Flux 2 / Klein KI-Modelle
FLUX.2 is Black Forest Labs' second generation: a larger text-to-image and editing model with native multi-reference input, far better text rendering, 4 megapixel output and a unified architecture that generates and edits in one pass. The dev weights are open, so the community has already trained more than a thousand FLUX.2 LoRAs. This page tracks them all: realism and skin detail, product and fashion looks, anime and illustration styles, plus the base checkpoints, ranked by heat so the LoRAs people are actually downloading this week rise to the top.
Heißeste Flux 2 / Klein-Modelle
Flux 2 / Klein-Anleitungen
Modelle
FLUX.2 Dev: prompting the newest Black Forest Labs model
FLUX.2 Dev brings larger prompts, better text, stronger realism and multi-reference editing. This guide covers the turbo workflow, guidance and resolution settings, prompt structure and ideas that use its new strengths.
Von Captain
2026-10-03
Modelle
What is a LoRA and how to use one in ComfyUI, Forge, Automatic1111 and on the cloud
LoRAs explained for people who want results, not maths: what a LoRA file changes, why it must match the base model's family, trigger words, weights, stacking several LoRAs, the folder and syntax for each UI, and how to try a LoRA on the cloud before downloading anything.
Von Captain
2026-05-20
Fehler & Lösungen
CUDA out of memory: how much VRAM each AI model needs and how to fit it
A VRAM table for SD 1.5, SDXL, Flux, FLUX.2, Qwen-Image, Z-Image, Wan 2.2 and HunyuanVideo, and the techniques that make a model fit: fp8 and GGUF quantisation, CPU offload, tiled VAE, resolution and frame limits, and when to stop fighting and run it hosted.
Von Captain
2026-05-18
Modelle
Flux vs SDXL vs SD 1.5 vs Qwen vs Z-Image: which model family to use in 2026
A practical comparison of the open image model families: prompt following, realism, anime and illustration, text rendering, speed, VRAM, LoRA ecosystem and licence, with a recommendation for each kind of work and hardware.
Von Captain
2026-05-22
Prompting
FLUX.2 prompting guide: natural-language prompts, multi-reference, editing and LoRAs
Prompting FLUX.2 dev for the results it is known for: paragraph prompts with subject, scene, light and lens, exact text in quotes, up to several reference images for products, people and styles, instruction-style edits, the guidance and step settings that matter, and how FLUX.2 LoRAs differ from Flux dev LoRAs.
Von Captain
2026-05-28
Fehler & Lösungen
VRAM requirements for every popular AI image and video model (2026): full precision, FP8 and GGUF
How much VRAM you need for SD 1.5, SDXL, SD 3.5, Z-Image Turbo, FLUX.1, FLUX.2 Klein and Dev, Qwen-Image, Wan 2.2, HunyuanVideo 1.5 and LTX-2, at full precision, FP8 and 4-bit GGUF, with the comfortable card and licence for each, what every GPU size from 8 to 48 GB can run, and the order of fixes when a model does not fit.
Von P.I. Panda
2026-10-06
AD
Keine Installation nötig – KI-Modelle in der Cloud ausführen
Keine GPU, keine Downloads, kein Python. Diese Dienste führen dieselben Open-Source-Modelle auf ihren eigenen Servern aus, sodass du in einer Minute im Browser, auf Discord oder Telegram loslegen kannst.
Weitere Modellfamilien
Text / LLM-Modelle
411
Anima-Modelle
366
Chroma-Modelle
12
Flux-Modelle
828
MiniMax H3-Modelle
152
Hunyuan-Modelle
104
Ideogram-Modelle
7
Krea2-Modelle
377
Qwen-Modelle
13
Qwen2-Modelle
26
Ltx2-Modelle
79
Stable Diffusion 1.5-Modelle
4,625
Stable Diffusion XL 1.0-Modelle
8,549
Zimage-Modelle
348
Wan-Modelle
342
ACE-Step-Modelle
2
AuK-Modelle
1
Boogu-Modelle
2
Chatterbox TTS-Modelle
1
Cosmos-Modelle
1
Ernie Image-Modelle
2
FireRed-Modelle
1
HeartMuLa-Modelle
1
HiDream-Modelle
3
Higgs Audio-Modelle
1
Lumina-Modelle
2
MiniMax Music-Modelle
1
MisoTTS-Modelle
1
Microsoft Lens-Modelle
1
PixelDiT-Modelle
1
Stable Diffusion 3.5-Modelle
3
Upscalers-Modelle
11
YuE-Modelle
2
Model
Trends
.ai
© ModelTrends.ai
|
Made in Japan
|
© 2026