Public/automatic
1
0
Fork 0
mirror of https://github.com/vladmandic/automatic synced 2026-09-18 16:54:33 +02:00
Code Issues Packages Projects Releases Wiki Activity

add prompt enhance to ltx and fix audio

Browse Source 
Signed-off-by: Vladimir Mandic <mandic00@live.com>
This commit is contained in:
Vladimir Mandic
2026-07-28 13:11:21 +02:00
parent 7a6fa28484
commit e280938e79
6 changed files with 17 additions and 17 deletions
Download Patch File Download Diff File Expand all files Collapse all files
modules/ltx/ltx_process.py
+3 -1
View File
@@ -341,7 +341,9 @@ def run_ltx(task_id,
try:
if needs_latent_path:
prompt_final, negative_final, networks = get_prompts(prompt, negative, styles)
if p.scripts is not None and isinstance(p.scripts, scripts_manager.ScriptRunner):
p.scripts.before_process(p)
prompt_final, negative_final, networks = get_prompts(p)
extra_networks.activate(p, networks)
# Encode once and reuse across stages; encode_prompt short-circuits when
# embeds are passed to __call__. CPU park keeps them off GPU between stages.
modules/ltx/ltx_ui.py
+8 -8
View File
@@ -67,8 +67,8 @@ def create_ui(prompt, negative, styles, overrides, script_inputs, mp4_fps, mp4_i
with gr.Accordion(open=False, label='Size', elem_id='ltx_size_accordion'):
width, height = ui_sections.create_resolution_inputs('ltx', default_width=832, default_height=480)
with gr.Row():
frames = gr.Slider(label='LTX Frames', minimum=1, maximum=1024, step=1, value=121, elem_id='ltx_frames')
seed = gr.Number(label='Initial seed', value=-1, elem_id='ltx_seed', container=True)
frames = gr.Slider(label='LTX frames', minimum=1, maximum=1024, step=1, value=121, elem_id='ltx_frames')
seed = gr.Number(label='LTX seed', value=-1, elem_id='ltx_seed', container=True)
random_seed = ToolButton(ui_symbols.random, elem_id='ltx_seed_random')
random_seed.click(fn=lambda: -1, show_progress='hidden', inputs=[], outputs=[seed])
input_media_accordion = gr.Accordion(open=False, label="Input media", elem_id='ltx_input_media_accordion', visible=False)
@@ -88,16 +88,16 @@ def create_ui(prompt, negative, styles, overrides, script_inputs, mp4_fps, mp4_i
condition_video_skip = gr.Slider(label='LTX frames skip', minimum=0, maximum=1024, step=1, value=0, elem_id="ltx_condition_video_sip")
with gr.Tab('Gallery prefix', id='ltx_condition_batch_tab'):
condition_files = gr.Files(label="Image Batch", interactive=True, elem_id="ltx_condition_batch")
upsample_accordion = gr.Accordion(open=False, label="Upsample", elem_id='ltx_upsample_accordion')
upsample_accordion = gr.Accordion(open=False, label="Upscale", elem_id='ltx_upsample_accordion')
with upsample_accordion:
with gr.Row():
upsample_enable = gr.Checkbox(label='LTX enable upsampling', value=False, elem_id="ltx_upsample_enable")
upsample_ratio = gr.Slider(label='LTX upsample ratio', minimum=1.0, maximum=4.0, step=0.1, value=2.0, elem_id="ltx_upsample_ratio")
upsample_enable = gr.Checkbox(label='LTX upscale', value=False, elem_id="ltx_upsample_enable")
upsample_ratio = gr.Slider(label='LTX scale', minimum=1.0, maximum=4.0, step=0.1, value=2.0, elem_id="ltx_upsample_ratio")
refine_accordion = gr.Accordion(open=False, label="Refine", elem_id='ltx_refine_accordion')
with refine_accordion:
with gr.Row():
refine_enable = gr.Checkbox(label='LTX enable refine', value=False, elem_id="ltx_refine_enable")
refine_strength = gr.Slider(label='LTX refine strength', minimum=0.1, maximum=1.0, step=0.05, value=0.4, elem_id="ltx_refine_strength")
refine_enable = gr.Checkbox(label='LTX refine', value=False, elem_id="ltx_refine_enable")
refine_strength = gr.Slider(label='LTX strength', minimum=0.1, maximum=1.0, step=0.05, value=0.4, elem_id="ltx_refine_strength")
parameters_accordion = gr.Accordion(open=False, label="Advanced", elem_id='ltx_parameters_accordion')
with parameters_accordion:
steps, sampler_index = ui_sections.create_sampler_and_steps_selection(None, "ltx", default_steps=50)
@@ -108,7 +108,7 @@ def create_ui(prompt, negative, styles, overrides, script_inputs, mp4_fps, mp4_i
dynamic_shift = gr.Checkbox(label='LTX dynamic shift', value=False, elem_id="ltx_dynamic_shift")
with gr.Row():
decode_timestep = gr.Slider(label='LTX decode timestep', minimum=0.0, maximum=1.0, step=0.01, value=0.05, elem_id="ltx_decode_timestep")
image_cond_noise_scale = gr.Slider(label='LTX image cond noise scale', minimum=0.0, maximum=1.0, step=0.005, value=0.025, elem_id="ltx_image_cond_noise_scale")
image_cond_noise_scale = gr.Slider(label='LTX image cond', minimum=0.0, maximum=1.0, step=0.005, value=0.025, elem_id="ltx_image_cond_noise_scale")
audio_accordion = gr.Accordion(open=False, label="Audio", elem_id='ltx_audio_accordion', visible=False)
with audio_accordion:
with gr.Row():
modules/ltx/ltx_util.py
+4 -4
View File
@@ -123,7 +123,7 @@ def ltx_scheduler_opts(sd_model, *, dynamic_shift=None, sampler_shift=None):
if orig_flow_shift is not None and hasattr(sd_model.scheduler.config, 'flow_shift'):
sd_model.scheduler.config.flow_shift = orig_flow_shift
sd_model.scheduler.register_to_config(flow_shift=orig_flow_shift)
log.debug(f'LTX: scheduler/opts restored dynamic_shift={orig_dynamic_shift} sampler_shift={orig_sampler_shift}')
# log.debug(f'LTX: scheduler/opts restored dynamic_shift={orig_dynamic_shift} sampler_shift={orig_sampler_shift}')
def _condition_cls(family: str):
@@ -201,9 +201,9 @@ def get_conditions(width, height, condition_strength, condition_images, conditio
return conditions
def get_prompts(prompt, negative, styles):
prompt = shared.prompt_styles.apply_styles_to_prompt(prompt, styles)
negative = shared.prompt_styles.apply_negative_styles_to_prompt(negative, styles)
def get_prompts(p):
prompt = shared.prompt_styles.apply_styles_to_prompt(p.prompt, p.styles)
negative = shared.prompt_styles.apply_negative_styles_to_prompt(p.negative_prompt, p.styles)
prompts, networks = extra_networks.parse_prompts([prompt])
prompt = prompts[0] if len(prompts) > 0 else prompt
return prompt, negative, networks
modules/video_models/video_save.py
+2 -2
View File
@@ -144,7 +144,7 @@ def add_audio_packets(container, audio_stream, audio: dict):
def add_audio_tensor(container, audio_stream, audio: torch.Tensor, sample_rate: int):
av = check_av()
if torch.is_tensor(audio):
audio = audio.detach().cpu().numpy()
audio = audio.detach().float().cpu().numpy()
if audio.ndim > 2:
audio = np.squeeze(audio)
if audio.ndim == 1:
@@ -156,7 +156,7 @@ def add_audio_tensor(container, audio_stream, audio: torch.Tensor, sample_rate:
if audio.dtype != np.int16:
audio = np.clip(audio, -1.0, 1.0)
audio = (audio * 32767.0).astype(np.int16)
audio_frame = av.AudioFrame.from_ndarray(np.ascontiguousarray(audio.T), format="s16", layout=layout)
audio_frame = av.AudioFrame.from_ndarray(audio, format="s16p", layout=layout)
audio_frame.sample_rate = sample_rate
add_audio_packets(container, audio_stream, {"sr": sample_rate, "layout": layout, "frames": [audio_frame]})
scripts/prompt_enhance/template.py
-1
View File
@@ -97,5 +97,4 @@ def set_template(
else:
chat_template = get_text_template(system, prompt, options, nsfw, has_system, has_prompt, has_processor, is_video, image)
print('HERE2', chat_template)
return chat_template
scripts/prompt_enhance_ext.py
-1
View File
@@ -389,7 +389,6 @@ class PromptEnhanceScript(scripts_manager.Script):
current_image = current_image.convert('RGB')
debug_log('Prompt enhance: Converted image to RGB mode')
print('HERE1', self.parent)
chat_template = set_template(
system=system,
prompt=prompt_text,