latent upscale with flux - recommended percent 0.5-0.6

pip install wheel
pip wheel --no-deps -w dist .
inside repo folder
it will be saved on dist folder

pip install wheel
pip wheel --no-deps -w dist .
inside repo folder
it will be saved on dist folder

this one worked on xpose
pip install setuptools wheel
python setup.py sdist bdist_wheel

this one worked on xpose
pip install setuptools wheel
python setup.py sdist bdist_wheel

python -m pip install --pre torch torchvision torchaudio --index-url https://download.pytorch.org/whl/nightly/cu128

python -m pip install --pre torch torchvision torchaudio --index-url https://download.pytorch.org/whl/nightly/cu128

Stop-motion, model animation. A time-machine on the table whirs into life with pistons moving and gears spinning. The hands of the clock spin rapidly. The characters watch the machine in awe. The camera orbits rapidly around the machine, showing the professor's Victorian style laboratory from all angles. The machine sparks and buzzes with waves of visible electrical energy.

Stop-motion, model animation. A time-machine on the table whirs into life with pistons moving and gears spinning. The hands of the clock spin rapidly. The characters watch the machine in awe. The camera orbits rapidly around the machine, showing the professor's Victorian style laboratory from all angles. The machine sparks and buzzes with waves of visible electrical energy.

Immerse yourself in a breathtakingly detailed photorealistic video of a cat, captured in a serene, sunlit indoor setting. The feline, a striking black and white tuxedo cat with piercing green eyes, is positioned on a plush, light-colored rug, its sleek fur glistening under the soft, golden-hour glow. The camera, held steady, frames the cat from a slightly elevated angle, allowing viewers to appreciate its elegant posture and the subtle play of light across its coat. As the cat gazes intently into the distance, its ears twitch slightly, hinting at a moment of curiosity or alertness. The background, softly blurred, features a hint of a window, suggesting a tranquil indoor environment. This cinematic experience, enhanced by dynamic color grading and meticulous lighting, invites viewers to connect with the cat's expressive features, creating a captivating, intimate portrait.

Immerse yourself in a breathtakingly detailed photorealistic video of a cat, captured in a serene, sunlit indoor setting. The feline, a striking black and white tuxedo cat with piercing green eyes, is positioned on a plush, light-colored rug, its sleek fur glistening under the soft, golden-hour glow. The camera, held steady, frames the cat from a slightly elevated angle, allowing viewers to appreciate its elegant posture and the subtle play of light across its coat. As the cat gazes intently into the distance, its ears twitch slightly, hinting at a moment of curiosity or alertness. The background, softly blurred, features a hint of a window, suggesting a tranquil indoor environment. This cinematic experience, enhanced by dynamic color grading and meticulous lighting, invites viewers to connect with the cat's expressive features, creating a captivating, intimate portrait.

set MAX_JOBS=1
python setup.py build_ext bdist_wheel

set MAX_JOBS=1
python setup.py build_ext bdist_wheel

requests.exceptions.HTTPError: 401 Client Error: Unauthorized for url: https://huggingface.co/api/models

requests.exceptions.HTTPError: 401 Client Error: Unauthorized for url: https://huggingface.co/api/models

huggingface-cli logout

huggingface-cli logout

    from triton._C.libtriton import ir, passes, llvm, amd
ImportError: DLL load failed while importing libtriton: A dynamic link library (DLL) initialization routine failed.

    from triton._C.libtriton import ir, passes, llvm, amd
ImportError: DLL load failed while importing libtriton: A dynamic link library (DLL) initialization routine failed.

\Comfy_UI_V24\ComfyUI\venv\Scripts>python.exe -m pip install -r \Comfy_UI_V24\ComfyUI\custom_nodes\ComfyUI-WanVideoWrapper\requirements.txt 

\Comfy_UI_V24\ComfyUI\venv\Scripts>python.exe -m pip install -r \Comfy_UI_V24\ComfyUI\custom_nodes\ComfyUI-WanVideoWrapper\requirements.txt 

 my prompt <refiner> <lora:Phantom_Wan_14B_FusionX_LoRA:1.0> <base> <lora:Phantom_Wan_14B_FusionX_LoRA:0.9> 

 my prompt <refiner> <lora:Phantom_Wan_14B_FusionX_LoRA:1.0> <base> <lora:Phantom_Wan_14B_FusionX_LoRA:0.9> 

 pip install flash-attn-triton and it should work on RTX 20xx (Turing), see https://github.com/rationalism/flash-attn-triton 

 pip install flash-attn-triton and it should work on RTX 20xx (Turing), see https://github.com/rationalism/flash-attn-triton 

@FurkanGozukara If you just run pip install sageattention, then it's SageAttention 1. It's hosted on pypi.org and you can see the wheel at https://pypi.org/project/sageattention/#files . It only uses Triton kernels, not CUDA kernels, so it's easy to install.

For FlashAttention that only uses Triton kernels, you can run pip install flash-attn-triton.

@FurkanGozukara If you just run pip install sageattention, then it's SageAttention 1. It's hosted on pypi.org and you can see the wheel at https://pypi.org/project/sageattention/#files . It only uses Triton kernels, not CUDA kernels, so it's easy to install.

For FlashAttention that only uses Triton kernels, you can run pip install flash-attn-triton.

Use --ddp_gradient_as_bucket_view param of DDP, that will solve this issue and yes the double memory consumption is expected without this param

Use --ddp_gradient_as_bucket_view param of DDP, that will solve this issue and yes the double memory consumption is expected without this param