Instructions to use tencent/SRPO with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use tencent/SRPO with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("tencent/SRPO", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
- DiffusionBee
请量化模型,我想尝试一下,能提供gguf版本吗?请问这个支持Flux的生态吗?
#1
by Universe97 - opened
请量化模型,我想尝试一下,能提供gguf版本吗?请问这个支持Flux的生态吗?
Thanks for your question! This model supports the full FLUX ecosystem—after all, it’s an enhanced version of the FLUX model itself through RL. Feel free to use it however you’d like!
Hello, can you provide a version of fp16 or fp8? I can't use fp32, can you quantify it? I really want to try it
This model doesn't work in standard flux model loaders. It seems it's a diffusors model in a sfetensor container rather than a standard safetensors model. Trying to use it in forge, for instance, returns unable to identify model.