Merge branch 'flux-refactor' into flux-refactor

examples/flux/FLUX.1-dev-Controlnet-Inpainting-Beta.py

@@ -0,0 +1,37 @@
+import torch
+from diffsynth.pipelines.flux_image_new import FluxImagePipeline, ModelConfig, ControlNetInput
+import numpy as np
+from PIL import Image
+
+
+pipe = FluxImagePipeline.from_pretrained(
+    torch_dtype=torch.bfloat16,
+    device="cuda",
+    model_configs=[
+        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="flux1-dev.safetensors"),
+        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder/model.safetensors"),
+        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder_2/"),
+        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="ae.safetensors"),
+        ModelConfig(model_id="alimama-creative/FLUX.1-dev-Controlnet-Inpainting-Beta", origin_file_pattern="diffusion_pytorch_model.safetensors"),
+    ],
+)
+
+image_1 = pipe(
+    prompt="a cat sitting on a chair",
+    height=1024, width=1024,
+    seed=8, rand_device="cuda",
+)
+image_1.save("image_1.jpg")
+
+mask = np.zeros((1024, 1024, 3), dtype=np.uint8)
+mask[100:350, 350: -300] = 255
+mask = Image.fromarray(mask)
+mask.save("mask.jpg")
+
+image_2 = pipe(
+    prompt="a cat sitting on a chair, wearing sunglasses",
+    controlnet_inputs=[ControlNetInput(image=image_1, inpaint_mask=mask, scale=0.9)],
+    height=1024, width=1024,
+    seed=9, rand_device="cuda",
+)
+image_2.save("image_2.jpg")

examples/flux/FLUX.1-dev-Controlnet-Union-alpha.py

@@ -0,0 +1,40 @@
+import torch
+from diffsynth.pipelines.flux_image_new import FluxImagePipeline, ModelConfig, ControlNetInput
+from diffsynth.controlnets.processors import Annotator
+from diffsynth import download_models
+
+
+
+download_models(["Annotators:Depth"])
+pipe = FluxImagePipeline.from_pretrained(
+    torch_dtype=torch.bfloat16,
+    device="cuda",
+    model_configs=[
+        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="flux1-dev.safetensors"),
+        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder/model.safetensors"),
+        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder_2/"),
+        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="ae.safetensors"),
+        ModelConfig(model_id="InstantX/FLUX.1-dev-Controlnet-Union-alpha", origin_file_pattern="diffusion_pytorch_model.safetensors"),
+    ],
+)
+
+image_1 = pipe(
+    prompt="a beautiful Asian girl, full body, red dress, summer",
+    height=1024, width=1024,
+    seed=6, rand_device="cuda",
+)
+image_1.save("image_1.jpg")
+
+image_canny = Annotator("canny")(image_1)
+image_depth = Annotator("depth")(image_1)
+
+image_2 = pipe(
+    prompt="a beautiful Asian girl, full body, red dress, winter",
+    controlnet_inputs=[
+        ControlNetInput(image=image_canny, scale=0.3, processor_id="canny"),
+        ControlNetInput(image=image_depth, scale=0.3, processor_id="depth"),
+    ],
+    height=1024, width=1024,
+    seed=7, rand_device="cuda",
+)
+image_2.save("image_2.jpg")

examples/flux/FLUX.1-dev-Controlnet-Upscaler.py

@@ -0,0 +1,33 @@
+import torch
+from diffsynth.pipelines.flux_image_new import FluxImagePipeline, ModelConfig, ControlNetInput
+
+
+pipe = FluxImagePipeline.from_pretrained(
+    torch_dtype=torch.bfloat16,
+    device="cuda",
+    model_configs=[
+        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="flux1-dev.safetensors"),
+        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder/model.safetensors"),
+        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder_2/"),
+        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="ae.safetensors"),
+        ModelConfig(model_id="jasperai/Flux.1-dev-Controlnet-Upscaler", origin_file_pattern="diffusion_pytorch_model.safetensors"),
+    ],
+)
+
+image_1 = pipe(
+    prompt="a photo of a cat, highly detailed",
+    height=768, width=768,
+    seed=0, rand_device="cuda",
+)
+image_1.save("image_1.jpg")
+
+image_1 = image_1.resize((2048, 2048))
+image_2 = pipe(
+    prompt="a photo of a cat, highly detailed",
+    controlnet_inputs=[ControlNetInput(image=image_1, scale=0.7)],
+    input_image=image_1,
+    denoising_strength=0.99,
+    height=2048, width=2048, tiled=True,
+    seed=1, rand_device="cuda",
+)
+image_2.save("image_2.jpg")

examples/flux/FLUX.1-dev.py

@@ -1,8 +1,5 @@
 import torch
-from PIL import Image
-from diffsynth import save_video, VideoData
 from diffsynth.pipelines.flux_image_new import FluxImagePipeline, ModelConfig
-from modelscope import dataset_snapshot_download
 
 
 pipe = FluxImagePipeline.from_pretrained(
@@ -16,8 +13,14 @@ pipe = FluxImagePipeline.from_pretrained(
     ],
 )
 
+prompt = "CG, masterpiece, best quality, solo, long hair, wavy hair, silver hair, blue eyes, blue dress, medium breasts, dress, underwater, air bubble, floating hair, refraction, portrait. The girl's flowing silver hair shimmers with every color of the rainbow and cascades down, merging with the floating flora around her."
+negative_prompt = "worst quality, low quality, monochrome, zombie, interlocked fingers, Aissist, cleavage, nsfw,"
+
+image = pipe(prompt=prompt, seed=0)
+image.save("flux.jpg")
+
 image = pipe(
-    prompt="a girl",
-    seed=0,
+    prompt=prompt, negative_prompt=negative_prompt,
+    seed=0, cfg_scale=2, num_inference_steps=50,
 )
-image.save("0.jpg")
+image.save("flux_cfg.jpg")