RedCraft & DarkBeast H3|Z|Klein LoRAs Collect
The Civitai H3 Training Contest
Submitted LoRA for H3 base & H3 RedCraft
Trigger word: ‘Exploded View Diagram’ , weight 0.7-1
General prompt :
Exploded View Diagram, For the target video, at 0.00 seconds into the target video, <Picture 1> (from [Shot 1]) is fully referenced.
integrated_multimodal_description: [Shot 1] Photoreal studio cinema, VFX already locked to <Picture 1>: [SUBJECT] already whole at the center, already the same form as in the still. Setting and existing markings already as in the still. No new lettering. A studio camera already starts a slow 180-degree orbit around the center, small amplitude, slow speed, one continuous move, no cut. Through the first part of the orbit: already [SUBJECT] comes apart fast along its own structure, already a wide scatter, already [KEY PARTS] fly far outward in every direction and stay readable, already each piece turns as it leaves. Through the middle: already the pieces hold wide apart, already a broad opened view, already the inner structure is clear. Through the last part: already the same pieces travel back from that wide scatter along those paths and seat into one whole again, already the orbit finishes the 180. Hold on the reassembled subject. No captions, titles, subtitles, or watermarks beyond markings already in <Picture 1>.
overall_soundscape: Parts leaving fast, a short open hush, pieces seating back together from far out, a soft studio hum, no speech.
non_diegetic_music: none.
站内活动链接( on-site event )：
Civitai H3 Contest: 2 Million Buzz and Half-Price H3 Generation
The Civitai H3 Training Contest
投稿作品收藏夹( Submitted LoRAs Collection )：
https://civarchive.com/collections/17983600
All entries must be LoRAs trained on MiniMax H3. Train locally, or with our on-site trainer, which supports H3 today.
All submissions must be SFW and must abide by Civitai's Terms of Service
Metafilm`s CATEGORICALINDEX 》
Grouped by base model, bases ordered by first production use (newest first); brands inside each base ordered by heat (total downloads); works inside each brand newest first. 282 works across 21 base models.
Type tags: fine-tune / LoRA / 工作流 / ControlNet. Data collected 2026-10-23.
▍RedCraft 红潮 ⌝ ▍Dark Beast 黑兽 ⌝ ▍FineView 欢视 ⌝
GGUF/BF16 for Local Multimodal ENV
Drama Story2 on Krea 2 Turbo https://civarchive.com/models/452459/?modelVersionId=3393223 GGUF Q8
REDGPT for realistic drama stills https://civarchive.com/models/452459/?modelVersionId=3131246 GGUF Q8
Krea 2 mix from the 赤佬3 https://civarchive.com/models/958009/?modelVersionId=3139241 Q4KM
K2T BUZZDEAL build for commercial https://civarchive.com/models/958009/?modelVersionId=3331574 Q4KM
REDQW21 Turbo texture-fixed https://civarchive.com/models/3003597 BF16
REF2i Hyper photographic https://civarchive.com/models/3015888 BF16
K2T for colorful youth https://civarchive.com/models/2242173/?modelVersionId=3365025 Q4KM
FLUX.1 Fill inpainting https://civarchive.com/models/958009/?modelVersionId=1445047 Q4KM
De-distilled Flux.1 with Aesthetic https://civarchive.com/models/958009/?modelVersionId=1387169 Q4KM
Krea 2 hardcore Dark Beast 3 edition https://civarchive.com/models/2242173/?modelVersionId=3173268 BF16
ZImage Turbo hardcore https://civarchive.com/models/2242173/?modelVersionId=2699886 FP32/BF16
SDXL 1.0 entry in the Dark Beast https://civarchive.com/models/2242173/?modelVersionId=2712294 FP32/BF16
Retro SD 1.5 HD rebuild https://civarchive.com/models/958009/?modelVersionId=1298797 FP32/BF16
OpenMOSS MOSS-Image https://civarchive.com/models/3007993/?modelVersionId=3436921 BF16
MOSS 4 fêtesnap NSFH https://civarchive.com/models/3007993/?modelVersionId=3448658 BF16
Paid MiniMax H3 director package https://civarchive.com/models/1295569/?modelVersionId=3375757 BF16
做好工具人 服务艺术家
Dark Beast Z8 SDA 🟥 ZITLoRA Edition 03/15/2026
DBZ 8 SDA 完整模型BF16：
https://civarchive.com/models/2242173?modelVersionId=2774410
DBZ 8 SDA workflow 配套工作流链接：
https://civarchive.com/models/579280?modelVersionId=2742099
通过引用 @FOK 提出的新型 语义方向对齐（Semantic Directional Alignment, SDA）损失，本模型 merge 了 饼儿佬 训练的 LoKr 适配器，在完美保持 8 步基线模型极致锐度和快速推理速度的同时，恢复了 原始教师模型 70.2% 的组合多样性（LPIPS）
Designed to rescue the "Diversity Collapse" problem in few-step distilled Flow Matching / Diffusion models. By applying @FOK novel Semantic Directional Alignment (SDA) Loss, this Model adapter recovers 70.2% of the original teacher model's compositional diversity (LPIPS)
https://huggingface.co/F16/z-image-turbo-sda
https://modelscope.cn/models/FFFFFFoo/z-image-turbo-sda
Dark Beast KLEIN 9b 🟦 V2.0 BFS 03/03/2026
DBK v2 BFS最佳换脸工作流，配套模型：
https://civarchive.com/models/2242173
DBK BFS workflow 配套工作流链接：
https://civarchive.com/models/579280
This is the next-level face-swap specialized evolution of the Dark Beast lineage, built on the lightning-fast FLUX.2 Klein 9B accelerated model from Black Forest Labs.
Engineered with targeted optimizations for face swapping practices, it integrates BFS (Best Face Swap) technology to completely eliminate the rigid, unnatural look that plagued earlier face replacements — delivering seamless, lifelike integrations with preserved identity, expression, and lighting.
It also fully fixes the portrait reference issue from the previous DB BlitZ versions
Special thanks to the scheme provider: https://github.com/alisson-anjos for the powerful BFS foundation that powers this breakthrough.🟦
The author's In-site link: https://civarchive.com/user/NRDX
Important notes:
This version is exclusively designed around the Klein 9B accelerated edition — no base model exists.
Usage is identical to Black Forest Labs' official FLUX.2 Klein 9B accelerated release: ultra-low steps (e.g., 4-5), CFG=1 fixed, blazing inference speed on consumer hardware.
In one sentence: Dark Beast's ferocious soul meets BFS (Best Face Swap) technology — more natural, and truly unstoppable! 🟦
for more infomation about BFS (Best Face Swap) :
https://huggingface.co/Alissonerdx
Alternatively, it can be directly applied to the entire Klein 9b/Qwen Edit base and Fine-tune models, through LoRA Adapter parameter injection.
2024
RedCraft | 红潮 CADS Q4 GGUF Enhancer-LoRA
De-distill&CADS Commercial Materials
Support online generation of ComfyUI WebUI
matching：
RedCraft | 红潮 CADS Commercial & Advertising Design System
GGUF format Q4 quantization version
for 1024 x 1024 inference
better with This Pages ：RedCraft-Q4enhancer-LoRA
The LoRA weight setting range is from 0.2 to 0.65
Inference parameters:
10-20 STEPS Euler / DPM++2M | beta / SGM_Uniform
CFG 3-3.5
Real CFG needs to be set (ignore guidance, or set to 0)
Description
Adapted for H3 base & H3 RedCraft
Trigger word: ‘Exploded View Diagram’
LoRA weight: 0.7-1
General prompt :
Exploded View Diagram, For the target video, at 0.00 seconds into the target video, <Picture 1> (from [Shot 1]) is fully referenced.
integrated_multimodal_description: [Shot 1] Photoreal studio cinema, VFX already locked to <Picture 1>: [SUBJECT] already whole at the center, already the same form as in the still. Setting and existing markings already as in the still. No new lettering. A studio camera already starts a slow 180-degree orbit around the center, small amplitude, slow speed, one continuous move, no cut. Through the first part of the orbit: already [SUBJECT] comes apart fast along its own structure, already a wide scatter, already [KEY PARTS] fly far outward in every direction and stay readable, already each piece turns as it leaves. Through the middle: already the pieces hold wide apart, already a broad opened view, already the inner structure is clear. Through the last part: already the same pieces travel back from that wide scatter along those paths and seat into one whole again, already the orbit finishes the 180. Hold on the reassembled subject. No captions, titles, subtitles, or watermarks beyond markings already in <Picture 1>.
overall_soundscape: Parts leaving fast, a short open hush, pieces seating back together from far out, a soft studio hum, no speech.
non_diegetic_music: none.