mirror of
https://github.com/modelscope/DiffSynth-Studio.git
synced 2026-03-18 22:08:13 +00:00
support ltx-2 training
This commit is contained in:
mi804
@@ -19,7 +19,12 @@ pipe = LTX2AudioVideoPipeline.from_pretrained(
|
||||
device="cuda",
|
||||
model_configs=[
|
||||
ModelConfig(model_id="google/gemma-3-12b-it-qat-q4_0-unquantized", origin_file_pattern="model-*.safetensors", **vram_config),
|
||||
ModelConfig(model_id="Lightricks/LTX-2", origin_file_pattern="ltx-2-19b-distilled.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="transformer_distilled.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="text_encoder_post_modules.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="video_vae_decoder.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="audio_vae_decoder.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="audio_vocoder.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="video_vae_encoder.safetensors", **vram_config),
|
||||
ModelConfig(model_id="Lightricks/LTX-2", origin_file_pattern="ltx-2-spatial-upscaler-x2-1.0.safetensors", **vram_config),
|
||||
],
|
||||
tokenizer_config=ModelConfig(model_id="google/gemma-3-12b-it-qat-q4_0-unquantized"),
|
||||
|
||||
@@ -19,7 +19,12 @@ pipe = LTX2AudioVideoPipeline.from_pretrained(
|
||||
device="cuda",
|
||||
model_configs=[
|
||||
ModelConfig(model_id="google/gemma-3-12b-it-qat-q4_0-unquantized", origin_file_pattern="model-*.safetensors", **vram_config),
|
||||
ModelConfig(model_id="Lightricks/LTX-2", origin_file_pattern="ltx-2-19b-dev.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="transformer.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="text_encoder_post_modules.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="video_vae_decoder.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="audio_vae_decoder.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="audio_vocoder.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="video_vae_encoder.safetensors", **vram_config),
|
||||
],
|
||||
tokenizer_config=ModelConfig(model_id="google/gemma-3-12b-it-qat-q4_0-unquantized"),
|
||||
)
|
||||
|
||||
@@ -19,7 +19,12 @@ pipe = LTX2AudioVideoPipeline.from_pretrained(
|
||||
device="cuda",
|
||||
model_configs=[
|
||||
ModelConfig(model_id="google/gemma-3-12b-it-qat-q4_0-unquantized", origin_file_pattern="model-*.safetensors", **vram_config),
|
||||
ModelConfig(model_id="Lightricks/LTX-2", origin_file_pattern="ltx-2-19b-dev.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="transformer.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="text_encoder_post_modules.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="video_vae_decoder.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="audio_vae_decoder.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="audio_vocoder.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="video_vae_encoder.safetensors", **vram_config),
|
||||
ModelConfig(model_id="Lightricks/LTX-2", origin_file_pattern="ltx-2-spatial-upscaler-x2-1.0.safetensors", **vram_config),
|
||||
],
|
||||
tokenizer_config=ModelConfig(model_id="google/gemma-3-12b-it-qat-q4_0-unquantized"),
|
||||
|
||||
@@ -17,7 +17,11 @@ pipe = LTX2AudioVideoPipeline.from_pretrained(
|
||||
device="cuda",
|
||||
model_configs=[
|
||||
ModelConfig(model_id="google/gemma-3-12b-it-qat-q4_0-unquantized", origin_file_pattern="model-*.safetensors", **vram_config),
|
||||
ModelConfig(model_id="Lightricks/LTX-2", origin_file_pattern="ltx-2-19b-dev.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="transformer.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="text_encoder_post_modules.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="video_vae_decoder.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="audio_vae_decoder.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="audio_vocoder.safetensors", **vram_config),
|
||||
ModelConfig(model_id="Lightricks/LTX-2", origin_file_pattern="ltx-2-spatial-upscaler-x2-1.0.safetensors", **vram_config),
|
||||
],
|
||||
tokenizer_config=ModelConfig(model_id="google/gemma-3-12b-it-qat-q4_0-unquantized"),
|
||||
|
||||
@@ -17,7 +17,11 @@ pipe = LTX2AudioVideoPipeline.from_pretrained(
|
||||
device="cuda",
|
||||
model_configs=[
|
||||
ModelConfig(model_id="google/gemma-3-12b-it-qat-q4_0-unquantized", origin_file_pattern="model-*.safetensors", **vram_config),
|
||||
ModelConfig(model_id="Lightricks/LTX-2", origin_file_pattern="ltx-2-19b-dev.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="transformer.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="text_encoder_post_modules.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="video_vae_decoder.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="audio_vae_decoder.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="audio_vocoder.safetensors", **vram_config),
|
||||
ModelConfig(model_id="Lightricks/LTX-2", origin_file_pattern="ltx-2-spatial-upscaler-x2-1.0.safetensors", **vram_config),
|
||||
],
|
||||
tokenizer_config=ModelConfig(model_id="google/gemma-3-12b-it-qat-q4_0-unquantized"),
|
||||
|
||||
@@ -17,7 +17,11 @@ pipe = LTX2AudioVideoPipeline.from_pretrained(
|
||||
device="cuda",
|
||||
model_configs=[
|
||||
ModelConfig(model_id="google/gemma-3-12b-it-qat-q4_0-unquantized", origin_file_pattern="model-*.safetensors", **vram_config),
|
||||
ModelConfig(model_id="Lightricks/LTX-2", origin_file_pattern="ltx-2-19b-dev.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="transformer.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="text_encoder_post_modules.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="video_vae_decoder.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="audio_vae_decoder.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="audio_vocoder.safetensors", **vram_config),
|
||||
ModelConfig(model_id="Lightricks/LTX-2", origin_file_pattern="ltx-2-spatial-upscaler-x2-1.0.safetensors", **vram_config),
|
||||
],
|
||||
tokenizer_config=ModelConfig(model_id="google/gemma-3-12b-it-qat-q4_0-unquantized"),
|
||||
|
||||
@@ -17,7 +17,11 @@ pipe = LTX2AudioVideoPipeline.from_pretrained(
|
||||
device="cuda",
|
||||
model_configs=[
|
||||
ModelConfig(model_id="google/gemma-3-12b-it-qat-q4_0-unquantized", origin_file_pattern="model-*.safetensors", **vram_config),
|
||||
ModelConfig(model_id="Lightricks/LTX-2", origin_file_pattern="ltx-2-19b-dev.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="transformer.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="text_encoder_post_modules.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="video_vae_decoder.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="audio_vae_decoder.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="audio_vocoder.safetensors", **vram_config),
|
||||
ModelConfig(model_id="Lightricks/LTX-2", origin_file_pattern="ltx-2-spatial-upscaler-x2-1.0.safetensors", **vram_config),
|
||||
],
|
||||
tokenizer_config=ModelConfig(model_id="google/gemma-3-12b-it-qat-q4_0-unquantized"),
|
||||
|
||||
@@ -17,7 +17,11 @@ pipe = LTX2AudioVideoPipeline.from_pretrained(
|
||||
device="cuda",
|
||||
model_configs=[
|
||||
ModelConfig(model_id="google/gemma-3-12b-it-qat-q4_0-unquantized", origin_file_pattern="model-*.safetensors", **vram_config),
|
||||
ModelConfig(model_id="Lightricks/LTX-2", origin_file_pattern="ltx-2-19b-dev.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="transformer.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="text_encoder_post_modules.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="video_vae_decoder.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="audio_vae_decoder.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="audio_vocoder.safetensors", **vram_config),
|
||||
ModelConfig(model_id="Lightricks/LTX-2", origin_file_pattern="ltx-2-spatial-upscaler-x2-1.0.safetensors", **vram_config),
|
||||
],
|
||||
tokenizer_config=ModelConfig(model_id="google/gemma-3-12b-it-qat-q4_0-unquantized"),
|
||||
|
||||
@@ -17,7 +17,11 @@ pipe = LTX2AudioVideoPipeline.from_pretrained(
|
||||
device="cuda",
|
||||
model_configs=[
|
||||
ModelConfig(model_id="google/gemma-3-12b-it-qat-q4_0-unquantized", origin_file_pattern="model-*.safetensors", **vram_config),
|
||||
ModelConfig(model_id="Lightricks/LTX-2", origin_file_pattern="ltx-2-19b-dev.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="transformer.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="text_encoder_post_modules.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="video_vae_decoder.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="audio_vae_decoder.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="audio_vocoder.safetensors", **vram_config),
|
||||
ModelConfig(model_id="Lightricks/LTX-2", origin_file_pattern="ltx-2-spatial-upscaler-x2-1.0.safetensors", **vram_config),
|
||||
],
|
||||
tokenizer_config=ModelConfig(model_id="google/gemma-3-12b-it-qat-q4_0-unquantized"),
|
||||
|
||||
@@ -17,7 +17,11 @@ pipe = LTX2AudioVideoPipeline.from_pretrained(
|
||||
device="cuda",
|
||||
model_configs=[
|
||||
ModelConfig(model_id="google/gemma-3-12b-it-qat-q4_0-unquantized", origin_file_pattern="model-*.safetensors", **vram_config),
|
||||
ModelConfig(model_id="Lightricks/LTX-2", origin_file_pattern="ltx-2-19b-dev.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="transformer.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="text_encoder_post_modules.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="video_vae_decoder.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="audio_vae_decoder.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="audio_vocoder.safetensors", **vram_config),
|
||||
ModelConfig(model_id="Lightricks/LTX-2", origin_file_pattern="ltx-2-spatial-upscaler-x2-1.0.safetensors", **vram_config),
|
||||
],
|
||||
tokenizer_config=ModelConfig(model_id="google/gemma-3-12b-it-qat-q4_0-unquantized"),
|
||||
|
||||
@@ -17,7 +17,11 @@ pipe = LTX2AudioVideoPipeline.from_pretrained(
|
||||
device="cuda",
|
||||
model_configs=[
|
||||
ModelConfig(model_id="google/gemma-3-12b-it-qat-q4_0-unquantized", origin_file_pattern="model-*.safetensors", **vram_config),
|
||||
ModelConfig(model_id="Lightricks/LTX-2", origin_file_pattern="ltx-2-19b-distilled.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="transformer_distilled.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="text_encoder_post_modules.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="video_vae_decoder.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="audio_vae_decoder.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="audio_vocoder.safetensors", **vram_config),
|
||||
ModelConfig(model_id="Lightricks/LTX-2", origin_file_pattern="ltx-2-spatial-upscaler-x2-1.0.safetensors", **vram_config),
|
||||
],
|
||||
tokenizer_config=ModelConfig(model_id="google/gemma-3-12b-it-qat-q4_0-unquantized"),
|
||||
|
||||
@@ -17,7 +17,11 @@ pipe = LTX2AudioVideoPipeline.from_pretrained(
|
||||
device="cuda",
|
||||
model_configs=[
|
||||
ModelConfig(model_id="google/gemma-3-12b-it-qat-q4_0-unquantized", origin_file_pattern="model-*.safetensors", **vram_config),
|
||||
ModelConfig(model_id="Lightricks/LTX-2", origin_file_pattern="ltx-2-19b-dev.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="transformer.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="text_encoder_post_modules.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="video_vae_decoder.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="audio_vae_decoder.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="audio_vocoder.safetensors", **vram_config),
|
||||
],
|
||||
tokenizer_config=ModelConfig(model_id="google/gemma-3-12b-it-qat-q4_0-unquantized"),
|
||||
)
|
||||
@@ -40,3 +44,12 @@ write_video_audio_ltx2(
|
||||
fps=24,
|
||||
audio_sample_rate=24000,
|
||||
)
|
||||
|
||||
|
||||
# ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="transformer.safetensors", **vram_config),
|
||||
# ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="text_encoder_post_modules.safetensors", **vram_config),
|
||||
# ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="video_vae_encoder.safetensors", **vram_config),
|
||||
# ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="video_vae_decoder.safetensors", **vram_config),
|
||||
# ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="audio_vae_decoder.safetensors", **vram_config),
|
||||
# ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="audio_vae_encoder.safetensors", **vram_config),
|
||||
# ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="audio_vocoder.safetensors", **vram_config),
|
||||
@@ -17,7 +17,11 @@ pipe = LTX2AudioVideoPipeline.from_pretrained(
|
||||
device="cuda",
|
||||
model_configs=[
|
||||
ModelConfig(model_id="google/gemma-3-12b-it-qat-q4_0-unquantized", origin_file_pattern="model-*.safetensors", **vram_config),
|
||||
ModelConfig(model_id="Lightricks/LTX-2", origin_file_pattern="ltx-2-19b-dev.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="transformer.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="text_encoder_post_modules.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="video_vae_decoder.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="audio_vae_decoder.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="audio_vocoder.safetensors", **vram_config),
|
||||
ModelConfig(model_id="Lightricks/LTX-2", origin_file_pattern="ltx-2-spatial-upscaler-x2-1.0.safetensors", **vram_config),
|
||||
],
|
||||
tokenizer_config=ModelConfig(model_id="google/gemma-3-12b-it-qat-q4_0-unquantized"),
|
||||
|
||||
@@ -19,7 +19,12 @@ pipe = LTX2AudioVideoPipeline.from_pretrained(
|
||||
device="cuda",
|
||||
model_configs=[
|
||||
ModelConfig(model_id="google/gemma-3-12b-it-qat-q4_0-unquantized", origin_file_pattern="model-*.safetensors", **vram_config),
|
||||
ModelConfig(model_id="Lightricks/LTX-2", origin_file_pattern="ltx-2-19b-distilled.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="transformer_distilled.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="text_encoder_post_modules.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="video_vae_decoder.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="audio_vae_decoder.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="audio_vocoder.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="video_vae_encoder.safetensors", **vram_config),
|
||||
ModelConfig(model_id="Lightricks/LTX-2", origin_file_pattern="ltx-2-spatial-upscaler-x2-1.0.safetensors", **vram_config),
|
||||
],
|
||||
tokenizer_config=ModelConfig(model_id="google/gemma-3-12b-it-qat-q4_0-unquantized"),
|
||||
|
||||
@@ -19,7 +19,12 @@ pipe = LTX2AudioVideoPipeline.from_pretrained(
|
||||
device="cuda",
|
||||
model_configs=[
|
||||
ModelConfig(model_id="google/gemma-3-12b-it-qat-q4_0-unquantized", origin_file_pattern="model-*.safetensors", **vram_config),
|
||||
ModelConfig(model_id="Lightricks/LTX-2", origin_file_pattern="ltx-2-19b-dev.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="transformer.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="text_encoder_post_modules.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="video_vae_decoder.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="audio_vae_decoder.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="audio_vocoder.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="video_vae_encoder.safetensors", **vram_config),
|
||||
],
|
||||
tokenizer_config=ModelConfig(model_id="google/gemma-3-12b-it-qat-q4_0-unquantized"),
|
||||
vram_limit=torch.cuda.mem_get_info("cuda")[1] / (1024 ** 3) - 0.5,
|
||||
|
||||
@@ -19,7 +19,12 @@ pipe = LTX2AudioVideoPipeline.from_pretrained(
|
||||
device="cuda",
|
||||
model_configs=[
|
||||
ModelConfig(model_id="google/gemma-3-12b-it-qat-q4_0-unquantized", origin_file_pattern="model-*.safetensors", **vram_config),
|
||||
ModelConfig(model_id="Lightricks/LTX-2", origin_file_pattern="ltx-2-19b-dev.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="transformer.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="text_encoder_post_modules.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="video_vae_decoder.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="audio_vae_decoder.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="audio_vocoder.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="video_vae_encoder.safetensors", **vram_config),
|
||||
ModelConfig(model_id="Lightricks/LTX-2", origin_file_pattern="ltx-2-spatial-upscaler-x2-1.0.safetensors", **vram_config),
|
||||
],
|
||||
tokenizer_config=ModelConfig(model_id="google/gemma-3-12b-it-qat-q4_0-unquantized"),
|
||||
|
||||
@@ -17,7 +17,11 @@ pipe = LTX2AudioVideoPipeline.from_pretrained(
|
||||
device="cuda",
|
||||
model_configs=[
|
||||
ModelConfig(model_id="google/gemma-3-12b-it-qat-q4_0-unquantized", origin_file_pattern="model-*.safetensors", **vram_config),
|
||||
ModelConfig(model_id="Lightricks/LTX-2", origin_file_pattern="ltx-2-19b-dev.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="transformer.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="text_encoder_post_modules.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="video_vae_decoder.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="audio_vae_decoder.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="audio_vocoder.safetensors", **vram_config),
|
||||
ModelConfig(model_id="Lightricks/LTX-2", origin_file_pattern="ltx-2-spatial-upscaler-x2-1.0.safetensors", **vram_config),
|
||||
],
|
||||
tokenizer_config=ModelConfig(model_id="google/gemma-3-12b-it-qat-q4_0-unquantized"),
|
||||
|
||||
@@ -17,7 +17,11 @@ pipe = LTX2AudioVideoPipeline.from_pretrained(
|
||||
device="cuda",
|
||||
model_configs=[
|
||||
ModelConfig(model_id="google/gemma-3-12b-it-qat-q4_0-unquantized", origin_file_pattern="model-*.safetensors", **vram_config),
|
||||
ModelConfig(model_id="Lightricks/LTX-2", origin_file_pattern="ltx-2-19b-dev.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="transformer.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="text_encoder_post_modules.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="video_vae_decoder.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="audio_vae_decoder.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="audio_vocoder.safetensors", **vram_config),
|
||||
ModelConfig(model_id="Lightricks/LTX-2", origin_file_pattern="ltx-2-spatial-upscaler-x2-1.0.safetensors", **vram_config),
|
||||
],
|
||||
tokenizer_config=ModelConfig(model_id="google/gemma-3-12b-it-qat-q4_0-unquantized"),
|
||||
|
||||
@@ -17,7 +17,11 @@ pipe = LTX2AudioVideoPipeline.from_pretrained(
|
||||
device="cuda",
|
||||
model_configs=[
|
||||
ModelConfig(model_id="google/gemma-3-12b-it-qat-q4_0-unquantized", origin_file_pattern="model-*.safetensors", **vram_config),
|
||||
ModelConfig(model_id="Lightricks/LTX-2", origin_file_pattern="ltx-2-19b-dev.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="transformer.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="text_encoder_post_modules.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="video_vae_decoder.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="audio_vae_decoder.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="audio_vocoder.safetensors", **vram_config),
|
||||
ModelConfig(model_id="Lightricks/LTX-2", origin_file_pattern="ltx-2-spatial-upscaler-x2-1.0.safetensors", **vram_config),
|
||||
],
|
||||
tokenizer_config=ModelConfig(model_id="google/gemma-3-12b-it-qat-q4_0-unquantized"),
|
||||
|
||||
@@ -17,7 +17,11 @@ pipe = LTX2AudioVideoPipeline.from_pretrained(
|
||||
device="cuda",
|
||||
model_configs=[
|
||||
ModelConfig(model_id="google/gemma-3-12b-it-qat-q4_0-unquantized", origin_file_pattern="model-*.safetensors", **vram_config),
|
||||
ModelConfig(model_id="Lightricks/LTX-2", origin_file_pattern="ltx-2-19b-dev.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="transformer.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="text_encoder_post_modules.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="video_vae_decoder.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="audio_vae_decoder.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="audio_vocoder.safetensors", **vram_config),
|
||||
ModelConfig(model_id="Lightricks/LTX-2", origin_file_pattern="ltx-2-spatial-upscaler-x2-1.0.safetensors", **vram_config),
|
||||
],
|
||||
tokenizer_config=ModelConfig(model_id="google/gemma-3-12b-it-qat-q4_0-unquantized"),
|
||||
|
||||
@@ -17,7 +17,11 @@ pipe = LTX2AudioVideoPipeline.from_pretrained(
|
||||
device="cuda",
|
||||
model_configs=[
|
||||
ModelConfig(model_id="google/gemma-3-12b-it-qat-q4_0-unquantized", origin_file_pattern="model-*.safetensors", **vram_config),
|
||||
ModelConfig(model_id="Lightricks/LTX-2", origin_file_pattern="ltx-2-19b-dev.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="transformer.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="text_encoder_post_modules.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="video_vae_decoder.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="audio_vae_decoder.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="audio_vocoder.safetensors", **vram_config),
|
||||
ModelConfig(model_id="Lightricks/LTX-2", origin_file_pattern="ltx-2-spatial-upscaler-x2-1.0.safetensors", **vram_config),
|
||||
],
|
||||
tokenizer_config=ModelConfig(model_id="google/gemma-3-12b-it-qat-q4_0-unquantized"),
|
||||
|
||||
@@ -17,7 +17,11 @@ pipe = LTX2AudioVideoPipeline.from_pretrained(
|
||||
device="cuda",
|
||||
model_configs=[
|
||||
ModelConfig(model_id="google/gemma-3-12b-it-qat-q4_0-unquantized", origin_file_pattern="model-*.safetensors", **vram_config),
|
||||
ModelConfig(model_id="Lightricks/LTX-2", origin_file_pattern="ltx-2-19b-dev.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="transformer.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="text_encoder_post_modules.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="video_vae_decoder.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="audio_vae_decoder.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="audio_vocoder.safetensors", **vram_config),
|
||||
ModelConfig(model_id="Lightricks/LTX-2", origin_file_pattern="ltx-2-spatial-upscaler-x2-1.0.safetensors", **vram_config),
|
||||
],
|
||||
tokenizer_config=ModelConfig(model_id="google/gemma-3-12b-it-qat-q4_0-unquantized"),
|
||||
|
||||
@@ -17,7 +17,11 @@ pipe = LTX2AudioVideoPipeline.from_pretrained(
|
||||
device="cuda",
|
||||
model_configs=[
|
||||
ModelConfig(model_id="google/gemma-3-12b-it-qat-q4_0-unquantized", origin_file_pattern="model-*.safetensors", **vram_config),
|
||||
ModelConfig(model_id="Lightricks/LTX-2", origin_file_pattern="ltx-2-19b-dev.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="transformer.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="text_encoder_post_modules.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="video_vae_decoder.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="audio_vae_decoder.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="audio_vocoder.safetensors", **vram_config),
|
||||
ModelConfig(model_id="Lightricks/LTX-2", origin_file_pattern="ltx-2-spatial-upscaler-x2-1.0.safetensors", **vram_config),
|
||||
],
|
||||
tokenizer_config=ModelConfig(model_id="google/gemma-3-12b-it-qat-q4_0-unquantized"),
|
||||
|
||||
@@ -17,7 +17,11 @@ pipe = LTX2AudioVideoPipeline.from_pretrained(
|
||||
device="cuda",
|
||||
model_configs=[
|
||||
ModelConfig(model_id="google/gemma-3-12b-it-qat-q4_0-unquantized", origin_file_pattern="model-*.safetensors", **vram_config),
|
||||
ModelConfig(model_id="Lightricks/LTX-2", origin_file_pattern="ltx-2-19b-distilled.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="transformer_distilled.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="text_encoder_post_modules.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="video_vae_decoder.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="audio_vae_decoder.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="audio_vocoder.safetensors", **vram_config),
|
||||
ModelConfig(model_id="Lightricks/LTX-2", origin_file_pattern="ltx-2-spatial-upscaler-x2-1.0.safetensors", **vram_config),
|
||||
],
|
||||
tokenizer_config=ModelConfig(model_id="google/gemma-3-12b-it-qat-q4_0-unquantized"),
|
||||
|
||||
@@ -17,7 +17,11 @@ pipe = LTX2AudioVideoPipeline.from_pretrained(
|
||||
device="cuda",
|
||||
model_configs=[
|
||||
ModelConfig(model_id="google/gemma-3-12b-it-qat-q4_0-unquantized", origin_file_pattern="model-*.safetensors", **vram_config),
|
||||
ModelConfig(model_id="Lightricks/LTX-2", origin_file_pattern="ltx-2-19b-dev.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="transformer.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="text_encoder_post_modules.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="video_vae_decoder.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="audio_vae_decoder.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="audio_vocoder.safetensors", **vram_config),
|
||||
],
|
||||
tokenizer_config=ModelConfig(model_id="google/gemma-3-12b-it-qat-q4_0-unquantized"),
|
||||
vram_limit=torch.cuda.mem_get_info("cuda")[1] / (1024 ** 3) - 0.5,
|
||||
|
||||
@@ -17,7 +17,11 @@ pipe = LTX2AudioVideoPipeline.from_pretrained(
|
||||
device="cuda",
|
||||
model_configs=[
|
||||
ModelConfig(model_id="google/gemma-3-12b-it-qat-q4_0-unquantized", origin_file_pattern="model-*.safetensors", **vram_config),
|
||||
ModelConfig(model_id="Lightricks/LTX-2", origin_file_pattern="ltx-2-19b-dev.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="transformer.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="text_encoder_post_modules.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="video_vae_decoder.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="audio_vae_decoder.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="audio_vocoder.safetensors", **vram_config),
|
||||
ModelConfig(model_id="Lightricks/LTX-2", origin_file_pattern="ltx-2-spatial-upscaler-x2-1.0.safetensors", **vram_config),
|
||||
],
|
||||
tokenizer_config=ModelConfig(model_id="google/gemma-3-12b-it-qat-q4_0-unquantized"),
|
||||
|
||||
35
examples/ltx2/model_training/full/LTX-2-T2AV-splited.sh
Normal file
35
examples/ltx2/model_training/full/LTX-2-T2AV-splited.sh
Normal file
@@ -0,0 +1,35 @@
|
||||
# Splited Training
|
||||
accelerate launch examples/ltx2/model_training/train.py \
|
||||
--dataset_base_path data/example_video_dataset/ltx2 \
|
||||
--dataset_metadata_path data/example_video_dataset/ltx2_t2av.csv \
|
||||
--data_file_keys "video,input_audio" \
|
||||
--extra_inputs "input_audio" \
|
||||
--height 512 \
|
||||
--width 768 \
|
||||
--num_frames 49 \
|
||||
--dataset_repeat 1 \
|
||||
--model_id_with_origin_paths "DiffSynth-Studio/LTX-2-Repackage:text_encoder_post_modules.safetensors,DiffSynth-Studio/LTX-2-Repackage:video_vae_encoder.safetensors,DiffSynth-Studio/LTX-2-Repackage:audio_vae_encoder.safetensors,google/gemma-3-12b-it-qat-q4_0-unquantized:model-*.safetensors" \
|
||||
--learning_rate 1e-4 \
|
||||
--num_epochs 5 \
|
||||
--remove_prefix_in_ckpt "pipe.dit." \
|
||||
--output_path "./models/train/LTX2-T2AV-full-splited-cache" \
|
||||
--trainable_models "dit" \
|
||||
--use_gradient_checkpointing \
|
||||
--task "sft:data_process"
|
||||
|
||||
accelerate launch examples/ltx2/model_training/train.py \
|
||||
--dataset_base_path ./models/train/LTX2-T2AV-full-splited-cache \
|
||||
--data_file_keys "video,input_audio" \
|
||||
--extra_inputs "input_audio" \
|
||||
--height 512 \
|
||||
--width 768 \
|
||||
--num_frames 49 \
|
||||
--dataset_repeat 100 \
|
||||
--model_id_with_origin_paths "DiffSynth-Studio/LTX-2-Repackage:transformer.safetensors" \
|
||||
--learning_rate 1e-4 \
|
||||
--num_epochs 5 \
|
||||
--remove_prefix_in_ckpt "pipe.dit." \
|
||||
--output_path "./models/train/LTX2-T2AV-full" \
|
||||
--trainable_models "dit" \
|
||||
--use_gradient_checkpointing \
|
||||
--task "sft:train"
|
||||
56
examples/ltx2/model_training/lora/LTX-2-T2AV-noaudio.sh
Normal file
56
examples/ltx2/model_training/lora/LTX-2-T2AV-noaudio.sh
Normal file
@@ -0,0 +1,56 @@
|
||||
# single stage training
|
||||
# accelerate launch examples/ltx2/model_training/train.py \
|
||||
# --dataset_base_path data/example_video_dataset/ltx2 \
|
||||
# --dataset_metadata_path data/example_video_dataset/ltx2_t2v.csv \
|
||||
# --height 256 \
|
||||
# --width 384 \
|
||||
# --num_frames 25\
|
||||
# --dataset_repeat 100 \
|
||||
# --model_id_with_origin_paths "DiffSynth-Studio/LTX-2-Repackage:transformer.safetensors,DiffSynth-Studio/LTX-2-Repackage:text_encoder_post_modules.safetensors,DiffSynth-Studio/LTX-2-Repackage:video_vae_encoder.safetensors,DiffSynth-Studio/LTX-2-Repackage:audio_vae_encoder.safetensors,google/gemma-3-12b-it-qat-q4_0-unquantized:model-*.safetensors" \
|
||||
# --learning_rate 1e-4 \
|
||||
# --num_epochs 5 \
|
||||
# --remove_prefix_in_ckpt "pipe.dit." \
|
||||
# --output_path "./models/train/LTX2-T2AV-noaudio_lora" \
|
||||
# --lora_base_model "dit" \
|
||||
# --lora_target_modules "to_k,to_q,to_v,to_out.0" \
|
||||
# --lora_rank 32 \
|
||||
# --use_gradient_checkpointing \
|
||||
# --find_unused_parameters
|
||||
|
||||
|
||||
# Splited Training
|
||||
accelerate launch examples/ltx2/model_training/train.py \
|
||||
--dataset_base_path data/example_video_dataset/ltx2 \
|
||||
--dataset_metadata_path data/example_video_dataset/ltx2_t2av.csv \
|
||||
--height 256 \
|
||||
--width 384 \
|
||||
--num_frames 49\
|
||||
--dataset_repeat 1 \
|
||||
--model_id_with_origin_paths "DiffSynth-Studio/LTX-2-Repackage:text_encoder_post_modules.safetensors,DiffSynth-Studio/LTX-2-Repackage:video_vae_encoder.safetensors,DiffSynth-Studio/LTX-2-Repackage:audio_vae_encoder.safetensors,google/gemma-3-12b-it-qat-q4_0-unquantized:model-*.safetensors" \
|
||||
--learning_rate 1e-4 \
|
||||
--num_epochs 5 \
|
||||
--remove_prefix_in_ckpt "pipe.dit." \
|
||||
--output_path "./models/train/LTX2-T2AV-noaudio_lora-splited-cache" \
|
||||
--lora_base_model "dit" \
|
||||
--lora_target_modules "to_k,to_q,to_v,to_out.0" \
|
||||
--lora_rank 32 \
|
||||
--use_gradient_checkpointing \
|
||||
--task "sft:data_process"
|
||||
|
||||
|
||||
accelerate launch examples/ltx2/model_training/train.py \
|
||||
--dataset_base_path ./models/train/LTX2-T2AV-noaudio_lora-splited-cache \
|
||||
--height 256 \
|
||||
--width 384 \
|
||||
--num_frames 49\
|
||||
--dataset_repeat 100 \
|
||||
--model_id_with_origin_paths "DiffSynth-Studio/LTX-2-Repackage:transformer.safetensors" \
|
||||
--learning_rate 1e-4 \
|
||||
--num_epochs 5 \
|
||||
--remove_prefix_in_ckpt "pipe.dit." \
|
||||
--output_path "./models/train/LTX2-T2AV-noaudio_lora" \
|
||||
--lora_base_model "dit" \
|
||||
--lora_target_modules "to_k,to_q,to_v,to_out.0" \
|
||||
--lora_rank 32 \
|
||||
--use_gradient_checkpointing \
|
||||
--task "sft:train"
|
||||
40
examples/ltx2/model_training/lora/LTX-2-T2AV-splited.sh
Normal file
40
examples/ltx2/model_training/lora/LTX-2-T2AV-splited.sh
Normal file
@@ -0,0 +1,40 @@
|
||||
# Splited Training
|
||||
accelerate launch examples/ltx2/model_training/train.py \
|
||||
--dataset_base_path data/example_video_dataset/ltx2 \
|
||||
--dataset_metadata_path data/example_video_dataset/ltx2_t2av.csv \
|
||||
--data_file_keys "video,input_audio" \
|
||||
--extra_inputs "input_audio" \
|
||||
--height 512 \
|
||||
--width 768 \
|
||||
--num_frames 49 \
|
||||
--dataset_repeat 1 \
|
||||
--model_id_with_origin_paths "DiffSynth-Studio/LTX-2-Repackage:text_encoder_post_modules.safetensors,DiffSynth-Studio/LTX-2-Repackage:video_vae_encoder.safetensors,DiffSynth-Studio/LTX-2-Repackage:audio_vae_encoder.safetensors,google/gemma-3-12b-it-qat-q4_0-unquantized:model-*.safetensors" \
|
||||
--learning_rate 1e-4 \
|
||||
--num_epochs 5 \
|
||||
--remove_prefix_in_ckpt "pipe.dit." \
|
||||
--output_path "./models/train/LTX2-T2AV_lora-splited-cache" \
|
||||
--lora_base_model "dit" \
|
||||
--lora_target_modules "to_k,to_q,to_v,to_out.0" \
|
||||
--lora_rank 32 \
|
||||
--use_gradient_checkpointing \
|
||||
--task "sft:data_process"
|
||||
|
||||
|
||||
accelerate launch examples/ltx2/model_training/train.py \
|
||||
--dataset_base_path ./models/train/LTX2-T2AV_lora-splited-cache \
|
||||
--data_file_keys "video,input_audio" \
|
||||
--extra_inputs "input_audio" \
|
||||
--height 512 \
|
||||
--width 768 \
|
||||
--num_frames 49 \
|
||||
--dataset_repeat 100 \
|
||||
--model_id_with_origin_paths "DiffSynth-Studio/LTX-2-Repackage:transformer.safetensors" \
|
||||
--learning_rate 1e-4 \
|
||||
--num_epochs 5 \
|
||||
--remove_prefix_in_ckpt "pipe.dit." \
|
||||
--output_path "./models/train/LTX2-T2AV_lora" \
|
||||
--lora_base_model "dit" \
|
||||
--lora_target_modules "to_k,to_q,to_v,to_out.0" \
|
||||
--lora_rank 32 \
|
||||
--use_gradient_checkpointing \
|
||||
--task "sft:train"
|
||||
19
examples/ltx2/model_training/lora/LTX-2-T2AV.sh
Normal file
19
examples/ltx2/model_training/lora/LTX-2-T2AV.sh
Normal file
@@ -0,0 +1,19 @@
|
||||
accelerate launch examples/ltx2/model_training/train.py \
|
||||
--dataset_base_path data/example_video_dataset/ltx2 \
|
||||
--dataset_metadata_path data/example_video_dataset/ltx2_t2av.csv \
|
||||
--data_file_keys "video,input_audio" \
|
||||
--extra_inputs "input_audio" \
|
||||
--height 256 \
|
||||
--width 384 \
|
||||
--num_frames 25\
|
||||
--dataset_repeat 100 \
|
||||
--model_id_with_origin_paths "DiffSynth-Studio/LTX-2-Repackage:transformer.safetensors,DiffSynth-Studio/LTX-2-Repackage:text_encoder_post_modules.safetensors,DiffSynth-Studio/LTX-2-Repackage:video_vae_encoder.safetensors,DiffSynth-Studio/LTX-2-Repackage:audio_vae_encoder.safetensors,google/gemma-3-12b-it-qat-q4_0-unquantized:model-*.safetensors" \
|
||||
--learning_rate 1e-4 \
|
||||
--num_epochs 5 \
|
||||
--remove_prefix_in_ckpt "pipe.dit." \
|
||||
--output_path "./models/train/LTX2-T2AV_lora" \
|
||||
--lora_base_model "dit" \
|
||||
--lora_target_modules "to_k,to_q,to_v,to_out.0" \
|
||||
--lora_rank 32 \
|
||||
--use_gradient_checkpointing \
|
||||
--find_unused_parameters
|
||||
162
examples/ltx2/model_training/train.py
Normal file
162
examples/ltx2/model_training/train.py
Normal file
@@ -0,0 +1,162 @@
|
||||
import torch, os, argparse, accelerate, warnings
|
||||
from diffsynth.core import UnifiedDataset
|
||||
from diffsynth.core.data.operators import LoadAudioWithTorchaudio, ToAbsolutePath
|
||||
from diffsynth.pipelines.wan_video import WanVideoPipeline, ModelConfig
|
||||
from diffsynth.pipelines.ltx2_audio_video import LTX2AudioVideoPipeline, ModelConfig
|
||||
from diffsynth.diffusion import *
|
||||
os.environ["TOKENIZERS_PARALLELISM"] = "false"
|
||||
|
||||
|
||||
class LTX2TrainingModule(DiffusionTrainingModule):
|
||||
def __init__(
|
||||
self,
|
||||
model_paths=None, model_id_with_origin_paths=None,
|
||||
tokenizer_path=None,
|
||||
trainable_models=None,
|
||||
lora_base_model=None, lora_target_modules="", lora_rank=32, lora_checkpoint=None,
|
||||
preset_lora_path=None, preset_lora_model=None,
|
||||
use_gradient_checkpointing=True,
|
||||
use_gradient_checkpointing_offload=False,
|
||||
extra_inputs=None,
|
||||
fp8_models=None,
|
||||
offload_models=None,
|
||||
device="cpu",
|
||||
task="sft",
|
||||
):
|
||||
super().__init__()
|
||||
# Warning
|
||||
if not use_gradient_checkpointing:
|
||||
warnings.warn("Gradient checkpointing is detected as disabled. To prevent out-of-memory errors, the training framework will forcibly enable gradient checkpointing.")
|
||||
use_gradient_checkpointing = True
|
||||
|
||||
# Load models
|
||||
model_configs = self.parse_model_configs(model_paths, model_id_with_origin_paths, fp8_models=fp8_models, offload_models=offload_models, device=device)
|
||||
tokenizer_config = ModelConfig(model_id="google/gemma-3-12b-it-qat-q4_0-unquantized") if tokenizer_path is None else ModelConfig(tokenizer_path)
|
||||
self.pipe = LTX2AudioVideoPipeline.from_pretrained(torch_dtype=torch.bfloat16, device=device, model_configs=model_configs, tokenizer_config=tokenizer_config)
|
||||
self.pipe = self.split_pipeline_units(task, self.pipe, trainable_models, lora_base_model)
|
||||
# Training mode
|
||||
self.switch_pipe_to_training_mode(
|
||||
self.pipe, trainable_models,
|
||||
lora_base_model, lora_target_modules, lora_rank, lora_checkpoint,
|
||||
preset_lora_path, preset_lora_model,
|
||||
task=task,
|
||||
)
|
||||
|
||||
# Store other configs
|
||||
self.use_gradient_checkpointing = use_gradient_checkpointing
|
||||
self.use_gradient_checkpointing_offload = use_gradient_checkpointing_offload
|
||||
self.extra_inputs = extra_inputs.split(",") if extra_inputs is not None else []
|
||||
self.fp8_models = fp8_models
|
||||
self.task = task
|
||||
self.task_to_loss = {
|
||||
"sft:data_process": lambda pipe, *args: args,
|
||||
"sft": lambda pipe, inputs_shared, inputs_posi, inputs_nega: FlowMatchSFTAudioVideoLoss(pipe, **inputs_shared, **inputs_posi),
|
||||
"sft:train": lambda pipe, inputs_shared, inputs_posi, inputs_nega: FlowMatchSFTAudioVideoLoss(pipe, **inputs_shared, **inputs_posi),
|
||||
}
|
||||
|
||||
def parse_extra_inputs(self, data, extra_inputs, inputs_shared):
|
||||
for extra_input in extra_inputs:
|
||||
inputs_shared[extra_input] = data[extra_input]
|
||||
return inputs_shared
|
||||
|
||||
def get_pipeline_inputs(self, data):
|
||||
inputs_posi = {"prompt": data["prompt"]}
|
||||
inputs_nega = {}
|
||||
inputs_shared = {
|
||||
# Assume you are using this pipeline for inference,
|
||||
# please fill in the input parameters.
|
||||
"input_video": data["video"],
|
||||
"height": data["video"][0].size[1],
|
||||
"width": data["video"][0].size[0],
|
||||
"num_frames": len(data["video"]),
|
||||
# Please do not modify the following parameters
|
||||
# unless you clearly know what this will cause.
|
||||
"cfg_scale": 1,
|
||||
"tiled": False,
|
||||
"rand_device": self.pipe.device,
|
||||
"use_gradient_checkpointing": self.use_gradient_checkpointing,
|
||||
"use_gradient_checkpointing_offload": self.use_gradient_checkpointing_offload,
|
||||
"video_patchifier": self.pipe.video_patchifier,
|
||||
"audio_patchifier": self.pipe.audio_patchifier,
|
||||
}
|
||||
inputs_shared = self.parse_extra_inputs(data, self.extra_inputs, inputs_shared)
|
||||
return inputs_shared, inputs_posi, inputs_nega
|
||||
|
||||
def forward(self, data, inputs=None):
|
||||
if inputs is None: inputs = self.get_pipeline_inputs(data)
|
||||
inputs = self.transfer_data_to_device(inputs, self.pipe.device, self.pipe.torch_dtype)
|
||||
for unit in self.pipe.units:
|
||||
inputs = self.pipe.unit_runner(unit, self.pipe, *inputs)
|
||||
loss = self.task_to_loss[self.task](self.pipe, *inputs)
|
||||
return loss
|
||||
|
||||
|
||||
def ltx2_parser():
|
||||
parser = argparse.ArgumentParser(description="Simple example of a training script.")
|
||||
parser = add_general_config(parser)
|
||||
parser = add_video_size_config(parser)
|
||||
parser.add_argument("--tokenizer_path", type=str, default=None, help="Path to tokenizer.")
|
||||
parser.add_argument("--frame_rate", type=float, default=24, help="frame rate of the training videos. If not specified, it will be determined by the dataset.")
|
||||
parser.add_argument("--initialize_model_on_cpu", default=False, action="store_true", help="Whether to initialize models on CPU.")
|
||||
return parser
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
parser = ltx2_parser()
|
||||
args = parser.parse_args()
|
||||
accelerator = accelerate.Accelerator(
|
||||
gradient_accumulation_steps=args.gradient_accumulation_steps,
|
||||
kwargs_handlers=[accelerate.DistributedDataParallelKwargs(find_unused_parameters=args.find_unused_parameters)],
|
||||
)
|
||||
dataset = UnifiedDataset(
|
||||
base_path=args.dataset_base_path,
|
||||
metadata_path=args.dataset_metadata_path,
|
||||
repeat=args.dataset_repeat,
|
||||
data_file_keys=args.data_file_keys.split(","),
|
||||
main_data_operator=UnifiedDataset.default_video_operator(
|
||||
base_path=args.dataset_base_path,
|
||||
max_pixels=args.max_pixels,
|
||||
height=args.height,
|
||||
width=args.width,
|
||||
height_division_factor=16,
|
||||
width_division_factor=16,
|
||||
num_frames=args.num_frames,
|
||||
time_division_factor=4,
|
||||
time_division_remainder=1,
|
||||
),
|
||||
special_operator_map={
|
||||
"input_audio": ToAbsolutePath(args.dataset_base_path) >> LoadAudioWithTorchaudio(duration=float(args.num_frames) / float(args.frame_rate)),
|
||||
}
|
||||
)
|
||||
model = LTX2TrainingModule(
|
||||
model_paths=args.model_paths,
|
||||
model_id_with_origin_paths=args.model_id_with_origin_paths,
|
||||
tokenizer_path=args.tokenizer_path,
|
||||
trainable_models=args.trainable_models,
|
||||
lora_base_model=args.lora_base_model,
|
||||
lora_target_modules=args.lora_target_modules,
|
||||
lora_rank=args.lora_rank,
|
||||
lora_checkpoint=args.lora_checkpoint,
|
||||
preset_lora_path=args.preset_lora_path,
|
||||
preset_lora_model=args.preset_lora_model,
|
||||
use_gradient_checkpointing=args.use_gradient_checkpointing,
|
||||
use_gradient_checkpointing_offload=args.use_gradient_checkpointing_offload,
|
||||
extra_inputs=args.extra_inputs,
|
||||
fp8_models=args.fp8_models,
|
||||
offload_models=args.offload_models,
|
||||
task=args.task,
|
||||
device="cpu" if args.initialize_model_on_cpu else accelerator.device,
|
||||
)
|
||||
model_logger = ModelLogger(
|
||||
args.output_path,
|
||||
remove_prefix_in_ckpt=args.remove_prefix_in_ckpt,
|
||||
)
|
||||
launcher_map = {
|
||||
"sft:data_process": launch_data_process_task,
|
||||
"direct_distill:data_process": launch_data_process_task,
|
||||
"sft": launch_training_task,
|
||||
"sft:train": launch_training_task,
|
||||
"direct_distill": launch_training_task,
|
||||
"direct_distill:train": launch_training_task,
|
||||
}
|
||||
launcher_map[args.task](accelerator, dataset, model, model_logger, args=args)
|
||||
47
examples/ltx2/model_training/validate_full/LTX-2-T2AV.py
Normal file
47
examples/ltx2/model_training/validate_full/LTX-2-T2AV.py
Normal file
@@ -0,0 +1,47 @@
|
||||
import torch
|
||||
from diffsynth.pipelines.ltx2_audio_video import LTX2AudioVideoPipeline, ModelConfig
|
||||
from diffsynth.utils.data.media_io_ltx2 import write_video_audio_ltx2
|
||||
|
||||
vram_config = {
|
||||
"offload_dtype": torch.bfloat16,
|
||||
"offload_device": "cpu",
|
||||
"onload_dtype": torch.bfloat16,
|
||||
"onload_device": "cuda",
|
||||
"preparing_dtype": torch.bfloat16,
|
||||
"preparing_device": "cuda",
|
||||
"computation_dtype": torch.bfloat16,
|
||||
"computation_device": "cuda",
|
||||
}
|
||||
pipe = LTX2AudioVideoPipeline.from_pretrained(
|
||||
torch_dtype=torch.bfloat16,
|
||||
device="cuda",
|
||||
model_configs=[
|
||||
ModelConfig(model_id="google/gemma-3-12b-it-qat-q4_0-unquantized", origin_file_pattern="model-*.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="text_encoder_post_modules.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="video_vae_decoder.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="audio_vae_decoder.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="audio_vocoder.safetensors", **vram_config),
|
||||
ModelConfig(path="./models/train/LTX2-T2AV-full/epoch-4.safetensors", **vram_config),
|
||||
],
|
||||
tokenizer_config=ModelConfig(model_id="google/gemma-3-12b-it-qat-q4_0-unquantized"),
|
||||
)
|
||||
prompt = "A beautiful sunset over the ocean."
|
||||
negative_prompt = "blurry, out of focus, overexposed, underexposed, low contrast, washed out colors, excessive noise, grainy texture, poor lighting, flickering, motion blur, distorted proportions, unnatural skin tones, deformed facial features, asymmetrical face, missing facial features, extra limbs, disfigured hands, wrong hand count, artifacts around text, inconsistent perspective, camera shake, incorrect depth of field, background too sharp, background clutter, distracting reflections, harsh shadows, inconsistent lighting direction, color banding, cartoonish rendering, 3D CGI look, unrealistic materials, uncanny valley effect, incorrect ethnicity, wrong gender, exaggerated expressions, wrong gaze direction, mismatched lip sync, silent or muted audio, distorted voice, robotic voice, echo, background noise, off-sync audio, incorrect dialogue, added dialogue, repetitive speech, jittery movement, awkward pauses, incorrect timing, unnatural transitions, inconsistent framing, tilted camera, flat lighting, inconsistent tone, cinematic oversaturation, stylized filters, or AI artifacts."
|
||||
height, width, num_frames = 512, 768, 121
|
||||
video, audio = pipe(
|
||||
prompt=prompt,
|
||||
negative_prompt=negative_prompt,
|
||||
seed=43,
|
||||
height=height,
|
||||
width=width,
|
||||
num_frames=num_frames,
|
||||
tiled=True,
|
||||
cfg_scale=4.0
|
||||
)
|
||||
write_video_audio_ltx2(
|
||||
video=video,
|
||||
audio=audio,
|
||||
output_path='ltx2_onestage.mp4',
|
||||
fps=24,
|
||||
audio_sample_rate=24000,
|
||||
)
|
||||
49
examples/ltx2/model_training/validate_lora/LTX-2-T2AV.py
Normal file
49
examples/ltx2/model_training/validate_lora/LTX-2-T2AV.py
Normal file
@@ -0,0 +1,49 @@
|
||||
import torch
|
||||
from diffsynth.pipelines.ltx2_audio_video import LTX2AudioVideoPipeline, ModelConfig
|
||||
from diffsynth.utils.data.media_io_ltx2 import write_video_audio_ltx2
|
||||
|
||||
vram_config = {
|
||||
"offload_dtype": torch.bfloat16,
|
||||
"offload_device": "cpu",
|
||||
"onload_dtype": torch.bfloat16,
|
||||
"onload_device": "cuda",
|
||||
"preparing_dtype": torch.bfloat16,
|
||||
"preparing_device": "cuda",
|
||||
"computation_dtype": torch.bfloat16,
|
||||
"computation_device": "cuda",
|
||||
}
|
||||
pipe = LTX2AudioVideoPipeline.from_pretrained(
|
||||
torch_dtype=torch.bfloat16,
|
||||
device="cuda",
|
||||
model_configs=[
|
||||
ModelConfig(model_id="google/gemma-3-12b-it-qat-q4_0-unquantized", origin_file_pattern="model-*.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="transformer.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="text_encoder_post_modules.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="video_vae_decoder.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="audio_vae_decoder.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="audio_vocoder.safetensors", **vram_config),
|
||||
],
|
||||
tokenizer_config=ModelConfig(model_id="google/gemma-3-12b-it-qat-q4_0-unquantized"),
|
||||
)
|
||||
pipe.load_lora(pipe.dit, "models/train/LTX2-T2AV_lora/epoch-4.safetensors")
|
||||
prompt = "A beautiful sunset over the ocean."
|
||||
negative_prompt = "blurry, out of focus, overexposed, underexposed, low contrast, washed out colors, excessive noise, grainy texture, poor lighting, flickering, motion blur, distorted proportions, unnatural skin tones, deformed facial features, asymmetrical face, missing facial features, extra limbs, disfigured hands, wrong hand count, artifacts around text, inconsistent perspective, camera shake, incorrect depth of field, background too sharp, background clutter, distracting reflections, harsh shadows, inconsistent lighting direction, color banding, cartoonish rendering, 3D CGI look, unrealistic materials, uncanny valley effect, incorrect ethnicity, wrong gender, exaggerated expressions, wrong gaze direction, mismatched lip sync, silent or muted audio, distorted voice, robotic voice, echo, background noise, off-sync audio, incorrect dialogue, added dialogue, repetitive speech, jittery movement, awkward pauses, incorrect timing, unnatural transitions, inconsistent framing, tilted camera, flat lighting, inconsistent tone, cinematic oversaturation, stylized filters, or AI artifacts."
|
||||
height, width, num_frames = 512, 768, 121
|
||||
height, width, num_frames = 256, 384, 25
|
||||
video, audio = pipe(
|
||||
prompt=prompt,
|
||||
negative_prompt=negative_prompt,
|
||||
seed=43,
|
||||
height=height,
|
||||
width=width,
|
||||
num_frames=num_frames,
|
||||
tiled=True,
|
||||
cfg_scale=4.0
|
||||
)
|
||||
write_video_audio_ltx2(
|
||||
video=video,
|
||||
audio=audio,
|
||||
output_path='ltx2_onestage.mp4',
|
||||
fps=24,
|
||||
audio_sample_rate=24000,
|
||||
)
|
||||
@@ -0,0 +1,49 @@
|
||||
import torch
|
||||
from diffsynth.pipelines.ltx2_audio_video import LTX2AudioVideoPipeline, ModelConfig
|
||||
from diffsynth.utils.data.media_io_ltx2 import write_video_audio_ltx2
|
||||
|
||||
vram_config = {
|
||||
"offload_dtype": torch.bfloat16,
|
||||
"offload_device": "cpu",
|
||||
"onload_dtype": torch.bfloat16,
|
||||
"onload_device": "cuda",
|
||||
"preparing_dtype": torch.bfloat16,
|
||||
"preparing_device": "cuda",
|
||||
"computation_dtype": torch.bfloat16,
|
||||
"computation_device": "cuda",
|
||||
}
|
||||
pipe = LTX2AudioVideoPipeline.from_pretrained(
|
||||
torch_dtype=torch.bfloat16,
|
||||
device="cuda",
|
||||
model_configs=[
|
||||
ModelConfig(model_id="google/gemma-3-12b-it-qat-q4_0-unquantized", origin_file_pattern="model-*.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="transformer.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="text_encoder_post_modules.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="video_vae_decoder.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="audio_vae_decoder.safetensors", **vram_config),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="audio_vocoder.safetensors", **vram_config),
|
||||
],
|
||||
tokenizer_config=ModelConfig(model_id="google/gemma-3-12b-it-qat-q4_0-unquantized"),
|
||||
)
|
||||
pipe.load_lora(pipe.dit, "models/train/LTX2-T2AV-noaudio_lora/epoch-4.safetensors")
|
||||
prompt = "A beautiful sunset over the ocean."
|
||||
negative_prompt = "blurry, out of focus, overexposed, underexposed, low contrast, washed out colors, excessive noise, grainy texture, poor lighting, flickering, motion blur, distorted proportions, unnatural skin tones, deformed facial features, asymmetrical face, missing facial features, extra limbs, disfigured hands, wrong hand count, artifacts around text, inconsistent perspective, camera shake, incorrect depth of field, background too sharp, background clutter, distracting reflections, harsh shadows, inconsistent lighting direction, color banding, cartoonish rendering, 3D CGI look, unrealistic materials, uncanny valley effect, incorrect ethnicity, wrong gender, exaggerated expressions, wrong gaze direction, mismatched lip sync, silent or muted audio, distorted voice, robotic voice, echo, background noise, off-sync audio, incorrect dialogue, added dialogue, repetitive speech, jittery movement, awkward pauses, incorrect timing, unnatural transitions, inconsistent framing, tilted camera, flat lighting, inconsistent tone, cinematic oversaturation, stylized filters, or AI artifacts."
|
||||
height, width, num_frames = 512, 768, 121
|
||||
height, width, num_frames = 256, 384, 25
|
||||
video, audio = pipe(
|
||||
prompt=prompt,
|
||||
negative_prompt=negative_prompt,
|
||||
seed=43,
|
||||
height=height,
|
||||
width=width,
|
||||
num_frames=num_frames,
|
||||
tiled=True,
|
||||
cfg_scale=4.0
|
||||
)
|
||||
write_video_audio_ltx2(
|
||||
video=video,
|
||||
audio=audio,
|
||||
output_path='ltx2_onestage.mp4',
|
||||
fps=24,
|
||||
audio_sample_rate=24000,
|
||||
)
|
||||
104
examples/ltx2/scripts/split_model_statedicts.py
Normal file
104
examples/ltx2/scripts/split_model_statedicts.py
Normal file
@@ -0,0 +1,104 @@
|
||||
from safetensors.torch import save_file
|
||||
from diffsynth import hash_state_dict_keys
|
||||
from diffsynth.core import load_state_dict
|
||||
from diffsynth.models.model_loader import ModelPool
|
||||
|
||||
model_pool = ModelPool()
|
||||
state_dict = load_state_dict("models/Lightricks/LTX-2/ltx-2-19b-dev.safetensors")
|
||||
|
||||
dit_state_dict = {}
|
||||
for name in state_dict:
|
||||
if name.startswith("model.diffusion_model."):
|
||||
new_name = name.replace("model.diffusion_model.", "")
|
||||
if new_name.startswith("audio_embeddings_connector.") or new_name.startswith("video_embeddings_connector."):
|
||||
continue
|
||||
dit_state_dict[name] = state_dict[name]
|
||||
|
||||
print(f"dit_state_dict keys hash: {hash_state_dict_keys(dit_state_dict)}")
|
||||
save_file(dit_state_dict, "models/DiffSynth-Studio/LTX-2-Repackage/transformer.safetensors")
|
||||
model_pool.auto_load_model(
|
||||
"models/DiffSynth-Studio/LTX-2-Repackage/transformer.safetensors",
|
||||
)
|
||||
|
||||
|
||||
video_vae_encoder_state_dict = {}
|
||||
for name in state_dict:
|
||||
if name.startswith("vae.encoder."):
|
||||
video_vae_encoder_state_dict[name] = state_dict[name]
|
||||
elif name.startswith("vae.per_channel_statistics."):
|
||||
video_vae_encoder_state_dict[name] = state_dict[name]
|
||||
|
||||
save_file(video_vae_encoder_state_dict, "models/DiffSynth-Studio/LTX-2-Repackage/video_vae_encoder.safetensors")
|
||||
print(f"video_vae_encoder keys hash: {hash_state_dict_keys(video_vae_encoder_state_dict)}")
|
||||
model_pool.auto_load_model("models/DiffSynth-Studio/LTX-2-Repackage/video_vae_encoder.safetensors")
|
||||
|
||||
|
||||
video_vae_decoder_state_dict = {}
|
||||
for name in state_dict:
|
||||
if name.startswith("vae.decoder."):
|
||||
video_vae_decoder_state_dict[name] = state_dict[name]
|
||||
elif name.startswith("vae.per_channel_statistics."):
|
||||
video_vae_decoder_state_dict[name] = state_dict[name]
|
||||
save_file(video_vae_decoder_state_dict, "models/DiffSynth-Studio/LTX-2-Repackage/video_vae_decoder.safetensors")
|
||||
print(f"video_vae_decoder keys hash: {hash_state_dict_keys(video_vae_decoder_state_dict)}")
|
||||
model_pool.auto_load_model("models/DiffSynth-Studio/LTX-2-Repackage/video_vae_decoder.safetensors")
|
||||
|
||||
|
||||
audio_vae_decoder_state_dict = {}
|
||||
for name in state_dict:
|
||||
if name.startswith("audio_vae.decoder."):
|
||||
audio_vae_decoder_state_dict[name] = state_dict[name]
|
||||
elif name.startswith("audio_vae.per_channel_statistics."):
|
||||
audio_vae_decoder_state_dict[name] = state_dict[name]
|
||||
save_file(audio_vae_decoder_state_dict, "models/DiffSynth-Studio/LTX-2-Repackage/audio_vae_decoder.safetensors")
|
||||
print(f"audio_vae_decoder keys hash: {hash_state_dict_keys(audio_vae_decoder_state_dict)}")
|
||||
model_pool.auto_load_model("models/DiffSynth-Studio/LTX-2-Repackage/audio_vae_decoder.safetensors")
|
||||
|
||||
|
||||
audio_vae_encoder_state_dict = {}
|
||||
for name in state_dict:
|
||||
if name.startswith("audio_vae.encoder."):
|
||||
audio_vae_encoder_state_dict[name] = state_dict[name]
|
||||
elif name.startswith("audio_vae.per_channel_statistics."):
|
||||
audio_vae_encoder_state_dict[name] = state_dict[name]
|
||||
save_file(audio_vae_encoder_state_dict, "models/DiffSynth-Studio/LTX-2-Repackage/audio_vae_encoder.safetensors")
|
||||
print(f"audio_vae_encoder keys hash: {hash_state_dict_keys(audio_vae_encoder_state_dict)}")
|
||||
model_pool.auto_load_model("models/DiffSynth-Studio/LTX-2-Repackage/audio_vae_encoder.safetensors")
|
||||
|
||||
|
||||
audio_vocoder_state_dict = {}
|
||||
for name in state_dict:
|
||||
if name.startswith("vocoder."):
|
||||
audio_vocoder_state_dict[name] = state_dict[name]
|
||||
save_file(audio_vocoder_state_dict, "models/DiffSynth-Studio/LTX-2-Repackage/audio_vocoder.safetensors")
|
||||
print(f"audio_vocoder keys hash: {hash_state_dict_keys(audio_vocoder_state_dict)}")
|
||||
model_pool.auto_load_model("models/DiffSynth-Studio/LTX-2-Repackage/audio_vocoder.safetensors")
|
||||
|
||||
|
||||
text_encoder_post_modules_state_dict = {}
|
||||
for name in state_dict:
|
||||
if name.startswith("text_embedding_projection."):
|
||||
text_encoder_post_modules_state_dict[name] = state_dict[name]
|
||||
elif name.startswith("model.diffusion_model.video_embeddings_connector."):
|
||||
text_encoder_post_modules_state_dict[name] = state_dict[name]
|
||||
elif name.startswith("model.diffusion_model.audio_embeddings_connector."):
|
||||
text_encoder_post_modules_state_dict[name] = state_dict[name]
|
||||
save_file(text_encoder_post_modules_state_dict, "models/DiffSynth-Studio/LTX-2-Repackage/text_encoder_post_modules.safetensors")
|
||||
print(f"text_encoder_post_modules keys hash: {hash_state_dict_keys(text_encoder_post_modules_state_dict)}")
|
||||
model_pool.auto_load_model("models/DiffSynth-Studio/LTX-2-Repackage/text_encoder_post_modules.safetensors")
|
||||
|
||||
|
||||
state_dict = load_state_dict("models/Lightricks/LTX-2/ltx-2-19b-distilled.safetensors")
|
||||
dit_state_dict = {}
|
||||
for name in state_dict:
|
||||
if name.startswith("model.diffusion_model."):
|
||||
new_name = name.replace("model.diffusion_model.", "")
|
||||
if new_name.startswith("audio_embeddings_connector.") or new_name.startswith("video_embeddings_connector."):
|
||||
continue
|
||||
dit_state_dict[name] = state_dict[name]
|
||||
|
||||
print(f"dit_state_dict keys hash: {hash_state_dict_keys(dit_state_dict)}")
|
||||
save_file(dit_state_dict, "models/DiffSynth-Studio/LTX-2-Repackage/transformer_distilled.safetensors")
|
||||
model_pool.auto_load_model(
|
||||
"models/DiffSynth-Studio/LTX-2-Repackage/transformer_distilled.safetensors",
|
||||
)
|
||||
Reference in New Issue
Block a user