support flux.1-kera-dev

2026-03-18 22:08:13 +00:00 · 2025-08-01 11:26:39 +08:00
parent f0ea049faa
commit b63f81c6e3
10 changed files with 126 additions and 0 deletions
--- a/examples/flux/README.md
+++ b/examples/flux/README.md
@@ -44,6 +44,7 @@ image.save("image.jpg")
 |Model ID|Extra Args|Inference|Low VRAM Inference|Full Training|Validation after Full Training|LoRA Training|Validation after LoRA Training|
 |-|-|-|-|-|-|-|-|
 |[FLUX.1-dev](https://www.modelscope.cn/models/black-forest-labs/FLUX.1-dev)||[code](./model_inference/FLUX.1-dev.py)|[code](./model_inference_low_vram/FLUX.1-dev.py)|[code](./model_training/full/FLUX.1-dev.sh)|[code](./model_training/validate_full/FLUX.1-dev.py)|[code](./model_training/lora/FLUX.1-dev.sh)|[code](./model_training/validate_lora/FLUX.1-dev.py)|
+|[FLUX.1-Kera-dev](https://www.modelscope.cn/models/black-forest-labs/FLUX.1-Krea-dev)||[code](./model_inference/FLUX.1-Kera-dev.py)|[code](./model_inference_low_vram/FLUX.1-Kera-dev.py)|[code](./model_training/full/FLUX.1-Kera-dev.sh)|[code](./model_training/validate_full/FLUX.1-Kera-dev.py)|[code](./model_training/lora/FLUX.1-Kera-dev.sh)|[code](./model_training/validate_lora/FLUX.1-Kera-dev.py)|
 |[FLUX.1-Kontext-dev](https://www.modelscope.cn/models/black-forest-labs/FLUX.1-Kontext-dev)|`kontext_images`|[code](./model_inference/FLUX.1-Kontext-dev.py)|[code](./model_inference_low_vram/FLUX.1-Kontext-dev.py)|[code](./model_training/full/FLUX.1-Kontext-dev.sh)|[code](./model_training/validate_full/FLUX.1-Kontext-dev.py)|[code](./model_training/lora/FLUX.1-Kontext-dev.sh)|[code](./model_training/validate_lora/FLUX.1-Kontext-dev.py)|
 |[FLUX.1-dev-Controlnet-Inpainting-Beta](https://www.modelscope.cn/models/alimama-creative/FLUX.1-dev-Controlnet-Inpainting-Beta)|`controlnet_inputs`|[code](./model_inference/FLUX.1-dev-Controlnet-Inpainting-Beta.py)|[code](./model_inference_low_vram/FLUX.1-dev-Controlnet-Inpainting-Beta.py)|[code](./model_training/full/FLUX.1-dev-Controlnet-Inpainting-Beta.sh)|[code](./model_training/validate_full/FLUX.1-dev-Controlnet-Inpainting-Beta.py)|[code](./model_training/lora/FLUX.1-dev-Controlnet-Inpainting-Beta.sh)|[code](./model_training/validate_lora/FLUX.1-dev-Controlnet-Inpainting-Beta.py)|
 |[FLUX.1-dev-Controlnet-Union-alpha](https://www.modelscope.cn/models/InstantX/FLUX.1-dev-Controlnet-Union-alpha)|`controlnet_inputs`|[code](./model_inference/FLUX.1-dev-Controlnet-Union-alpha.py)|[code](./model_inference_low_vram/FLUX.1-dev-Controlnet-Union-alpha.py)|[code](./model_training/full/FLUX.1-dev-Controlnet-Union-alpha.sh)|[code](./model_training/validate_full/FLUX.1-dev-Controlnet-Union-alpha.py)|[code](./model_training/lora/FLUX.1-dev-Controlnet-Union-alpha.sh)|[code](./model_training/validate_lora/FLUX.1-dev-Controlnet-Union-alpha.py)|
--- a/examples/flux/README_zh.md
+++ b/examples/flux/README_zh.md
@@ -44,6 +44,7 @@ image.save("image.jpg")
 |模型 ID|额外参数|推理|低显存推理|全量训练|全量训练后验证|LoRA 训练|LoRA 训练后验证|
 |-|-|-|-|-|-|-|-|
 |[FLUX.1-dev](https://www.modelscope.cn/models/black-forest-labs/FLUX.1-dev)||[code](./model_inference/FLUX.1-dev.py)|[code](./model_inference_low_vram/FLUX.1-dev.py)|[code](./model_training/full/FLUX.1-dev.sh)|[code](./model_training/validate_full/FLUX.1-dev.py)|[code](./model_training/lora/FLUX.1-dev.sh)|[code](./model_training/validate_lora/FLUX.1-dev.py)|
+|[FLUX.1-Kera-dev](https://www.modelscope.cn/models/black-forest-labs/FLUX.1-Krea-dev)||[code](./model_inference/FLUX.1-Kera-dev.py)|[code](./model_inference_low_vram/FLUX.1-Kera-dev.py)|[code](./model_training/full/FLUX.1-Kera-dev.sh)|[code](./model_training/validate_full/FLUX.1-Kera-dev.py)|[code](./model_training/lora/FLUX.1-Kera-dev.sh)|[code](./model_training/validate_lora/FLUX.1-Kera-dev.py)|
 |[FLUX.1-Kontext-dev](https://www.modelscope.cn/models/black-forest-labs/FLUX.1-Kontext-dev)|`kontext_images`|[code](./model_inference/FLUX.1-Kontext-dev.py)|[code](./model_inference_low_vram/FLUX.1-Kontext-dev.py)|[code](./model_training/full/FLUX.1-Kontext-dev.sh)|[code](./model_training/validate_full/FLUX.1-Kontext-dev.py)|[code](./model_training/lora/FLUX.1-Kontext-dev.sh)|[code](./model_training/validate_lora/FLUX.1-Kontext-dev.py)|
 |[FLUX.1-dev-Controlnet-Inpainting-Beta](https://www.modelscope.cn/models/alimama-creative/FLUX.1-dev-Controlnet-Inpainting-Beta)|`controlnet_inputs`|[code](./model_inference/FLUX.1-dev-Controlnet-Inpainting-Beta.py)|[code](./model_inference_low_vram/FLUX.1-dev-Controlnet-Inpainting-Beta.py)|[code](./model_training/full/FLUX.1-dev-Controlnet-Inpainting-Beta.sh)|[code](./model_training/validate_full/FLUX.1-dev-Controlnet-Inpainting-Beta.py)|[code](./model_training/lora/FLUX.1-dev-Controlnet-Inpainting-Beta.sh)|[code](./model_training/validate_lora/FLUX.1-dev-Controlnet-Inpainting-Beta.py)|
 |[FLUX.1-dev-Controlnet-Union-alpha](https://www.modelscope.cn/models/InstantX/FLUX.1-dev-Controlnet-Union-alpha)|`controlnet_inputs`|[code](./model_inference/FLUX.1-dev-Controlnet-Union-alpha.py)|[code](./model_inference_low_vram/FLUX.1-dev-Controlnet-Union-alpha.py)|[code](./model_training/full/FLUX.1-dev-Controlnet-Union-alpha.sh)|[code](./model_training/validate_full/FLUX.1-dev-Controlnet-Union-alpha.py)|[code](./model_training/lora/FLUX.1-dev-Controlnet-Union-alpha.sh)|[code](./model_training/validate_lora/FLUX.1-dev-Controlnet-Union-alpha.py)|
--- a/examples/flux/model_inference/FLUX.1-Kera-dev.py
+++ b/examples/flux/model_inference/FLUX.1-Kera-dev.py
@@ -0,0 +1,27 @@
+import torch
+from diffsynth.pipelines.flux_image_new import FluxImagePipeline, ModelConfig
+
+
+pipe = FluxImagePipeline.from_pretrained(
+    torch_dtype=torch.bfloat16,
+    device="cuda",
+    model_configs=[
+        ModelConfig(model_id="black-forest-labs/FLUX.1-Krea-dev", origin_file_pattern="flux1-krea-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"),
+    ],
+)
+
+prompt = "An beautiful woman is riding a bicycle in a park, wearing a red dress"
+negative_prompt = "worst quality, low quality, monochrome, zombie, interlocked fingers, Aissist, cleavage, nsfw,"
+
+image = pipe(prompt=prompt, seed=0, embedded_guidance=4.5)
+image.save("flux_kera.jpg")
+
+image = pipe(
+    prompt=prompt, negative_prompt=negative_prompt,
+    seed=0, cfg_scale=2, num_inference_steps=50,
+    embedded_guidance=4.5
+)
+image.save("flux_kera_cfg.jpg")
--- a/examples/flux/model_inference_low_vram/FLUX.1-Kera-dev.py
+++ b/examples/flux/model_inference_low_vram/FLUX.1-Kera-dev.py
@@ -0,0 +1,28 @@
+import torch
+from diffsynth.pipelines.flux_image_new import FluxImagePipeline, ModelConfig
+
+
+pipe = FluxImagePipeline.from_pretrained(
+    torch_dtype=torch.bfloat16,
+    device="cuda",
+    model_configs=[
+        ModelConfig(model_id="black-forest-labs/FLUX.1-Krea-dev", origin_file_pattern="flux1-krea-dev.safetensors"),
+        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder/model.safetensors", offload_device="cpu", offload_dtype=torch.float8_e4m3fn),
+        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder_2/", offload_device="cpu", offload_dtype=torch.float8_e4m3fn),
+        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="ae.safetensors", offload_device="cpu", offload_dtype=torch.float8_e4m3fn),
+    ],
+)
+pipe.enable_vram_management()
+
+prompt = "An beautiful woman is riding a bicycle in a park, wearing a red dress"
+negative_prompt = "worst quality, low quality, monochrome, zombie, interlocked fingers, Aissist, cleavage, nsfw,"
+
+image = pipe(prompt=prompt, seed=0, embedded_guidance=4.5)
+image.save("flux_kera.jpg")
+
+image = pipe(
+    prompt=prompt, negative_prompt=negative_prompt,
+    seed=0, cfg_scale=2, num_inference_steps=50,
+    embedded_guidance=4.5
+)
+image.save("flux_kera_cfg.jpg")
--- a/examples/flux/model_training/full/FLUX.1-Kera-dev.sh
+++ b/examples/flux/model_training/full/FLUX.1-Kera-dev.sh
@@ -0,0 +1,12 @@
+accelerate launch --config_file examples/flux/model_training/full/accelerate_config.yaml examples/flux/model_training/train.py \
+  --dataset_base_path data/example_image_dataset \
+  --dataset_metadata_path data/example_image_dataset/metadata.csv \
+  --max_pixels 1048576 \
+  --dataset_repeat 400 \
+  --model_id_with_origin_paths "black-forest-labs/FLUX.1-Krea-dev:flux1-krea-dev.safetensors,black-forest-labs/FLUX.1-dev:text_encoder/model.safetensors,black-forest-labs/FLUX.1-dev:text_encoder_2/,black-forest-labs/FLUX.1-dev:ae.safetensors" \
+  --learning_rate 1e-5 \
+  --num_epochs 1 \
+  --remove_prefix_in_ckpt "pipe.dit." \
+  --output_path "./models/train/FLUX.1-Kera-dev_full" \
+  --trainable_models "dit" \
+  --use_gradient_checkpointing
--- a/examples/flux/model_training/lora/FLUX.1-Kera-dev.sh
+++ b/examples/flux/model_training/lora/FLUX.1-Kera-dev.sh
@@ -0,0 +1,15 @@
+accelerate launch examples/flux/model_training/train.py \
+  --dataset_base_path data/example_image_dataset \
+  --dataset_metadata_path data/example_image_dataset/metadata.csv \
+  --max_pixels 1048576 \
+  --dataset_repeat 50 \
+  --model_id_with_origin_paths "black-forest-labs/FLUX.1-Krea-dev:flux1-krea-dev.safetensors,black-forest-labs/FLUX.1-dev:text_encoder/model.safetensors,black-forest-labs/FLUX.1-dev:text_encoder_2/,black-forest-labs/FLUX.1-dev:ae.safetensors" \
+  --learning_rate 1e-4 \
+  --num_epochs 5 \
+  --remove_prefix_in_ckpt "pipe.dit." \
+  --output_path "./models/train/FLUX.1-Kera-dev_lora" \
+  --lora_base_model "dit" \
+  --lora_target_modules "a_to_qkv,b_to_qkv,ff_a.0,ff_a.2,ff_b.0,ff_b.2,a_to_out,b_to_out,proj_out,norm.linear,norm1_a.linear,norm1_b.linear,to_qkv_mlp" \
+  --lora_rank 32 \
+  --align_to_opensource_format \
+  --use_gradient_checkpointing
--- a/examples/flux/model_training/validate_full/FLUX.1-Kera-dev.py
+++ b/examples/flux/model_training/validate_full/FLUX.1-Kera-dev.py
@@ -0,0 +1,20 @@
+import torch
+from diffsynth.pipelines.flux_image_new import FluxImagePipeline, ModelConfig
+from diffsynth import load_state_dict
+
+
+pipe = FluxImagePipeline.from_pretrained(
+    torch_dtype=torch.bfloat16,
+    device="cuda",
+    model_configs=[
+        ModelConfig(model_id="black-forest-labs/FLUX.1-Krea-dev", origin_file_pattern="flux1-krea-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"),
+    ],
+)
+state_dict = load_state_dict("models/train/FLUX.1-Kera-dev_full/epoch-0.safetensors")
+pipe.dit.load_state_dict(state_dict)
+
+image = pipe(prompt="a dog", seed=0)
+image.save("image_FLUX.1-Kera-dev_full.jpg")
--- a/examples/flux/model_training/validate_lora/FLUX.1-Kera-dev.py
+++ b/examples/flux/model_training/validate_lora/FLUX.1-Kera-dev.py
@@ -0,0 +1,18 @@
+import torch
+from diffsynth.pipelines.flux_image_new import FluxImagePipeline, ModelConfig
+
+
+pipe = FluxImagePipeline.from_pretrained(
+    torch_dtype=torch.bfloat16,
+    device="cuda",
+    model_configs=[
+        ModelConfig(model_id="black-forest-labs/FLUX.1-Krea-dev", origin_file_pattern="flux1-krea-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"),
+    ],
+)
+pipe.load_lora(pipe.dit, "models/train/FLUX.1-Kera-dev_lora/epoch-4.safetensors", alpha=1)
+
+image = pipe(prompt="a dog", seed=0)
+image.save("image_FLUX.1-Kera-dev_lora.jpg")