repair_image_Flux.2-Klein9B_V2.safetensors

114 MB · SafeTensor

<image-repair2-flux2>

Fixed the issue, now it works with gguf models too Image Repair Flux.2-Klein9B Hey everyone! This is my second LoRa. So, I took the original idea from How it works: I trained this using a LoRA subtraction method (clean originals vs. degraded/pixelated versions). Because it extracts the exact "delta" of the degradation, it only targets the artifacts and noise without altering the core of image. It may not work with all images, on very complex detailed patterns it can hallucinate like the original flux2, try a different seed. Also, as you can see from the examples, the original flux2 saturation is poorly controlled. Training details: Latent: 512X512 (Also lora work with higher resolution and other aspect ratio) I tried 1024 latent size when training, but OOM forced me to optimize the settings. Lora rank: 16 Steps: 2000 Grad_accum: 4 Source images: 227 (all created in 2k/4k NanoBananaPro + Some Flux2.Kein9B) These settings were before lora was weakened. She was initially retrained. this is 0.3 Strength of original train. As with the author of the idea, all settings were created by a neural network (not chatgpt) and Python scripts were used for configuration. Recommended Settings: - LoRA Weight: 1.0 - Trigger Words: make image high quality - CFG: 1 - Steps: 4-6 I hope for positive feedback, but I hope you find this version useful. Also think it can be improved further. Later, soon... Do not use lora with the ImageScaleToTotalPixels node. Some image with this node is totally sh*t

SHA256

41BBB989B2515CEEB0A6B420B26B0C53F8F33EB03DE7DEE1F9E18B8B3A12F7C5

ModelTrends.ai Model ID

#25231

Steps

6

Guidance

1.2

Seed

12345

Size

1024x1024

Steps

6

Guidance

1.2

Seed

12345

Size

1024x1024

Steps

6

Guidance

1.2

Seed

12345

Size

1024x1024

Steps

6

Guidance

1.2

Seed

12345

Size

1024x1024

Sampler

er_sde

Steps

4

Guidance

1

Seed

12345

Size

1536x1024