theluyuan/DiffSynth-Studio
1
0
Fork 0
mirror of https://github.com/modelscope/DiffSynth-Studio.git synced 2026-03-21 08:08:13 +00:00
Code Issues Packages Projects Releases Wiki Activity

ltx2.3 train

Browse Source
This commit is contained in:
mi804
2026-03-06 18:08:42 +08:00
parent c9c2561791
commit d40efe897f
13 changed files with 346 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files

17
examples/ltx2/model_inference/LTX-2.3-T2AV-OneStage.py
View File

@@ -12,15 +12,30 @@ vram_config = {
"computation_dtype": torch.bfloat16,
"computation_device": "cuda",
}
# use the repackaged modelconfig from "DiffSynth-Studio/LTX-2.3-Repackage" to avoid redundant model loading
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="Lightricks/LTX-2.3", origin_file_pattern="ltx-2.3-22b-dev.safetensors", **vram_config),
ModelConfig(model_id="DiffSynth-Studio/LTX-2.3-Repackage", origin_file_pattern="transformer.safetensors", **vram_config),
ModelConfig(model_id="DiffSynth-Studio/LTX-2.3-Repackage", origin_file_pattern="text_encoder_post_modules.safetensors", **vram_config),
ModelConfig(model_id="DiffSynth-Studio/LTX-2.3-Repackage", origin_file_pattern="video_vae_decoder.safetensors", **vram_config),
ModelConfig(model_id="DiffSynth-Studio/LTX-2.3-Repackage", origin_file_pattern="audio_vae_decoder.safetensors", **vram_config),
ModelConfig(model_id="DiffSynth-Studio/LTX-2.3-Repackage", origin_file_pattern="audio_vocoder.safetensors", **vram_config),
],
tokenizer_config=ModelConfig(model_id="google/gemma-3-12b-it-qat-q4_0-unquantized"),
)
# use the following modelconfig if you want to initialize model from offical checkpoints from "Lightricks/LTX-2.3"
# 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="Lightricks/LTX-2.3", origin_file_pattern="ltx-2.3-22b-dev.safetensors", **vram_config),
# ],
# tokenizer_config=ModelConfig(model_id="google/gemma-3-12b-it-qat-q4_0-unquantized"),
# )
prompt = "A girl is very happy, she is speaking: “I enjoy working with Diffsynth-Studio, it's a perfect framework.”"
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