Instructions to use wikeeyang/SRPO-Refine-Quantized-v1.0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use wikeeyang/SRPO-Refine-Quantized-v1.0 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("wikeeyang/SRPO-Refine-Quantized-v1.0", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
SRPO-Flux-int8 convrot
#3
by LPZLZ - opened
May I ask Mr. Yang, can you make an SRPO-Flux-int8 convrot through the SRPO Flux fp32 version? And also int8 convrot of Qwen image 2512.
Thank you very much!
May I ask Mr. Yang, can you make an SRPO-Flux-int8 convrot through the SRPO Flux fp32 version? And also int8 convrot of Qwen image 2512.
Thank you very much!
you can convert this model by yourself through ComfyUI officel model tools...Qwen-Image-2512 int8_convrot compare to fp8 just so so...
Do you have a link to ComfyUI model tools?
Do you have a link to ComfyUI model tools?