anima_pencil-XL版本v3.0.0 (ID: 435001)

Easy, Simple, High Quality (with a slight trade-off in variety)

blue_pencil-XL meets ANIMAGINE XL 3.0 /ANIMAGINE XL 3.1

---

License: Fair AI Public License 1.0-SD
You should share the merge recipe if you release a model merged with anima_pencil-XL.
This license does not add any restrictions on your generated images.
For more details, please see the license section of ANIMAGINE XL 3.0.

Please see the "About this Version" section for information on each version.

`No generation services` only apply to v2.0.0

---

HuggingFace: https://huggingface.co/bluepen5805/anima_pencil-XL

---

Why not merge ANIMAGINE XL 3.X into blue_pencil-XL?

I want to provide blue_pencil-XL under the CreativeML Open RAIL++-M license.

描述:

recommend to decrease CFG scale.

# Checkpoints

• blue_pencil-XL-v6.0.0

• anima_pencil-XL-v1.0.0

• ANIMAGINE XL 3.1

• ANIMAGINE XL 3.0

• ANIMAGINE XL 2.0

• Anime Illust Diffusion XL v0.8

• /Anime/bulldozer_BETA v2.0

• SwampMachine v2.0

• AAM XL Anime Mix v1.0

• AbyssOrange XL Else v1.0

• ShiratakiMix XL v1.0

• LizMix v4.0

# LoRAs

• self-made QualitySlider (Concept Sliders)

• flat_sdxl v1.0

• Aesthetic Anime LoRA v1s

# Recipe

1. blue_pencil-XL-v6.0.0 + ( ANIMAGINE XL 3.0 - ANIMAGINE XL 2.0 ) x 1.0, Add difference(trainDifference)

2. [1] + ( ANIMAGINE XL 3.1 - ANIMAGINE XL 3.0 ) x 1.0, Add difference(trainDifference)

3. ( blue_pencil-XL-v5.0.0 x 0.3 ) + ( [2] x 0.7 ), Weight sum(cosineA), Elemental: "BASE:conditioner.embedders.0.transformer:0.3,BASE:conditioner.embedders.1.model:0.85"

4. [3] + ( Anime Illust Diffusion XL v0.8 - ANIMAGINE XL 3.0 ) x 0.2, Add difference(trainDifference)

5. [4] + ( /Anime/bulldozer_BETA v2.0 - ANIMAGINE XL 3.0 ) x 0.3, Add difference(trainDifference)

6. [5] + ( SwampMachine v2.0 - ANIMAGINE XL 3.0 ) x 0.2, Add difference(trainDifference)

7. [6] + ( AAM XL Anime Mix v1.0 - ANIMAGINE XL 3.0 ) x 0.4, Add difference(trainDifference)

8. [7] + ( AbyssOrange XL Else v1.0 - ANIMAGINE XL 3.0 ) x 0.2, Add difference(trainDifference)

9. ( [8] x 0.7 ) + ( ShiratakiMix XL v1.0 v1.0 x 0.3 ), Weight sum(cosineA)

10. ( [9] x 0.7 ) + ( LizMix v4.0 x 0.3 ), Weight sum(cosineA)

11. ( [10] x 0.45 ) + ( [3] x 0.55 ), Weight sum(cosineB), Elemental: "BASE:conditioner.embedders.0.transformer:0.9,BASE:conditioner.embedders.1.model:0.1"

12. [11] + ( QualitySlider + flat_sdxl v1.0:-0.15 + Aesthetic Anime LoRA v1s:0.05)

13. [12] x 0.95 + ( anima_pencil-XL-v1.0.0 x 0.05), Weight sum(cosineA)

训练词语: