Description
Describe the bug
When using the FluxPriorReduxPipeline the prompt_embeds_scale and pooled_prompt_embeds_scale seem to have no effect on the final generation.
Reproduction
async def get_redux_embeds(image, prompt, strength):
redux_repo = "black-forest-labs/FLUX.1-Redux-dev"
text_encoder, tokenizer, text_encoder_2, tokenizer_2 = await get_text_encoders()
redux_pipeline = FluxPriorReduxPipeline.from_pretrained(redux_repo,
text_encoder=text_encoder,
tokenizer=tokenizer,
text_encoder_2=text_encoder_2,
tokenizer_2=tokenizer_2,
torch_dtype=dtype).to("cuda")
redux_embeds, redux_pooled_embeds = redux_pipeline(image=image,
prompt=prompt,
prompt_2=prompt,
prompt_embeds_scale=strength,
pooled_prompt_embeds_scale=strength,
return_dict=False)
redux_pipeline.to("cpu")
del redux_pipeline, text_encoder, tokenizer, text_encoder_2, tokenizer_2
torch.cuda.empty_cache()
gc.collect()
return redux_embeds, redux_pooled_embeds
async def get_text_encoders():
model_name = "black-forest-labs/FLUX.1-dev"
revision = "refs/pr/3"
text_encoder = CLIPTextModel.from_pretrained("openai/clip-vit-large-patch14", torch_dtype=dtype)
tokenizer = CLIPTokenizer.from_pretrained("openai/clip-vit-large-patch14", torch_dtype=dtype)
text_encoder_2 = T5EncoderModel.from_pretrained(model_name, subfolder="text_encoder_2", torch_dtype=dtype,
revision=revision)
tokenizer_2 = T5TokenizerFast.from_pretrained(model_name, subfolder="tokenizer_2", torch_dtype=dtype,
revision=revision)
return text_encoder, tokenizer, text_encoder_2, tokenizer_2
Logs
System Info
- 🤗 Diffusers version: 0.33.1
- Platform: Linux-6.8.0-60-generic-x86_64-with-glibc2.39
- Running on Google Colab?: No
- Python version: 3.12.3
- PyTorch version (GPU?): 2.7.0+cu126 (True)
- Flax version (CPU?/GPU?/TPU?): not installed (NA)
- Jax version: not installed
- JaxLib version: not installed
- Huggingface_hub version: 0.31.2
- Transformers version: 4.51.3
- Accelerate version: 1.7.0
- PEFT version: 0.15.2
- Bitsandbytes version: 0.45.5
- Safetensors version: 0.5.3
- xFormers version: not installed
- Accelerator: NVIDIA GeForce RTX 3090, 24576 MiB
- Using GPU in script?:
- Using distributed or parallel set-up in script?: