Loreto Parisi

Support Style reference, Seed image and Control parameters.

4

### Feature request / 功能建议 Any plan to add support to style reference, seed image and control parameters? ### Motivation / 动机 This feature has been speculated in [this](https://naomiclarkson0.medium.com/cogvideox-5b-the-truely-open-source-sora-alternative-38d0e87deee9) article:...

### System Info / 系統信息 ``` Collecting environment information... PyTorch version: 2.4.1+cu121 Is debug build: False CUDA used to build PyTorch: 12.1 ROCM used to build PyTorch: N/A OneFlow version:...

[Bug] Support to compile CogVideoXPipeline

1

### Your current environment information ``` Collecting environment information... PyTorch version: 2.4.0+cu121 Is debug build: False CUDA used to build PyTorch: 12.1 ROCM used to build PyTorch: N/A OneFlow version:...

ValueError: ('Unsupported kind: ', 'FRAGMENT')

1

I'm getting this import error when trying to import the libraty ```shell from torchao.quantization import quantize_ File "/home/coder/.local/lib/python3.10/site-packages/torchao/__init__.py", line 31, in from torchao.quantization import ( File "/home/coder/.local/lib/python3.10/site-packages/torchao/quantization/__init__.py", line 7, in...

OutOfMemoryError: CUDA out of memory with 24GB. Is it possible to apply torchao quantization?

16

I'm getting a OOM running the ```bash python enhance_a_video.py \ --version v2 \ --up_scale 4 --target_fps 24 --noise_aug 250 \ --solver_mode 'fast' --steps 15 \ --input_path 'prompts/' \ --prompt_path 'prompts/text_prompts.txt'...

Error UNCERTAIN_STATE with origin ETIMEDOUT and Retry Strategy

1

### Issue Supposed to have a vpn timeout errors, I get this error on the redis client: ```json { "code": "UNCERTAIN_STATE", "command": "GET", "args": [ "c9903ac70a7b58e1bef3ff0fe2c9dcd0" ], "origin": { "errno":...

Research: Benchmarking DeepSeek-R1 IQ1_S 1.58bit

42

### Research Stage - [ ] Background Research (Let's try to avoid reinventing the wheel) - [ ] Hypothesis Formed (How do you think this will work and it's effect?)...

[BENCHMARKS] DeepScaleR-1.5B-Preview F16 ollama GGUF vs llama.cpp

3

Running on Mac M1 Pro the brand new `DeepScaleR-1.5B-Preview` quantized F16 ([here](https://ollama.com/library/deepscaler:latest)) I see `ollama` GGUF quantization running (eval rate) at `48.19 tokens/s` (short prompt) ```bash ollama run deepscaler --verbose...