SD3.5M-FlowGRPO-GenEval

367
9
—
by
jieliu
Other
OTHER
2505.05470B params
New
367 downloads
Early-stage
Try on Hugging FaceAdd to Compare
Edge AI:
Mobile
Laptop
Server
5600GB+ RAM
Mobile
Laptop
Server
Quick Summary

[Update] We release a new GenEval model that maintains image quality close to the base model, while still achieving the original GenEval score of 95.

Device Compatibility

Mobile
4-6GB RAM
Laptop
16GB RAM
Server
GPU
Minimum Recommended
2334GB+ RAM

Code Examples

Model Detailspythonpytorch
import torch
from diffusers import StableDiffusion3Pipeline
from diffusers.schedulers import FlowMatchEulerDiscreteScheduler
from peft import PeftModel

model_id = "stabilityai/stable-diffusion-3.5-medium"
lora_ckpt_path = "jieliu/SD3.5M-FlowGRPO-GenEval"
device = "cuda"


pipe = StableDiffusion3Pipeline.from_pretrained(model_id, torch_dtype=torch.float16)
pipe.transformer = PeftModel.from_pretrained(pipe.transformer, lora_ckpt_path)
pipe.transformer = pipe.transformer.merge_and_unload()
pipe = pipe.to(device)

prompt = 'a photo of a black kite and a green bear'
image = pipe(prompt, height=512, width=512, num_inference_steps=40,guidance_scale=4.5,negative_prompt="").images[0]  
image.save(f"flow_grpo.png")
Model Detailspythonpytorch
import torch
from diffusers import StableDiffusion3Pipeline
from diffusers.schedulers import FlowMatchEulerDiscreteScheduler
from peft import PeftModel

model_id = "stabilityai/stable-diffusion-3.5-medium"
lora_ckpt_path = "jieliu/SD3.5M-FlowGRPO-GenEval"
device = "cuda"


pipe = StableDiffusion3Pipeline.from_pretrained(model_id, torch_dtype=torch.float16)
pipe.transformer = PeftModel.from_pretrained(pipe.transformer, lora_ckpt_path)
pipe.transformer = pipe.transformer.merge_and_unload()
pipe = pipe.to(device)

prompt = 'a photo of a black kite and a green bear'
image = pipe(prompt, height=512, width=512, num_inference_steps=40,guidance_scale=4.5,negative_prompt="").images[0]  
image.save(f"flow_grpo.png")
Model Detailspythonpytorch
import torch
from diffusers import StableDiffusion3Pipeline
from diffusers.schedulers import FlowMatchEulerDiscreteScheduler
from peft import PeftModel

model_id = "stabilityai/stable-diffusion-3.5-medium"
lora_ckpt_path = "jieliu/SD3.5M-FlowGRPO-GenEval"
device = "cuda"


pipe = StableDiffusion3Pipeline.from_pretrained(model_id, torch_dtype=torch.float16)
pipe.transformer = PeftModel.from_pretrained(pipe.transformer, lora_ckpt_path)
pipe.transformer = pipe.transformer.merge_and_unload()
pipe = pipe.to(device)

prompt = 'a photo of a black kite and a green bear'
image = pipe(prompt, height=512, width=512, num_inference_steps=40,guidance_scale=4.5,negative_prompt="").images[0]  
image.save(f"flow_grpo.png")
Model Detailspythonpytorch
import torch
from diffusers import StableDiffusion3Pipeline
from diffusers.schedulers import FlowMatchEulerDiscreteScheduler
from peft import PeftModel

model_id = "stabilityai/stable-diffusion-3.5-medium"
lora_ckpt_path = "jieliu/SD3.5M-FlowGRPO-GenEval"
device = "cuda"


pipe = StableDiffusion3Pipeline.from_pretrained(model_id, torch_dtype=torch.float16)
pipe.transformer = PeftModel.from_pretrained(pipe.transformer, lora_ckpt_path)
pipe.transformer = pipe.transformer.merge_and_unload()
pipe = pipe.to(device)

prompt = 'a photo of a black kite and a green bear'
image = pipe(prompt, height=512, width=512, num_inference_steps=40,guidance_scale=4.5,negative_prompt="").images[0]  
image.save(f"flow_grpo.png")
Model Detailspythonpytorch
import torch
from diffusers import StableDiffusion3Pipeline
from diffusers.schedulers import FlowMatchEulerDiscreteScheduler
from peft import PeftModel

model_id = "stabilityai/stable-diffusion-3.5-medium"
lora_ckpt_path = "jieliu/SD3.5M-FlowGRPO-GenEval"
device = "cuda"


pipe = StableDiffusion3Pipeline.from_pretrained(model_id, torch_dtype=torch.float16)
pipe.transformer = PeftModel.from_pretrained(pipe.transformer, lora_ckpt_path)
pipe.transformer = pipe.transformer.merge_and_unload()
pipe = pipe.to(device)

prompt = 'a photo of a black kite and a green bear'
image = pipe(prompt, height=512, width=512, num_inference_steps=40,guidance_scale=4.5,negative_prompt="").images[0]  
image.save(f"flow_grpo.png")

Deploy This Model

Production-ready deployment in minutes

Together.ai

Instant API access to this model

Fastest API

Production-ready inference API. Start free, scale to millions.

Try Free API

Replicate

One-click model deployment

Easiest Setup

Run models in the cloud with simple API. No DevOps required.

Deploy Now

Disclosure: We may earn a commission from these partners. This helps keep LLMYourWay free.