theluyuan/DiffSynth-Studio
1
0
Fork 0
mirror of https://github.com/modelscope/DiffSynth-Studio.git synced 2026-03-23 17:38:10 +00:00
Code Issues Packages Projects Releases Wiki Activity

update LTX-2.3 doc (#1364)

Browse Source
This commit is contained in:
Zhongjie Duan
2026-03-23 17:10:53 +08:00
committed by GitHub
parent 5d198287f0
commit f7b9ae7d57
2 changed files with 24 additions and 128 deletions
Download Patch File Download Diff File Expand all files Collapse all files

76
docs/en/Model_Details/LTX-2.md
View File

@@ -24,88 +24,36 @@ from diffsynth.pipelines.ltx2_audio_video import LTX2AudioVideoPipeline, ModelCo
from diffsynth.utils.data.media_io_ltx2 import write_video_audio_ltx2
vram_config = {
"offload_dtype": torch.float8_e5m2,
"offload_dtype": torch.bfloat16,
"offload_device": "cpu",
"onload_dtype": torch.float8_e5m2,
"onload_device": "cpu",
"preparing_dtype": torch.float8_e5m2,
"onload_dtype": torch.bfloat16,
"onload_device": "cuda",
"preparing_dtype": torch.bfloat16,
"preparing_device": "cuda",
"computation_dtype": torch.bfloat16,
"computation_device": "cuda",
}
"""
Offical model repo: https://www.modelscope.cn/models/Lightricks/LTX-2
Repackaged model repo: https://www.modelscope.cn/models/DiffSynth-Studio/LTX-2-Repackage
For base models of LTX-2, offical checkpoint (with model config ModelConfig(model_id="Lightricks/LTX-2", origin_file_pattern="ltx-2-19b-dev.safetensors"))
and repackaged checkpoints (with model config ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="*.safetensors")) are both supported.
We have repackeged the official checkpoints in DiffSynth-Studio/LTX-2-Repackage repo to support separate loading of different submodules,
and avoid redundant memory usage when users only want to use part of the model.
"""
# use the repackaged modelconfig from "DiffSynth-Studio/LTX-2-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="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),
ModelConfig(model_id="Lightricks/LTX-2.3", origin_file_pattern="ltx-2.3-22b-dev.safetensors", **vram_config),
ModelConfig(model_id="Lightricks/LTX-2.3", origin_file_pattern="ltx-2.3-spatial-upscaler-x2-1.0.safetensors", **vram_config),
],
tokenizer_config=ModelConfig(model_id="google/gemma-3-12b-it-qat-q4_0-unquantized"),
stage2_lora_config=ModelConfig(model_id="Lightricks/LTX-2", origin_file_pattern="ltx-2-19b-distilled-lora-384.safetensors"),
vram_limit=torch.cuda.mem_get_info("cuda")[1] / (1024 ** 3) - 0.5,
stage2_lora_config=ModelConfig(model_id="Lightricks/LTX-2.3", origin_file_pattern="ltx-2.3-22b-distilled-lora-384.safetensors"),
)
# use the following modelconfig if you want to initialize model from offical checkpoints from "Lightricks/LTX-2"
# 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", origin_file_pattern="ltx-2-19b-dev.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"),
# stage2_lora_config=ModelConfig(model_id="Lightricks/LTX-2", origin_file_pattern="ltx-2-19b-distilled-lora-384.safetensors"),
# vram_limit=torch.cuda.mem_get_info("cuda")[1] / (1024 ** 3) - 0.5,
# )
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 * 2, 768 * 2, 121
prompt = "Two cute orange cats, wearing boxing gloves, stand in a boxing ring and fight each other. They are punching each other fast and yelling: 'I will win!'"
negative_prompt = pipe.default_negative_prompt["LTX-2.3"]
video, audio = pipe(
prompt=prompt,
negative_prompt=negative_prompt,
seed=43,
height=height,
width=width,
num_frames=num_frames,
tiled=True,
use_two_stage_pipeline=True,
)
write_video_audio_ltx2(
video=video,
audio=audio,
output_path='ltx2_twostage.mp4',
fps=24,
audio_sample_rate=24000,
height=1024, width=1536, num_frames=121,
tiled=True, use_two_stage_pipeline=True,
)
write_video_audio_ltx2(video=video, audio=audio, output_path='video.mp4', fps=24, audio_sample_rate=pipe.audio_vocoder.output_sampling_rate)
```
## Model Overview

76
docs/zh/Model_Details/LTX-2.md
View File

@@ -24,88 +24,36 @@ from diffsynth.pipelines.ltx2_audio_video import LTX2AudioVideoPipeline, ModelCo
from diffsynth.utils.data.media_io_ltx2 import write_video_audio_ltx2
vram_config = {
"offload_dtype": torch.float8_e5m2,
"offload_dtype": torch.bfloat16,
"offload_device": "cpu",
"onload_dtype": torch.float8_e5m2,
"onload_device": "cpu",
"preparing_dtype": torch.float8_e5m2,
"onload_dtype": torch.bfloat16,
"onload_device": "cuda",
"preparing_dtype": torch.bfloat16,
"preparing_device": "cuda",
"computation_dtype": torch.bfloat16,
"computation_device": "cuda",
}
"""
Offical model repo: https://www.modelscope.cn/models/Lightricks/LTX-2
Repackaged model repo: https://www.modelscope.cn/models/DiffSynth-Studio/LTX-2-Repackage
For base models of LTX-2, offical checkpoint (with model config ModelConfig(model_id="Lightricks/LTX-2", origin_file_pattern="ltx-2-19b-dev.safetensors"))
and repackaged checkpoints (with model config ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="*.safetensors")) are both supported.
We have repackeged the official checkpoints in DiffSynth-Studio/LTX-2-Repackage repo to support separate loading of different submodules,
and avoid redundant memory usage when users only want to use part of the model.
"""
# use the repackaged modelconfig from "DiffSynth-Studio/LTX-2-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="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),
ModelConfig(model_id="Lightricks/LTX-2.3", origin_file_pattern="ltx-2.3-22b-dev.safetensors", **vram_config),
ModelConfig(model_id="Lightricks/LTX-2.3", origin_file_pattern="ltx-2.3-spatial-upscaler-x2-1.0.safetensors", **vram_config),
],
tokenizer_config=ModelConfig(model_id="google/gemma-3-12b-it-qat-q4_0-unquantized"),
stage2_lora_config=ModelConfig(model_id="Lightricks/LTX-2", origin_file_pattern="ltx-2-19b-distilled-lora-384.safetensors"),
vram_limit=torch.cuda.mem_get_info("cuda")[1] / (1024 ** 3) - 0.5,
stage2_lora_config=ModelConfig(model_id="Lightricks/LTX-2.3", origin_file_pattern="ltx-2.3-22b-distilled-lora-384.safetensors"),
)
# use the following modelconfig if you want to initialize model from offical checkpoints from "Lightricks/LTX-2"
# 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", origin_file_pattern="ltx-2-19b-dev.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"),
# stage2_lora_config=ModelConfig(model_id="Lightricks/LTX-2", origin_file_pattern="ltx-2-19b-distilled-lora-384.safetensors"),
# vram_limit=torch.cuda.mem_get_info("cuda")[1] / (1024 ** 3) - 0.5,
# )
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 * 2, 768 * 2, 121
prompt = "Two cute orange cats, wearing boxing gloves, stand in a boxing ring and fight each other. They are punching each other fast and yelling: 'I will win!'"
negative_prompt = pipe.default_negative_prompt["LTX-2.3"]
video, audio = pipe(
prompt=prompt,
negative_prompt=negative_prompt,
seed=43,
height=height,
width=width,
num_frames=num_frames,
tiled=True,
use_two_stage_pipeline=True,
)
write_video_audio_ltx2(
video=video,
audio=audio,
output_path='ltx2_twostage.mp4',
fps=24,
audio_sample_rate=24000,
height=1024, width=1536, num_frames=121,
tiled=True, use_two_stage_pipeline=True,
)
write_video_audio_ltx2(video=video, audio=audio, output_path='video.mp4', fps=24, audio_sample_rate=pipe.audio_vocoder.output_sampling_rate)
```
## 模型总览