import torch
from diffusers import ModularPipeline

pipe = ModularPipeline.from_pretrained("black-forest-labs/flux-3-image-klein-base")
pipe.load_components(dtype={"vae": torch.float32, "default": torch.bfloat16})
pipe.to("cuda")

image = pipe(
    prompt="A red fox in a snow-covered forest clearing at golden hour",
    generator=torch.Generator().manual_seed(0),
    output="images",
)[0]
image.save("fox.png")

out = pipe(
    prompt="A red fox in a snow-covered forest clearing at golden hour",
    generator=torch.Generator().manual_seed(0),
    output=["images", "prompt"],
)
print(out["prompt"])

Full-color outdoor wildlife photograph taken from a low eye-level perspective in a snow-covered forest clearing at golden hour. In the center foreground, a red fox stands in profile facing left, its body turned toward the viewer and its head raised as it looks across the clearing. The fox has dense rust-red winter fur, a white throat and chest, black lower legs, pointed ears with dark tips, and a long bushy tail ending in white. ...

print(pipe.blocks.sub_blocks["prompt_upsampler"].doc)

  Inputs:
      prompt (`str`):
          The edit instruction to expand into the full caption (one per call).
      image (`Image | list`, *optional*):
          The reference image(s) of the edit, at most 10; the same ones the pipeline receives.
      boxes (`list`, *optional*):
          Layout boxes, each {'id', 'desc', 'from', 'src_bbox', 'tgt_bbox'} with the boxes as [y_min, x_min, y_max, x_max] in
          0-1: ...
      max_new_tokens (`int`, *optional*, defaults to 3584):
          The most tokens the upsampler may generate for the caption.

  Outputs:
      prompt (`str`):
          The full caption, replacing the request.

blocks = ModularPipeline.from_pretrained("black-forest-labs/flux-3-image-klein-base").blocks
pup_block = blocks.sub_blocks.pop("prompt_upsampler")

pup = pup_block.init_pipeline("black-forest-labs/flux-3-image-klein-base")
pup.load_components(dtype=torch.bfloat16)
pup.to("cuda")
caption = pup(prompt="A red fox in a snow-covered forest clearing at golden hour", output="prompt")

pipe = blocks.init_pipeline("black-forest-labs/flux-3-image-klein-base")
pipe.load_components(dtype={"vae": torch.float32, "default": torch.bfloat16})
pipe.to("cuda")
image = pipe(prompt=caption, generator=torch.Generator().manual_seed(0), output="images")[0]

night = pipe(
    prompt="the same scene at night under a full moon",
    image=image,
    generator=torch.Generator().manual_seed(0),
    output=["images", "prompt"],
)

combined = pipe(
    prompt="the fox from the first image sitting on the wooden bench from the second image",
    image=[image, bench],
    height=768,
    width=1360,
    output="images",
)[0]

boxes = [
    {"id": "balloon_1", "desc": "a red and yellow striped hot-air balloon", "bbox": [0.08, 0.06, 0.48, 0.38]},
    {"id": "balloon_2", "desc": "a small blue hot-air balloon", "bbox": [0.20, 0.62, 0.42, 0.80]},
]
out = pipe(prompt="hot-air balloons over a green valley at sunrise", boxes=boxes, output=["images", "prompt"])

boxes = [{"id": "cactus", "desc": "a small potted cactus", "from": "target", "src_bbox": None, "tgt_bbox": [0.55, 0.62, 0.85, 0.85]}]
out = pipe(prompt="add a small potted cactus in the marked spot", image=mug, boxes=boxes, output=["images", "prompt"])

boxes = [{"id": "knight", "desc": "the knight figure", "from": "ref_image_0", "src_bbox": [0.50, 0.15, 0.85, 0.35], "tgt_bbox": [0.19, 0.06, 0.54, 0.26]}]
out = pipe(prompt="move the knight up and to the left, keep the rest unchanged", image=knight, boxes=boxes, output=["images", "prompt"])

pipe.guider = pipe.guider.new(guidance_scale=5.0)

pipe = ModularPipeline.from_pretrained("black-forest-labs/flux-3-image-klein")
pipe.load_components(dtype=torch.bfloat16)
pipe.to("cuda")

image = pipe(prompt=prompt, generator=torch.Generator().manual_seed(0), output="images")[0]

height, width = 1024, 1024
h, w = height // 16, width // 16

noise = torch.randn((h * w, 128), generator=torch.Generator().manual_seed(0)).to(torch.bfloat16)
latents = noise.T.reshape(1, 128, h, w)

image = pipe(prompt=prompt, latents=latents, height=height, width=width, output="images")[0]

from diffusers.modular_pipelines import Flux3AutoBlocks

print(Flux3AutoBlocks().available_workflows)
# ["text2image", "image_conditioned"]

t2i = ModularPipeline.from_pretrained("black-forest-labs/flux-3-image-klein-base", workflow="text2image")
print(t2i.blocks.doc)

blocks = Flux3AutoBlocks()  # or Flux3DistilledAutoBlocks
for loop in walk_denoise_loops(blocks):
    loop.sub_blocks["callback"] = CallbackOnStepEnd()
pipe = blocks.init_pipeline("black-forest-labs/flux-3-image-klein-base")

image = pipe(prompt=caption, callback_on_step_end=my_callback, output="images")[0]

from diffusers import ComponentsManager, ModularPipeline

manager = ComponentsManager()
pipe = ModularPipeline.from_pretrained("black-forest-labs/flux-3-image-klein-base", components_manager=manager)
pipe.load_components(dtype={"vae": torch.float32, "default": torch.bfloat16})
manager.enable_auto_cpu_offload(device="cuda")

import torch
from diffusers import Flux3Transformer2DModel, ModularPipeline

transformer = Flux3Transformer2DModel.from_single_file(
    "https://huggingface.co/black-forest-labs/flux-3-image-klein-base/blob/main/model.safetensors",
    config="black-forest-labs/flux-3-image-klein-base",
    subfolder="transformer",
    dtype=torch.bfloat16,
)

pipe = ModularPipeline.from_pretrained("black-forest-labs/flux-3-image-klein-base")
pipe.load_components(dtype={"vae": torch.float32, "default": torch.bfloat16})
pipe.update_components(transformer=transformer)
pipe.to("cuda")

from diffusers import BFLQuantizationConfig

transformer = Flux3Transformer2DModel.from_single_file(
    "https://huggingface.co/black-forest-labs/flux-3-image-klein-base/blob/main/variants/nvfp4/model.safetensors",
    config="black-forest-labs/flux-3-image-klein-base",
    subfolder="transformer",
    quantization_config=BFLQuantizationConfig(compute_dtype=torch.bfloat16),
    dtype=torch.bfloat16,
)

transformer = Flux3Transformer2DModel.from_single_file(
    "https://huggingface.co/black-forest-labs/flux-3-image-klein/blob/main/variants/nvfp4/model.safetensors",
    config="black-forest-labs/flux-3-image-klein",
    subfolder="transformer",
    quantization_config=BFLQuantizationConfig(compute_dtype=torch.bfloat16),
    dtype=torch.bfloat16,
)