nodes/hao-ai-lab-FastVideo
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

[refactor]: move apps and docs to generate(request) and from_config

Browse Source 
DreamVerse, FastVideo Studio, the ComfyUI node, the README, and the
inference docs call VideoGenerator.generate with nested requests and
VideoGenerator.from_config with typed configs, and read GenerationResult
attributes instead of result dict keys.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_012M91wnVFmPEvJ9h39r5BH7
This commit is contained in:
Davids048
2026-10-03 02:15:04 +00:00
co-authored by Claude Opus 5.5
parent 9139c0411b
commit d6ba5ced94
12 changed files with 263 additions and 192 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/inference/architecture.md
+5 -5
View File
@@ -372,10 +372,10 @@ generator = VideoGenerator.from_pretrained(
model_path="Wan-AI/Wan2.1-T2V-14B-Diffusers",
num_gpus=1, tp_size=1, sp_size=1,
)
result = generator.generate_video(
prompt="A cat dancing",
height=720, width=1280, num_frames=81,
)
result = generator.generate({
"prompt": "A cat dancing",
"sampling": {"height": 720, "width": 1280, "num_frames": 81},
})
```
**CLI** (`fastvideo/entrypoints/cli/`):
@@ -421,7 +421,7 @@ User: VideoGenerator.from_pretrained(model_path, **kwargs)
├─ torch.compile (if enabled)
└─ warmup_sequence_parallel_communication()
User: generator.generate_video(prompt, ...)
User: generator.generate(request)
│
├─ ForwardBatch constructed from SamplingParam + user args
└─ pipeline.forward(batch, fastvideo_args)
docs/inference/configuration.md
+31 -34
View File
@@ -37,7 +37,7 @@ You can customize generation behavior using `PipelineConfig` and
`SamplingParam`:
```python
from fastvideo import VideoGenerator, SamplingParam, PipelineConfig
from fastvideo import VideoGenerator, PipelineConfig
def main():
model_name = "Wan-AI/Wan2.1-T2V-1.3B-Diffusers"
@@ -45,43 +45,40 @@ def main():
config.vae_precision = "fp16"
# Create the generator
generator = VideoGenerator.from_pretrained(
model_name,
num_gpus=1,
dit_layerwise_offload=True, # FastVideoArgs option
pipeline_config=config
)
# Create and customize sampling parameters
sampling_param = SamplingParam.from_pretrained("Wan-AI/Wan2.1-T2V-1.3B-Diffusers")
# How many frames to generate
sampling_param.num_frames = 45
# Video resolution (width, height)
sampling_param.width = 1024
sampling_param.height = 576
# How many steps we denoise the video (higher = better quality, slower generation)
sampling_param.num_inference_steps = 30
# How strongly the video conforms to the prompt (higher = more faithful to prompt)
sampling_param.guidance_scale = 7.5
# Random seed for reproducibility
sampling_param.seed = 42 # Optional, leave unset for random results
generator = VideoGenerator.from_config({
"model_path": model_name,
"engine": {
"num_gpus": 1,
"offload": {"dit_layerwise": True}, # FastVideoArgs option
},
"pipeline": {"experimental": {"pipeline_config": config}},
})
# Generate video with custom parameters
prompt = "A beautiful sunset over a calm ocean, with gentle waves."
video = generator.generate_video(
prompt,
sampling_param=sampling_param,
output_path="my_videos/", # Controls where videos are saved
save_video=True
)
video = generator.generate({
"prompt": prompt,
"sampling": {
# How many frames to generate
"num_frames": 45,
# Video resolution (width, height)
"width": 1024,
"height": 576,
# How many steps we denoise the video (higher = better quality, slower generation)
"num_inference_steps": 30,
# How strongly the video conforms to the prompt (higher = more faithful to prompt)
"guidance_scale": 7.5,
# Random seed for reproducibility
"seed": 42, # Optional, leave unset for random results
},
"output": {
"output_path": "my_videos/", # Controls where videos are saved
"save_video": True,
},
})
# If return_frames=True, frames are available in video["frames"]
print(f"Generated {len(video['frames'])} frames")
# If return_frames=True, frames are available in video.frames
print(f"Generated {len(video.frames)} frames")
if __name__ == '__main__':
main()
docs/inference/inference_quick_start.md
+17 -14
View File
@@ -45,11 +45,13 @@ def main():
prompt = "A curious raccoon peers through a vibrant field of yellow sunflowers, its eyes wide with interest."
# Generate the video
video = generator.generate_video(
prompt,
output_path="my_videos/", # Controls where videos are saved
save_video=True
)
video = generator.generate({
"prompt": prompt,
"output": {
"output_path": "my_videos/", # Controls where videos are saved
"save_video": True,
},
})
if __name__ == '__main__':
main()
@@ -75,23 +77,24 @@ Please see the [support matrix](support_matrix.md) for the list of supported mod
You can generate a video starting from an initial image:
```python
from fastvideo import VideoGenerator, SamplingParam
from fastvideo import VideoGenerator
def main():
# Create the generator
model_name = "Wan-AI/Wan2.1-I2V-14B-480P-Diffusers"
generator = VideoGenerator.from_pretrained(model_name, num_gpus=1)
# Set up parameters with an initial image
sampling_param = SamplingParam.from_pretrained(model_name)
sampling_param.image_path = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/astronaut.jpg"
sampling_param.num_frames = 107
# Generate video based on the image
prompt = "A photograph coming to life with gentle movement"
generator.generate_video(prompt, sampling_param=sampling_param,
output_path="my_videos/",
save_video=True)
generator.generate({
"prompt": prompt,
# Set up parameters with an initial image
"inputs": {
"image_path": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/astronaut.jpg",
},
"sampling": {"num_frames": 107},
"output": {"output_path": "my_videos/", "save_video": True},
})
if __name__ == '__main__':
main()
docs/inference/offloading.md
+2 -2
View File
@@ -215,7 +215,7 @@ generator = VideoGenerator.from_pretrained(
)
prompt = "A curious raccoon peers through a vibrant field of yellow sunflowers."
video = generator.generate_video(prompt, output_path="output/", save_video=True)
video = generator.generate({"prompt": prompt, "output": {"output_path": "output/", "save_video": True}})
```
### Multi-GPU with FSDP
@@ -238,5 +238,5 @@ generator = VideoGenerator.from_pretrained(
)
prompt = "A majestic lion strides across the golden savanna."
video = generator.generate_video(prompt, output_path="output/", save_video=True)
video = generator.generate({"prompt": prompt, "output": {"output_path": "output/", "save_video": True}})
```
docs/inference/optimizations.md
+33 -23
View File
@@ -176,7 +176,7 @@ gen = VideoGenerator.from_pretrained(
num_gpus=1,
use_fsdp_inference=False, # FSDP is incompatible with FP4 pointer path
)
gen.generate_video(prompt="A raccoon in sunflowers", save_video=True)
gen.generate(request={"prompt": "A raccoon in sunflowers", "output": {"save_video": True}})
```
#### Known Limitations
@@ -206,14 +206,20 @@ os.environ["FASTVIDEO_ATTENTION_BACKEND"] = "ATTN_QAT_INFER"
from fastvideo import VideoGenerator
from fastvideo.layers.quantization import get_quantization_config
gen = VideoGenerator.from_pretrained(
"Wan-AI/Wan2.1-T2V-1.3B-Diffusers",
num_gpus=1,
# Wan-2.1 uses the nvfp4_qat config (NVFP4 is LTX2-specific). Pass an
# instance — the bare string is not resolved on the from_pretrained path.
transformer_quant=get_quantization_config("nvfp4_qat")(),
use_fsdp_inference=False, # FSDP shards invalidate the FP4 tensor pointers
)
gen = VideoGenerator.from_config({
"model_path": "Wan-AI/Wan2.1-T2V-1.3B-Diffusers",
"engine": {
"num_gpus": 1,
"use_fsdp_inference": False, # FSDP shards invalidate the FP4 tensor pointers
},
"pipeline": {
"experimental": {
# Wan-2.1 uses the nvfp4_qat config (NVFP4 is LTX2-specific). Pass an
# instance — the bare string is not resolved under pipeline.experimental.
"transformer_quant": get_quantization_config("nvfp4_qat")(),
},
},
})
gen.generate(request={"prompt": "A raccoon in sunflowers", "output": {"save_video": True}})
```
@@ -305,12 +311,16 @@ automatically.
from fastvideo import VideoGenerator
from fastvideo.layers.quantization import get_quantization_config
gen = VideoGenerator.from_pretrained(
"Wan-AI/Wan2.1-T2V-1.3B-Diffusers",
# Pass an instance — the bare string is not resolved on the from_pretrained path.
transformer_quant=get_quantization_config("FP8")(), # per-tensor (default)
# transformer_quant=get_quantization_config("FP8")(granularity="channel"), # slower, higher accuracy
)
gen = VideoGenerator.from_config({
"model_path": "Wan-AI/Wan2.1-T2V-1.3B-Diffusers",
"pipeline": {
"experimental": {
# Pass an instance — the bare string is not resolved under pipeline.experimental.
"transformer_quant": get_quantization_config("FP8")(), # per-tensor (default)
# "transformer_quant": get_quantization_config("FP8")(granularity="channel"), # slower, higher accuracy
},
},
})
gen.generate(request={"prompt": "A raccoon in sunflowers", "output": {"save_video": True}})
```
@@ -376,10 +386,10 @@ device is unsupported. Legacy VSA, MiniMax-H3 tile-256 VSA, and the explicit
eager with one warning instead of failing mid-denoise.
```python
generator = VideoGenerator.from_pretrained(
"MiniMaxAI/MiniMax-H3",
inference_torch_compile=True, # or FASTVIDEO_INFERENCE_TORCH_COMPILE=1
)
generator = VideoGenerator.from_config({
"model_path": "MiniMaxAI/MiniMax-H3",
"engine": {"compile": {"regional": True}}, # or FASTVIDEO_INFERENCE_TORCH_COMPILE=1
})
```
In a YAML config, set `generator.engine.compile.regional: true`.
@@ -501,10 +511,10 @@ for backend in ["TORCH_SDPA", "FLASH_ATTN", "SAGE_ATTN"]:
os.environ["FASTVIDEO_ATTENTION_BACKEND"] = backend
generator = VideoGenerator.from_pretrained("your-model-id")
start_time = time.perf_counter()
generator.generate_video(
prompt="Your prompt",
seed=1024,
)
generator.generate({
"prompt": "Your prompt",
"sampling": {"seed": 1024},
})
elapsed = time.perf_counter() - start_time
print(f"{backend}: {elapsed:.2f}s")
```