, topdown=True):
|
for dirpath, subdirs, filenames in os.walk(directory, followlinks=True, topdown=True):
|
||||||
subdirs[:] = [d for d in subdirs if d not in excluded_dir_names]
|
subdirs[:] = [d for d in subdirs if d not in excluded_dir_names]
|
||||||
for file_name in filenames:
|
for file_name in filenames:
|
||||||
@ -159,8 +161,9 @@ def recursive_search(directory, excluded_dir_names=None):
|
|||||||
try:
|
try:
|
||||||
dirs[path] = os.path.getmtime(path)
|
dirs[path] = os.path.getmtime(path)
|
||||||
except FileNotFoundError:
|
except FileNotFoundError:
|
||||||
print(f"Warning: Unable to access {path}. Skipping this path.")
|
logging.warning(f"Warning: Unable to access {path}. Skipping this path.")
|
||||||
continue
|
continue
|
||||||
|
logging.debug("found {} files".format(len(result)))
|
||||||
return result, dirs
|
return result, dirs
|
||||||
|
|
||||||
def filter_files_extensions(files, extensions):
|
def filter_files_extensions(files, extensions):
|
||||||
@ -249,7 +252,7 @@ def get_save_image_path(filename_prefix, output_dir, image_width=0, image_height
|
|||||||
"\n full_output_folder: " + os.path.abspath(full_output_folder) + \
|
"\n full_output_folder: " + os.path.abspath(full_output_folder) + \
|
||||||
"\n output_dir: " + output_dir + \
|
"\n output_dir: " + output_dir + \
|
||||||
"\n commonpath: " + os.path.commonpath((output_dir, os.path.abspath(full_output_folder)))
|
"\n commonpath: " + os.path.commonpath((output_dir, os.path.abspath(full_output_folder)))
|
||||||
print(err)
|
logging.error(err)
|
||||||
raise Exception(err)
|
raise Exception(err)
|
||||||
|
|
||||||
try:
|
try:
|
||||||
|
|||||||
3
nodes.py
3
nodes.py
@ -41,7 +41,7 @@ def before_node_execution():
|
|||||||
def interrupt_processing(value=True):
|
def interrupt_processing(value=True):
|
||||||
comfy.model_management.interrupt_current_processing(value)
|
comfy.model_management.interrupt_current_processing(value)
|
||||||
|
|
||||||
MAX_RESOLUTION=8192
|
MAX_RESOLUTION=16384
|
||||||
|
|
||||||
class CLIPTextEncode:
|
class CLIPTextEncode:
|
||||||
@classmethod
|
@classmethod
|
||||||
@ -1876,6 +1876,7 @@ def load_custom_node(module_path, ignore=set()):
|
|||||||
sp = os.path.splitext(module_path)
|
sp = os.path.splitext(module_path)
|
||||||
module_name = sp[0]
|
module_name = sp[0]
|
||||||
try:
|
try:
|
||||||
|
logging.debug("Trying to load custom node {}".format(module_path))
|
||||||
if os.path.isfile(module_path):
|
if os.path.isfile(module_path):
|
||||||
module_spec = importlib.util.spec_from_file_location(module_name, module_path)
|
module_spec = importlib.util.spec_from_file_location(module_name, module_path)
|
||||||
module_dir = os.path.split(module_path)[0]
|
module_dir = os.path.split(module_path)[0]
|
||||||
|
|||||||
@ -947,7 +947,7 @@ describe("group node", () => {
|
|||||||
expect(p1.widgets.value.widget.options?.step).toBe(80); // width/height step * 10
|
expect(p1.widgets.value.widget.options?.step).toBe(80); // width/height step * 10
|
||||||
|
|
||||||
expect(p2.widgets.value.widget.options?.min).toBe(16); // width/height min
|
expect(p2.widgets.value.widget.options?.min).toBe(16); // width/height min
|
||||||
expect(p2.widgets.value.widget.options?.max).toBe(8192); // width/height max
|
expect(p2.widgets.value.widget.options?.max).toBe(16384); // width/height max
|
||||||
expect(p2.widgets.value.widget.options?.step).toBe(80); // width/height step * 10
|
expect(p2.widgets.value.widget.options?.step).toBe(80); // width/height step * 10
|
||||||
|
|
||||||
expect(p1.widgets.value.value).toBe(128);
|
expect(p1.widgets.value.value).toBe(128);
|
||||||
|
|||||||
Loading…
x
Reference in New Issue
Block a user