camenduru

I converted to flax I put it https://huggingface.co/flax/stable-diffusion-2 if someone needs

I am also curious 🤔 @loboere please try https://github.com/huggingface/accelerate ``` pip install accelerate accelerate config ```

maybe second pipe missing `generator=generator` ```py generator = torch.Generator(device="cuda").manual_seed(87) display(pipe.text2img(prompt, negative_prompt=neg_prompt, width=512,height=512,max_embeddings_multiples=3, generator=generator).images[0]) generator = torch.Generator(device="cuda").manual_seed(87) display(pipe.text2img(prompt, negative_prompt=neg_prompt, width=512,height=512,max_embeddings_multiples=3).images[0]) ```

@thisislance98 try `generator = torch.cuda.manual_seed_all(seed)` or `generator = torch.cuda.manual_seed(seed)` ```py for _ in range(2): # Get a new random seed, store it and use it as the generator state seed...

I am testing...

😥 ``` RuntimeError Traceback (most recent call last) [](https://localhost:8080/#) in 1 get_ipython().system('pip install diffusers transformers -qq') 2 from diffusers import StableDiffusionPipeline ----> 3 pipe = StableDiffusionPipeline.from_pretrained("camenduru/test", safety_checker=None).to("cuda") 2 frames [/usr/local/lib/python3.7/dist-packages/transformers/modeling_utils.py](https://localhost:8080/#)...

@jorahn I add the model here https://huggingface.co/camenduru/test if you need

hi @patrickvonplaten yes we need help, maybe the problem is this https://github.com/huggingface/diffusers/pull/1217#issuecomment-1312739419 please tell us how to adapt the old function to diffusers

thanks @Lime-Cakes ❤ this is super cool news 🔥 if you need tester I can test

 https://github.com/camenduru/diffusers/blob/from_flax_v2/src/diffusers/modeling_pytorch_flax_utils.py https://huggingface.co/camenduru/plushies-pt