Skip to content
Python

more spoil

DeepBeepMeepba764e8d6055
diff --git a/README.md b/README.md
index 9b8f70d..d9be0fd 100644
--- a/README.md
+++ b/README.md
@@ -20,21 +20,27 @@ WanGP supports the Wan (and derived models), Hunyuan Video and LTV Video models
**Follow DeepBeepMeep on Twitter/X to get the Latest News**: https://x.com/deepbeepmeep
## 🔥 Latest Updates :
-### September 25 2025: WanGP v8.73 - Here Are ~~Two~~Three New Contenders in the Vace Arena !
+### September 25 2025: WanGP v8.73 - ~~Here Are Two Three New Contenders in the Vace Arena !~~ The Never Ending Release
-So in today's release you will find two Wannabe Vace that covers each only a subset of Vace features but offers some interesting advantages:
+So in ~~today's~~ this release you will find two Wannabe Vace that covers each only a subset of Vace features but offers some interesting advantages:
- **Wan 2.2 Animate**: this model is specialized in *Body Motion* and *Facial Motion transfers*. It does that very well. You can use this model to either *Replace* a person in an in Video or *Animate* the person of your choice using an existing *Pose Video* (remember *Animate Anyone* ?). By default it will keep the original soundtrack. *Wan 2.2 Animate* seems to be under the hood a derived i2v model and should support the corresponding Loras Accelerators (for instance *FusioniX t2v*). Also as a WanGP exclusivity, you will find support for *Outpainting*.
In order to use Wan 2.2 Animate you will need first to stop by the *Mat Anyone* embedded tool, to extract the *Video Mask* of the person from which you want to extract the motion.
+With version WanGP 8.74, there is an extra option that allows you to apply *Relighting* when Replacing a person. Also, you can now Animate a person without providing a Video Mask to target the source of the motion (with the risk it will be less precise)
+
- **Lucy Edit**: this one claims to be a *Nano Banana* for Videos. Give it a video and asks it to change it (it is specialized in clothes changing) and voila ! The nice thing about it is that is it based on the *Wan 2.2 5B* model and therefore is very fast especially if you the *FastWan* finetune that is also part of the package.
Also because I wanted to spoil you:
- **Qwen Edit Plus**: also known as the *Qwen Edit 25th September Update* which is specialized in combining multiple Objects / People. There is also a new support for *Pose transfer* & *Recolorisation*. All of this made easy to use in WanGP. You will find right now only the quantized version since HF crashes when uploading the unquantized version.
+- **T2V Video 2 Video Masking**: ever wanted to apply a Lora, a process (for instance Upsampling) or a Text Prompt on only a (moving) part of a Source Video. Look no further, I have added *Masked Video 2 Video* (which works also in image2image) in the *Text 2 Video* models. As usual you just need to use *Matanyone* to creatre the mask.
+
+
*Update 8.71*: fixed Fast Lucy Edit that didnt contain the lora
*Update 8.72*: shadow drop of Qwen Edit Plus
*Update 8.73*: Qwen Preview & InfiniteTalk Start image
+*Update 8.74*: Animate Relighting / Nomask mode , t2v Masked Video to Video
### September 15 2025: WanGP v8.6 - Attack of the Clones
diff --git a/defaults/animate.json b/defaults/animate.json
index fee26d7..bf45f4a 100644
--- a/defaults/animate.json
+++ b/defaults/animate.json
@@ -2,12 +2,16 @@
"model": {
"name": "Wan2.2 Animate",
"architecture": "animate",
- "description": "Wan-Animate takes a video and a character image as input, and generates a video in either 'animation' or 'replacement' mode.",
+ "description": "Wan-Animate takes a video and a character image as input, and generates a video in either 'Animation' or 'Replacement' mode. Sliding Window of 81 frames at least are recommeded to obtain the best Style continuity.",
"URLs": [
"https://huggingface.co/DeepBeepMeep/Wan2.2/resolve/main/wan2.2_animate_14B_bf16.safetensors",
"https://huggingface.co/DeepBeepMeep/Wan2.2/resolve/main/wan2.2_animate_14B_quanto_fp16_int8.safetensors",
"https://huggingface.co/DeepBeepMeep/Wan2.2/resolve/main/wan2.2_animate_14B_quanto_bf16_int8.safetensors"
],
+ "preload_URLs" :
+ [
+ "https://huggingface.co/DeepBeepMeep/Wan2.2/resolve/main/wan2.2_animate_relighting_lora.safetensors"
+ ],
"group": "wan2_2"
}
}
\ No newline at end of file
diff --git a/models/flux/sampling.py b/models/flux/sampling.py
index 92ee590..939543c 100644
--- a/models/flux/sampling.py
+++ b/models/flux/sampling.py
@@ -292,7 +292,7 @@ def denoise(
callback(-1, None, True)
original_image_latents = None if img_cond_seq is None else img_cond_seq.clone()
-
+ original_timesteps = timesteps
morph, first_step = False, 0
if img_msk_latents is not None:
randn = torch.randn_like(original_image_latents)
@@ -309,7 +309,7 @@ def denoise(
updated_num_steps= len(timesteps) -1
if callback != None:
from shared.utils.loras_mutipliers import update_loras_slists
- update_loras_slists(model, loras_slists, updated_num_steps)
+ update_loras_slists(model, loras_slists, len(original_timesteps))
callback(-1, None, True, override_num_inference_steps = updated_num_steps)
from mmgp import offload
# this is ignored for schnell
diff --git a/models/qwen/pipeline_qwenimage.py b/models/qwen/pipeline_qwenimage.py
index 134cc51..02fd473 100644
--- a/models/qwen/pipeline_qwenimage.py
+++ b/models/qwen/pipeline_qwenimage.py
@@ -825,7 +825,7 @@ class QwenImagePipeline(): #DiffusionPipeline
)
num_warmup_steps = max(len(timesteps) - num_inference_steps * self.scheduler.order, 0)
self._num_timesteps = len(timesteps)
-
+ original_timesteps = timesteps
# handle guidance
if self.transformer.guidance_embeds:
guidance = torch.full([1], guidance_scale, device=device, dtype=torch.float32)
@@ -860,7 +860,7 @@ class QwenImagePipeline(): #DiffusionPipeline
updated_num_steps= len(timesteps)
if callback != None:
from shared.utils.loras_mutipliers import update_loras_slists
- update_loras_slists(self.transformer, loras_slists, updated_num_steps)
+ update_loras_slists(self.transformer, loras_slists, len(original_timesteps))
callback(-1, None, True, override_num_inference_steps = updated_num_steps)
diff --git a/models/wan/any2video.py b/models/wan/any2video.py
index 6b4ae62..285340d 100644
--- a/models/wan/any2video.py
+++ b/models/wan/any2video.py
@@ -34,6 +34,7 @@ from shared.utils.vace_preprocessor import VaceVideoProcessor
from shared.utils.basic_flowmatch import FlowMatchScheduler
from shared.utils.utils import get_outpainting_frame_location, resize_lanczos, calculate_new_dimensions, convert_image_to_tensor, fit_image_into_canvas
from .multitalk.multitalk_utils import MomentumBuffer, adaptive_projected_guidance, match_and_blend_colors, match_and_blend_colors_with_mask
+from shared.utils.audio_video import save_video
from mmgp import safetensors2
from shared.utils.audio_video import save_video
@@ -434,7 +435,7 @@ class WanAny2V:
start_step_no = 0
ref_images_count = 0
trim_frames = 0
- extended_overlapped_latents = clip_image_start = clip_image_end = None
+ extended_overlapped_latents = clip_image_start = clip_image_end = image_mask_latents = None
no_noise_latents_injection = infinitetalk
timestep_injection = False
lat_frames = int((frame_num - 1) // self.vae_stride[0]) + 1
@@ -585,7 +586,7 @@ class WanAny2V:
kwargs['cam_emb'] = cam_emb
# Video 2 Video
- if denoising_strength < 1. and input_frames != None:
+ if "G" in video_prompt_type and input_frames != None:
height, width = input_frames.shape[-2:]
source_latents = self.vae.encode([input_frames])[0].unsqueeze(0)
injection_denoising_step = 0
@@ -616,6 +617,14 @@ class WanAny2V:
if hasattr(sample_scheduler, "sigmas"): sample_scheduler.sigmas= sample_scheduler.sigmas[injection_denoising_step:]
injection_denoising_step = 0
+ if input_masks is not None and not "U" in video_prompt_type:
+ image_mask_latents = torch.nn.functional.interpolate(input_masks, size= source_latents.shape[-2:], mode="nearest").unsqueeze(0)
+ if image_mask_latents.shape[2] !=1:
+ image_mask_latents = torch.cat([ image_mask_latents[:,:, :1], torch.nn.functional.interpolate(image_mask_latents, size= (source_latents.shape[-3]-1, *source_latents.shape[-2:]), mode="nearest") ], dim=2)
+ image_mask_latents = torch.where(image_mask_latents>=0.5, 1., 0. )[:1].to(self.device)
+ # save_video(image_mask_latents.squeeze(0), "mama.mp4", value_range=(0,1) )
+ # image_mask_rebuilt = image_mask_latents.repeat_interleave(8, dim=-1).repeat_interleave(8, dim=-2).unsqueeze(0)
+
# Phantom
if phantom:
lat_input_ref_images_neg = None
@@ -737,7 +746,7 @@ class WanAny2V:
denoising_extra = ""
from shared.utils.loras_mutipliers import update_loras_slists, get_model_switch_steps
- phase_switch_step, phase_switch_step2, phases_description = get_model_switch_steps(timesteps, updated_num_steps, guide_phases, 0 if self.model2 is None else model_switch_phase, switch_threshold, switch2_threshold )
+ phase_switch_step, phase_switch_step2, phases_description = get_model_switch_steps(original_timesteps,guide_phases, 0 if self.model2 is None else model_switch_phase, switch_threshold, switch2_threshold )
if len(phases_description) > 0: set_header_text(phases_description)
guidance_switch_done = guidance_switch2_done = False
if guide_phases > 1: denoising_extra = f"Phase 1/{guide_phases} High Noise" if self.model2 is not None else f"Phase 1/{guide_phases}"
@@ -748,8 +757,8 @@ class WanAny2V:
denoising_extra = f"Phase {phase_no}/{guide_phases} {'Low Noise' if trans == self.model2 else 'High Noise'}" if self.model2 is not None else f"Phase {phase_no}/{guide_phases}"
callback(step_no-1, denoising_extra = denoising_extra)
return guide_scale, guidance_switch_done, trans, denoising_extra
- update_loras_slists(self.model, loras_slists, updated_num_steps, phase_switch_step= phase_switch_step, phase_switch_step2= phase_switch_step2)
- if self.model2 is not None: update_loras_slists(self.model2, loras_slists, updated_num_steps, phase_switch_step= phase_switch_step, phase_switch_step2= phase_switch_step2)
+ update_loras_slists(self.model, loras_slists, len(original_timesteps), phase_switch_step= phase_switch_step, phase_switch_step2= phase_switch_step2)
+ if self.model2 is not None: update_loras_slists(self.model2, loras_slists, len(original_timesteps), phase_switch_step= phase_switch_step, phase_switch_step2= phase_switch_step2)
callback(-1, None, True, override_num_inference_steps = updated_num_steps, denoising_extra = denoising_extra)
def clear():
@@ -762,6 +771,7 @@ class WanAny2V:
scheduler_kwargs = {} if isinstance(sample_scheduler, FlowMatchScheduler) else {"generator": seed_g}
# b, c, lat_f, lat_h, lat_w
latents = torch.randn(batch_size, *target_shape, dtype=torch.float32, device=self.device, generator=seed_g)
+ if "G" in video_prompt_type: randn = latents
if apg_switch != 0:
apg_momentum = -0.75
apg_norm_threshold = 55
@@ -784,23 +794,21 @@ class WanAny2V:
timestep = torch.full((target_shape[-3],), t, dtype=torch.int64, device=latents.device)
timestep[:source_latents.shape[2]] = 0
- kwargs.update({"t": timestep, "current_step": start_step_no + i})
+ kwargs.update({"t": timestep, "current_step_no": i, "real_step_no": start_step_no + i })
kwargs["slg_layers"] = slg_layers if int(slg_start * sampling_steps) <= i < int(slg_end * sampling_steps) else None
if denoising_strength < 1 and i <= injection_denoising_step:
sigma = t / 1000
- noise = torch.randn(batch_size, *target_shape, dtype=torch.float32, device=self.device, generator=seed_g)
if inject_from_start:
- new_latents = latents.clone()
- new_latents[:,:, :source_latents.shape[2] ] = noise[:, :, :source_latents.shape[2] ] * sigma + (1 - sigma) * source_latents
+ noisy_image = latents.clone()
+ noisy_image[:,:, :source_latents.shape[2] ] = randn[:, :, :source_latents.shape[2] ] * sigma + (1 - sigma) * source_latents
for latent_no, keep_latent in enumerate(latent_keep_frames):
if not keep_latent:
- new_latents[:, :, latent_no:latent_no+1 ] = latents[:, :, latent_no:latent_no+1]
- latents = new_latents
- new_latents = None
+ noisy_image[:, :, latent_no:latent_no+1 ] = latents[:, :, latent_no:latent_no+1]
+ latents = noisy_image
+ noisy_image = None
else:
- latents = noise * sigma + (1 - sigma) * source_latents
- noise = None
+ latents = randn * sigma + (1 - sigma) * source_latents
if extended_overlapped_latents != None:
if no_noise_latents_injection:
@@ -940,6 +948,13 @@ class WanAny2V:
latents,
**scheduler_kwargs)[0]
+
+ if image_mask_latents is not None:
+ sigma = 0 if i == len(timesteps)-1 else timesteps[i+1]/1000
+ noisy_image = randn * sigma + (1 - sigma) * source_latents
+ latents = noisy_image * (1-image_mask_latents) + image_mask_latents * latents
+
+
if callback is not None:
latents_preview = latents
if ref_images_before and ref_images_count > 0: latents_preview = latents_preview[:, :, ref_images_count: ]
@@ -999,3 +1014,11 @@ class WanAny2V:
setattr(target, "face_adapter_fuser_blocks", module )
delattr(model, "face_adapter")
+ def get_loras_transformer(self, get_model_recursive_prop, base_model_type, model_type, video_prompt_type, model_mode, **kwargs):
+ if base_model_type == "animate":
+ if "1" in video_prompt_type:
+ preloadURLs = get_model_recursive_prop(model_type, "preload_URLs")
+ if len(preloadURLs) > 0:
+ return [os.path.join("ckpts", os.path.basename(preloadURLs[0]))] , [1]
+ return [], []
+
diff --git a/models/wan/modules/model.py b/models/wan/modules/model.py
index c98087b..cd02470 100644
--- a/models/wan/modules/model.py
+++ b/models/wan/modules/model.py
@@ -1220,7 +1220,8 @@ class WanModel(ModelMixin, ConfigMixin):
y=None,
freqs = None,
pipeline = None,
- current_step = 0,
+ current_step_no = 0,
+ real_step_no = 0,
x_id= 0,
max_steps = 0,
slg_layers=None,
@@ -1310,9 +1311,9 @@ class WanModel(ModelMixin, ConfigMixin):
del causal_mask
offload.shared_state["embed_sizes"] = grid_sizes
- offload.shared_state["step_no"] = current_step
+ offload.shared_state["step_no"] = real_step_no
offload.shared_state["max_steps"] = max_steps
- if current_step == 0 and x_id == 0: clear_caches()
+ if current_step_no == 0 and x_id == 0: clear_caches()
# arguments
kwargs = dict(
@@ -1336,7 +1337,7 @@ class WanModel(ModelMixin, ConfigMixin):
if standin_ref is not None:
standin_cache_enabled = False
kwargs["standin_phase"] = 2
- if current_step == 0 or not standin_cache_enabled :
+ if current_step_no == 0 or not standin_cache_enabled :
standin_x = self.patch_embedding(standin_ref).to(modulation_dtype).flatten(2).transpose(1, 2)
standin_e = self.time_embedding( sinusoidal_embedding_1d(self.freq_dim, torch.zeros_like(t)).to(modulation_dtype) )
standin_e0 = self.time_projection(standin_e).unflatten(1, (6, self.dim)).to(e.dtype)
@@ -1401,7 +1402,7 @@ class WanModel(ModelMixin, ConfigMixin):
skips_steps_cache = self.cache
if skips_steps_cache != None:
if skips_steps_cache.cache_type == "mag":
- if current_step <= skips_steps_cache.start_step:
+ if real_step_no <= skips_steps_cache.start_step:
should_calc = True
elif skips_steps_cache.one_for_all and x_id != 0: # not joint pass, not main pas, one for all
assert len(x_list) == 1
@@ -1410,7 +1411,7 @@ class WanModel(ModelMixin, ConfigMixin):
x_should_calc = []
for i in range(1 if skips_steps_cache.one_for_all else len(x_list)):
cur_x_id = i if joint_pass else x_id
- cur_mag_ratio = skips_steps_cache.mag_ratios[current_step * 2 + cur_x_id] # conditional and unconditional in one list
+ cur_mag_ratio = skips_steps_cache.mag_ratios[real_step_no * 2 + cur_x_id] # conditional and unconditional in one list
skips_steps_cache.accumulated_ratio[cur_x_id] *= cur_mag_ratio # magnitude ratio between current step and the cached step
skips_steps_cache.accumulated_steps[cur_x_id] += 1 # skip steps plus 1
cur_skip_err = np.abs(1-skips_steps_cache.accumulated_ratio[cur_x_id]) # skip error of current steps
@@ -1430,7 +1431,7 @@ class WanModel(ModelMixin, ConfigMixin):
if x_id != 0:
should_calc = skips_steps_cache.should_calc
else:
- if current_step <= skips_steps_cache.start_step or current_step == skips_steps_cache.num_steps-1:
+ if real_step_no <= skips_steps_cache.start_step or real_step_no == skips_steps_cache.num_steps-1:
should_calc = True
skips_steps_cache.accumulated_rel_l1_distance = 0
else:
diff --git a/models/wan/wan_handler.py b/models/wan/wan_handler.py
index 574c990..c587544 100644
--- a/models/wan/wan_handler.py
+++ b/models/wan/wan_handler.py
@@ -124,12 +124,20 @@ class family_handler():
if base_model_type in ["t2v"]:
extra_model_def["guide_custom_choices"] = {
- "choices":[("Use Text Prompt Only", ""),("Video to Video guided by Text Prompt", "GUV")],
+ "choices":[("Use Text Prompt Only", ""),
+ ("Video to Video guided by Text Prompt", "GUV"),
+ ("Video to Video guided by Text Prompt and Restricted to the Area of the Video Mask", "GVA")],
"default": "",
- "letters_filter": "GUV",
+ "letters_filter": "GUVA",
"label": "Video to Video"
}
+ extra_model_def["mask_preprocessing"] = {
+ "selection":[ "", "A"],
+ "visible": False
+ }
+
+
if base_model_type in ["infinitetalk"]:
extra_model_def["no_background_removal"] = True
extra_model_def["all_image_refs_are_background_ref"] = True
@@ -160,14 +168,22 @@ class family_handler():
if base_model_type in ["animate"]:
extra_model_def["guide_custom_choices"] = {
"choices":[
- ("Animate Person in Reference Image using Motion of Person in Control Video", "PVBXAKI"),
- ("Replace Person in Control Video Person in Reference Image", "PVBAI"),
+ ("Animate Person in Reference Image using Motion of Whole Control Video", "PVBKI"),
+ ("Animate Person in Reference Image using Motion of Targeted Person in Control Video", "PVBXAKI"),
+ ("Replace Person in Control Video by Person in Reference Image", "PVBAI"),
+ ("Replace Person in Control Video by Person in Reference Image and Apply Relighting Process", "PVBAI1"),
],
- "default": "KI",
- "letters_filter": "PVBXAKI",
+ "default": "PVBKI",
+ "letters_filter": "PVBXAKI1",
"label": "Type of Process",
"show_label" : False,
}
+
+ extra_model_def["mask_preprocessing"] = {
+ "selection":[ "", "A", "XA"],
+ "visible": False
+ }
+
extra_model_def["video_guide_outpainting"] = [0,1]
extra_model_def["keep_frames_video_guide_not_supported"] = True
extra_model_def["extract_guide_from_window_start"] = True
@@ -480,8 +496,8 @@ class family_handler():
"video_prompt_type": "UV",
})
elif base_model_type in ["animate"]:
- ui_defaults.update({
- "video_prompt_type": "PVBXAKI",
+ ui_defaults.update({
+ "video_prompt_type": "PVBKI",
"mask_expand": 20,
"audio_prompt_type": "R",
})
diff --git a/shared/utils/loras_mutipliers.py b/shared/utils/loras_mutipliers.py
index 58cc9a9..e0cec6a 100644
--- a/shared/utils/loras_mutipliers.py
+++ b/shared/utils/loras_mutipliers.py
@@ -99,7 +99,7 @@ def parse_loras_multipliers(loras_multipliers, nb_loras, num_inference_steps, me
return loras_list_mult_choices_nums, slists_dict, ""
-def update_loras_slists(trans, slists_dict, num_inference_steps, phase_switch_step = None, phase_switch_step2 = None ):
+def update_loras_slists(trans, slists_dict, num_inference_steps, phase_switch_step = None, phase_switch_step2 = None):
from mmgp import offload
sz = len(slists_dict["phase1"])
slists = [ expand_slist(slists_dict, i, num_inference_steps, phase_switch_step, phase_switch_step2 ) for i in range(sz) ]
@@ -108,7 +108,8 @@ def update_loras_slists(trans, slists_dict, num_inference_steps, phase_switch_st
-def get_model_switch_steps(timesteps, total_num_steps, guide_phases, model_switch_phase, switch_threshold, switch2_threshold ):
+def get_model_switch_steps(timesteps, guide_phases, model_switch_phase, switch_threshold, switch2_threshold ):
+ total_num_steps = len(timesteps)
model_switch_step = model_switch_step2 = None
for i, t in enumerate(timesteps):
if guide_phases >=2 and model_switch_step is None and t <= switch_threshold: model_switch_step = i
diff --git a/wgp.py b/wgp.py
index d1eae3b..def856f 100644
--- a/wgp.py
+++ b/wgp.py
@@ -63,7 +63,7 @@ AUTOSAVE_FILENAME = "queue.zip"
PROMPT_VARS_MAX = 10
target_mmgp_version = "3.6.0"
-WanGP_version = "8.73"
+WanGP_version = "8.74"
settings_version = 2.36
max_source_video_frames = 3000
prompt_enhancer_image_caption_model, prompt_enhancer_image_caption_processor, prompt_enhancer_llm_model, prompt_enhancer_llm_tokenizer = None, None, None, None
@@ -3699,13 +3699,15 @@ def extract_faces_from_video_with_mask(input_video_path, input_mask_path, max_fr
any_mask = input_mask_path != None
video = get_resampled_video(input_video_path, start_frame, max_frames, target_fps)
if len(video) == 0: return None
+ frame_height, frame_width, _ = video[0].shape
+ num_frames = len(video)
if any_mask:
mask_video = get_resampled_video(input_mask_path, start_frame, max_frames, target_fps)
- frame_height, frame_width, _ = video[0].shape
-
- num_frames = min(len(video), len(mask_video))
+ num_frames = min(num_frames, len(mask_video))
if num_frames == 0: return None
- video, mask_video = video[:num_frames], mask_video[:num_frames]
+ video = video[:num_frames]
+ if any_mask:
+ mask_video = mask_video[:num_frames]
from preprocessing.face_preprocessor import FaceProcessor
face_processor = FaceProcessor()
@@ -6970,39 +6972,49 @@ def refresh_video_prompt_type_alignment(state, video_prompt_type, video_prompt_t
all_guide_processes ="PDESLCMUVB"
-def refresh_video_prompt_type_video_guide(state, video_prompt_type, video_prompt_type_video_guide, image_mode, old_image_mask_guide_value, old_image_guide_value, old_image_mask_value ):
+def refresh_video_prompt_type_video_guide(state, filter_type, video_prompt_type, video_prompt_type_video_guide, image_mode, old_image_mask_guide_value, old_image_guide_value, old_image_mask_value ):
+ model_type = state["model_type"]
+ model_def = get_model_def(model_type)
old_video_prompt_type = video_prompt_type
- video_prompt_type = del_in_sequence(video_prompt_type, all_guide_processes)
+ if filter_type == "alt":
+ guide_custom_choices = model_def.get("guide_custom_choices",{})
+ letter_filter = guide_custom_choices.get("letters_filter","")
+ else:
+ letter_filter = all_guide_processes
+ video_prompt_type = del_in_sequence(video_prompt_type, letter_filter)
video_prompt_type = add_to_sequence(video_prompt_type, video_prompt_type_video_guide)
visible = "V" in video_prompt_type
- model_type = state["model_type"]
- model_def = get_model_def(model_type)
any_outpainting= image_mode in model_def.get("video_guide_outpainting", [])
mask_visible = visible and "A" in video_prompt_type and not "U" in video_prompt_type
image_outputs = image_mode > 0
keep_frames_video_guide_visible = not image_outputs and visible and not model_def.get("keep_frames_video_guide_not_supported", False)
image_mask_guide, image_guide, image_mask = switch_image_guide_editor(image_mode, old_video_prompt_type , video_prompt_type, old_image_mask_guide_value, old_image_guide_value, old_image_mask_value )
+ # mask_video_input_visible = image_mode == 0 and mask_visible
mask_preprocessing = model_def.get("mask_preprocessing", None)
if mask_preprocessing is not None:
mask_selector_visible = mask_preprocessing.get("visible", True)
else:
mask_selector_visible = True
- return video_prompt_type, gr.update(visible = visible and not image_outputs), image_guide, gr.update(visible = keep_frames_video_guide_visible), gr.update(visible = visible and "G" in video_prompt_type), gr.update(visible= (visible or "F" in video_prompt_type or "K" in video_prompt_type) and any_outpainting), gr.update(visible= visible and mask_selector_visible and not "U" in video_prompt_type ) , gr.update(visible= mask_visible and not image_outputs), image_mask, image_mask_guide, gr.update(visible= mask_visible)
-
-
-def refresh_video_prompt_type_video_guide_alt(state, video_prompt_type, video_prompt_type_video_guide_alt, image_mode):
- model_def = get_model_def(state["model_type"])
- guide_custom_choices = model_def.get("guide_custom_choices",{})
- video_prompt_type = del_in_sequence(video_prompt_type, guide_custom_choices.get("letters_filter",""))
- video_prompt_type = add_to_sequence(video_prompt_type, video_prompt_type_video_guide_alt)
- control_video_visible = "V" in video_prompt_type
ref_images_visible = "I" in video_prompt_type
- denoising_strength_visible = "G" in video_prompt_type
- return video_prompt_type, gr.update(visible = control_video_visible and image_mode ==0), gr.update(visible = control_video_visible and image_mode >=1), gr.update(visible = ref_images_visible ), gr.update(visible = denoising_strength_visible )
-
-# def refresh_video_prompt_video_guide_trigger(state, video_prompt_type, video_prompt_type_video_guide):
-# video_prompt_type_video_guide = video_prompt_type_video_guide.split("#")[0]
-# return refresh_video_prompt_type_video_guide(state, video_prompt_type, video_prompt_type_video_guide)
+ return video_prompt_type, gr.update(visible = visible and not image_outputs), image_guide, gr.update(visible = keep_frames_video_guide_visible), gr.update(visible = visible and "G" in video_prompt_type), gr.update(visible= (visible or "F" in video_prompt_type or "K" in video_prompt_type) and any_outpainting), gr.update(visible= visible and mask_selector_visible and not "U" in video_prompt_type ) , gr.update(visible= mask_visible and not image_outputs), image_mask, image_mask_guide, gr.update(visible= mask_visible), gr.update(visible = ref_images_visible )
+
+
+# def refresh_video_prompt_type_video_guide_alt(state, video_prompt_type, video_prompt_type_video_guide_alt, image_mode, old_image_mask_guide_value, old_image_guide_value, old_image_mask_value ):
+# old_video_prompt_type = video_prompt_type
+# model_def = get_model_def(state["model_type"])
+# guide_custom_choices = model_def.get("guide_custom_choices",{})
+# video_prompt_type = del_in_sequence(video_prompt_type, guide_custom_choices.get("letters_filter",""))
+# video_prompt_type = add_to_sequence(video_prompt_type, video_prompt_type_video_guide_alt)
+# image_outputs = image_mode > 0
+# control_video_visible = "V" in video_prompt_type
+# ref_images_visible = "I" in video_prompt_type
+# denoising_strength_visible = "G" in video_prompt_type
+# mask_expand_visible = control_video_visible and "A" in video_prompt_type and not "U" in video_prompt_type
+# mask_video_input_visible = image_mode == 0 and mask_expand_visible
+# image_mask_guide, image_guide, image_mask = switch_image_guide_editor(image_mode, old_video_prompt_type , video_prompt_type, old_image_mask_guide_value, old_image_guide_value, old_image_mask_value )
+# keep_frames_video_guide_visible = not image_outputs and visible and not model_def.get("keep_frames_video_guide_not_supported", False)
+
+# return video_prompt_type, gr.update(visible = control_video_visible and image_mode ==0), gr.update(visible = control_video_visible and image_mode >=1), gr.update(visible = ref_images_visible ), gr.update(visible = denoising_strength_visible ), gr.update(visible = mask_video_input_visible ), gr.update(visible = mask_expand_visible), image_mask_guide, image_guide, image_mask, gr.update(visible = keep_frames_video_guide_visible)
def refresh_preview(state):
gen = get_gen_info(state)
@@ -8294,9 +8306,10 @@ def generate_video_tab(update_form = False, state_dict = None, ui_defaults = Non
image_prompt_type_radio.change(fn=refresh_image_prompt_type_radio, inputs=[state, image_prompt_type, image_prompt_type_radio], outputs=[image_prompt_type, image_start_row, image_end_row, video_source, keep_frames_video_source, image_prompt_type_endcheckbox], show_progress="hidden" )
image_prompt_type_endcheckbox.change(fn=refresh_image_prompt_type_endcheckbox, inputs=[state, image_prompt_type, image_prompt_type_radio, image_prompt_type_endcheckbox], outputs=[image_prompt_type, image_end_row] )
video_prompt_type_image_refs.input(fn=refresh_video_prompt_type_image_refs, inputs = [state, video_prompt_type, video_prompt_type_image_refs,image_mode], outputs = [video_prompt_type, image_refs_row, remove_background_images_ref, image_refs_relative_size, frames_positions,video_guide_outpainting_col], show_progress="hidden")
- video_prompt_type_video_guide.input(fn=refresh_video_prompt_type_video_guide, inputs = [state, video_prompt_type, video_prompt_type_video_guide, image_mode, image_mask_guide, image_guide, image_mask], outputs = [video_prompt_type, video_guide, image_guide, keep_frames_video_guide, denoising_strength, video_guide_outpainting_col, video_prompt_type_video_mask, video_mask, image_mask, image_mask_guide, mask_expand], show_progress="hidden")
- video_prompt_type_video_guide_alt.input(fn=refresh_video_prompt_type_video_guide_alt, inputs = [state, video_prompt_type, video_prompt_type_video_guide_alt, image_mode], outputs = [video_prompt_type, video_guide, image_guide, image_refs_row, denoising_strength ], show_progress="hidden")
- video_prompt_type_video_mask.input(fn=refresh_video_prompt_type_video_mask, inputs = [state, video_prompt_type, video_prompt_type_video_mask, image_mode, image_mask_guide, image_guide, image_mask], outputs = [video_prompt_type, video_mask, image_mask_guide, image_guide, image_mask, mask_expand], show_progress="hidden")
+ video_prompt_type_video_guide.input(fn=refresh_video_prompt_type_video_guide, inputs = [state, gr.State(""), video_prompt_type, video_prompt_type_video_guide, image_mode, image_mask_guide, image_guide, image_mask], outputs = [video_prompt_type, video_guide, image_guide, keep_frames_video_guide, denoising_strength, video_guide_outpainting_col, video_prompt_type_video_mask, video_mask, image_mask, image_mask_guide, mask_expand, image_refs_row], show_progress="hidden")
+ video_prompt_type_video_guide_alt.input(fn=refresh_video_prompt_type_video_guide, inputs = [state, gr.State("alt"),video_prompt_type, video_prompt_type_video_guide_alt, image_mode, image_mask_guide, image_guide, image_mask], outputs = [video_prompt_type, video_guide, image_guide, keep_frames_video_guide, denoising_strength, video_guide_outpainting_col, video_prompt_type_video_mask, video_mask, image_mask, image_mask_guide, mask_expand, image_refs_row], show_progress="hidden")
+ # video_prompt_type_video_guide_alt.input(fn=refresh_video_prompt_type_video_guide_alt, inputs = [state, video_prompt_type, video_prompt_type_video_guide_alt, image_mode, image_mask_guide, image_guide, image_mask], outputs = [video_prompt_type, video_guide, image_guide, image_refs_row, denoising_strength, video_mask, mask_expand, image_mask_guide, image_guide, image_mask, keep_frames_video_guide ], show_progress="hidden")
+ video_prompt_type_video_mask.input(fn=refresh_video_prompt_type_video_mask, inputs = [state, video_prompt_type, video_prompt_type_video_mask, image_mode, image_mask_guide, image_guide, image_mask], outputs = [video_prompt_type, video_mask, image_mask_guide, image_guide, image_mask, mask_expand], show_progress="hidden")
video_prompt_type_alignment.input(fn=refresh_video_prompt_type_alignment, inputs = [state, video_prompt_type, video_prompt_type_alignment], outputs = [video_prompt_type])
multi_prompts_gen_type.select(fn=refresh_prompt_labels, inputs=[multi_prompts_gen_type, image_mode], outputs=[prompt, wizard_prompt, image_end], show_progress="hidden")
video_guide_outpainting_top.input(fn=update_video_guide_outpainting, inputs=[video_guide_outpainting, video_guide_outpainting_top, gr.State(0)], outputs = [video_guide_outpainting], trigger_mode="multiple" )