- #1
- #2
flux2
FLUX.2 [dev] is Black Forest Labs' second-generation open-weights image model, released in November 2025. It is a much larger flow-matching transformer than FLUX.1 that uses the Mistral Small 3.1 vision-language model as its text encoder,…FLUX.2 [dev] is Black Forest Labs' second-generation open-weights image model, released in November 2025. It is a much larger flow-matching transformer than FLUX.1 that uses the Mistral Small 3.1 vision-language model as its text encoder, which gives it far better understanding of long, descriptive prompts, reliable multi-line typography and real-world knowledge about brands, materials and lighting. It was designed from the start as a unified model: the same weights generate from text, edit an existing picture from instructions, and combine up to ten reference images for character, product or style consistency, with output up to 4 megapixels. The family also includes the smaller FLUX.2 Klein 4B and 9B distillations that most Flux2 LoRAs in this catalog are trained on. This entry is the text-to-image workflow, accelerated with a turbo LoRA so that it finishes in a handful of steps.
- #3
flux
The fastest Flux DEV fp8 workflow, supports up to 5 loras. Built-in upscaler is a factor of 1.4, modify with /slot8 - #4
qwen
Qwen-Image is the image generation foundation model of Alibaba's Qwen team, released as open weights in August 2025. It is a 20-billion-parameter multimodal diffusion transformer that reads prompts through the Qwen2.5-VL vision-language…Qwen-Image is the image generation foundation model of Alibaba's Qwen team, released as open weights in August 2025. It is a 20-billion-parameter multimodal diffusion transformer that reads prompts through the Qwen2.5-VL vision-language model, and its headline strength is text: it renders long paragraphs, multi-line signs, posters and mixed Chinese and English typography with an accuracy no earlier open model reached. The same team's technical report also shows strong results for layout-heavy prompts, infographics and precise image editing, and the companion Qwen-Image-Edit model is the basis of many editing workflows. It generates natively around 1.3 to 1.6 megapixels in the usual aspect ratios and takes natural-language prompts rather than tag lists; the team recommends appending quality phrases such as 'Ultra HD, 4K, cinematic composition'. This entry is the version 2512 text-to-image workflow (the December 2025 refresh of the weights); the original release is kept as qwen-v1.
- #5
sdxl
Stable Diffusion XL version 1.0 is here, and the Refiner 1.0 is also installed. This is the official full release, but our software needs adjustment to fully support it. Only the /render command works and SDXL cannot be mixed with old…Stable Diffusion XL version 1.0 is here, and the Refiner 1.0 is also installed. This is the official full release, but our software needs adjustment to fully support it. Only the /render command works and SDXL cannot be mixed with old styles, recipes, loras, inversions, and other commands yet. Keep an eye on the XL news topic in Telegram VIP for more information
- #6
DeepSeek V4.1 Flash
DeepSeek | 1,048,576 token context | $0.04/M input, $0.68/M output. DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B…DeepSeek | 1,048,576 token context | $0.04/M input, $0.68/M output. DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on output from a 552B-parameter backbone, an asymmetric split that keeps per-token compute low relative to the model's total size. Image understanding is native to the architecture, with visual and text embeddings trained jointly from the start of pre-training rather than added afterward as in the earlier experimental V4 Flash Vision ExpOpens in new tab. It is suited for coding, terminal, and computer-use agents, along with long-horizon tasks that must run to completion across many steps and long-context analysis. Compressed KV caching cuts cache memory to roughly a quarter of the previous Flash generation, significantly reducing costs on agentic workloads. DeepSeek positions it as the cost-efficient tier of the V4.1 family and reports that it exceeds V4 ProOpens in new tab on performance, speed, and task completion time.
- #7
sdv15
Stable Diffusion 1.5 by Stability / RunwayML, the OG model. Someone said it was weird that we didn't have this in the concepts collection, and they were correct, so here you go! Of course, this model is over a year old, but it's still…Stable Diffusion 1.5 by Stability / RunwayML, the OG model. Someone said it was weird that we didn't have this in the concepts collection, and they were correct, so here you go! Of course, this model is over a year old, but it's still fantastic in its own right.
- #8
zimage turbo
Also known as "ZIT" -- Z-Image Turbo from Alibaba is a fast, low-steps general purpose realism text to image model. Doesn't support negative prompts. Works best at around 9 steps and 1 guidance at 1024x1024. - #9
ReV Animated
Rev Animated 2.0 is under new management - the project is now maintained by Zovya This is a remaster of the classic popular Revani series for SD15 - #10
Counterfeit V3.0
CounterfeitV3.0 by rqdwdw. The 3.0 version of Counterfeit has much brighter colors and more focus on the subject, whereas the previous model was more muted and pastel-like. The backgrounds look totally different in particular, so we're…CounterfeitV3.0 by rqdwdw. The 3.0 version of Counterfeit has much brighter colors and more focus on the subject, whereas the previous model was more muted and pastel-like. The backgrounds look totally different in particular, so we're going to keep both. It should be noted that there are 10 upvotes and 3 comments about green spots from users on Civitai.
- #11
Wan 2.1
Wan 2.1 is the February 2025 generation of Alibaba's open Wan video models: 1.3B and 14B weights for text-to-video and image-to-video. It has been superseded by Wan 2.2 (July 2025), which gives clearly better motion, detail and prompt…Wan 2.1 is the February 2025 generation of Alibaba's open Wan video models: 1.3B and 14B weights for text-to-video and image-to-video. It has been superseded by Wan 2.2 (July 2025), which gives clearly better motion, detail and prompt following with the same kind of workflows, so there is no reason to start with Wan 2.1 in 2026 or later. This page stays as a reference for the older LoRAs and workflows that were made for it.
- #12
GLM 5.3 Flash
Z.ai | 1,048,576 token context | $0.02/M input, $0.72/M output. GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks. Its hybrid sparse and linear attention architecture…Z.ai | 1,048,576 token context | $0.02/M input, $0.72/M output. GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks. Its hybrid sparse and linear attention architecture maintains accurate long-context behavior while reducing compute overhead. Yes, the stealth model Ox Alpha was revealed to be ZAI's new model, GLM-5.3 Flash.
- #13
Hy4 preview
Tencent | 1,048,576 token context | $0.83/M input, $2.50/M output. Tencent: Hy4 preview is a mixture-of-experts model from Tencent, with 49B active parameters out of 770B total. It is designed for coding agents, complex tool-use workflows,…Tencent | 1,048,576 token context | $0.83/M input, $2.50/M output. Tencent: Hy4 preview is a mixture-of-experts model from Tencent, with 49B active parameters out of 770B total. It is designed for coding agents, complex tool-use workflows, and productivity tasks that require planning, context continuity, and sustained multi-step execution.
- #14
MiMo V2.6 Flash
Xiaomi | 1.050.000 Token Kontext | $0,14/M Eingabe, $0,28/M Ausgabe. MiMo-V2.6-Flash ist ein Open-Source-Grundlagenmodell von Xiaomi. Es basiert auf einer Mixture-of-Experts-Architektur mit insgesamt 309 Mrd. Parametern und 15 Mrd.…Xiaomi | 1.050.000 Token Kontext | $0,14/M Eingabe, $0,28/M Ausgabe. MiMo-V2.6-Flash ist ein Open-Source-Grundlagenmodell von Xiaomi. Es basiert auf einer Mixture-of-Experts-Architektur mit insgesamt 309 Mrd. Parametern und 15 Mrd. aktivierten pro Token und verwendet einen hybriden Aufmerksamkeitsmechanismus für höhere Recheneffizienz. Das Modell verfügt über ein 1M-Token-Kontextfenster und native multimodale Fähigkeiten. Optimiert für agentische Workflows liefert es starke Leistungen in den Bereichen Coding, visuelle, allgemeine und Forschungs-Szenarien und glänzt bei komplexen Langzeitaufgaben mit robuster Generalisierung über eine vielfältige Bandbreite von Agenten-Anwendungen.
- #15
DeepSeek V4 Flash 0731
DeepSeek | 1,048,576 token context | $0.01/M input, $1.28/M output. DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for…DeepSeek | 1,048,576 token context | $0.01/M input, $1.28/M output. DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows. This is the GA release of DeepSeek V4 Flash.
- #16
- #17
- #18
Nemotron 3 Ultra
NVIDIA | 262.144 Token Kontext | $0,60/M Eingabe, $2,40/M Ausgabe. NVIDIA Nemotron 3 Ultra ist ein Open Frontier-Reasoning- und Orchestrierungsmodell von NVIDIA mit 55 Mrd. aktiven Parametern von insgesamt 550 Mrd. (MoE). Es basiert auf…NVIDIA | 262.144 Token Kontext | $0,60/M Eingabe, $2,40/M Ausgabe. NVIDIA Nemotron 3 Ultra ist ein Open Frontier-Reasoning- und Orchestrierungsmodell von NVIDIA mit 55 Mrd. aktiven Parametern von insgesamt 550 Mrd. (MoE). Es basiert auf einer hybriden Transformer-Mamba Mixture-of-Experts-Architektur und unterstützt Text-Ein- und Ausgabe mit einem Kontextfenster von bis zu 1M Tokens. Es eignet sich für langlaufende agentische Workflows, einschließlich Agenten-Orchestrierung, Coding-Agenten, tiefgehender Forschung und komplexer Unternehmensaufgaben. Besonders stark ist es bei mehrstufigem Reasoning und Planung, mit Hochdurchsatz-Inferenz für volumenstarke Agenten-Pipelines. Es ist Teil der NVIDIA Nemotron-Familie offener Modelle für agentische KI.
- #19
Step 5 Preview
StepFun | 1,048,576 token context | $1.00/M input, $2.70/M output. Step 5 Preview is StepFun's flagship model for agentic work, built on a sparse Mixture-of-Experts architecture (27B active / 600B total parameters). It performs strongly in…StepFun | 1,048,576 token context | $1.00/M input, $2.70/M output. Step 5 Preview is StepFun's flagship model for agentic work, built on a sparse Mixture-of-Experts architecture (27B active / 600B total parameters). It performs strongly in software engineering and professional knowledge work, with particular strength in finance. It is designed for extended tasks that span large codebases and documents, using tools and refining results over multiple steps.
- #20
Add More Details Detail Enhancer / Tweaker (细节调整) LoRA
Add More Details - Detail Enhancer / Tweaker (细节调整) LoRA by Lykon writes: his between 0.5 and 1 weight, depending on your preference. You can go lower than 0.5 for a more subtle effect, of course. I also found out that this gives some…Add More Details - Detail Enhancer / Tweaker (细节调整) LoRA by Lykon writes: his between 0.5 and 1 weight, depending on your preference. You can go lower than 0.5 for a more subtle effect, of course. I also found out that this gives some interesting results at negative weight, sometimes
- #21
waifu
waifu-diffusion by hakurei. A long running base model trained on crisp-looking anime. Compared to your other anime base model options, this one is fairly well-rounded, which unfortunately has been detrimental in making it a clear winner in…waifu-diffusion by hakurei. A long running base model trained on crisp-looking anime. Compared to your other anime base model options, this one is fairly well-rounded, which unfortunately has been detrimental in making it a clear winner in any category.
- #22
hyper
The "hyper-xl" model is optimized to significantly increase generation speed. - #23
GLM 5.3
Z.ai | 1.048.576 Token Kontext | $0,08/M Eingabe, $4,80/M Ausgabe. GLM-5.3 ist ein groß angelegtes Reasoning-Modell von Z.ai, entwickelt für komplexes Software-Engineering und Langzeit-Agentenaufgaben. Es unterstützt Text-Ein- und Ausgabe…Z.ai | 1.048.576 Token Kontext | $0,08/M Eingabe, $4,80/M Ausgabe. GLM-5.3 ist ein groß angelegtes Reasoning-Modell von Z.ai, entwickelt für komplexes Software-Engineering und Langzeit-Agentenaufgaben. Es unterstützt Text-Ein- und Ausgabe mit einem 1M-Token-Kontextfenster und verbessert GLM-5.2 im Coding sowie im Gleichgewicht zwischen Leistung und Token-Effizienz. Reasoning ist immer aktiv und kann nicht deaktiviert werden. Reasoning-Stufen low, high und max werden unterstützt; max ist Standard.
- #24
- #25
Detail Tweaker LoRA (细节调整LoRA)
LoRA designed for removing or adding detail while keeping the style of the render the same. Current strength is good from 0 - 2 depending on your use case. In the future, it can be used as negative weight to reduce details. Works with…LoRA designed for removing or adding detail while keeping the style of the render the same. Current strength is good from 0 - 2 depending on your use case. In the future, it can be used as negative weight to reduce details. Works with anime, semi-real and realistic models and styles.
- #26
DeepSeek V4 Flash 0423
DeepSeek | 1.048.576 Token Kontext | $0,09/M Eingabe, $0,18/M Ausgabe. DeepSeek V4 Flash ist ein auf Effizienz optimiertes Mixture-of-Experts-Modell von DeepSeek mit 284 Mrd. Gesamtparametern und 13 Mrd. aktivierten Parametern, das ein…DeepSeek | 1.048.576 Token Kontext | $0,09/M Eingabe, $0,18/M Ausgabe. DeepSeek V4 Flash ist ein auf Effizienz optimiertes Mixture-of-Experts-Modell von DeepSeek mit 284 Mrd. Gesamtparametern und 13 Mrd. aktivierten Parametern, das ein 1M-Token-Kontextfenster unterstützt. Es ist für schnelle Inferenz und Workloads mit hohem Durchsatz ausgelegt und bietet dabei starke Reasoning- und Coding-Leistungen. Das Modell beinhaltet hybride Aufmerksamkeit für effiziente Langzeit-Kontextverarbeitung. Reasoning-Stufen high und xhigh werden unterstützt; xhigh entspricht maximalem Reasoning. Es eignet sich gut für Anwendungen wie Coding-Assistenten, Chat-Systeme und Agenten-Workflows, bei denen Reaktionsfähigkeit und Kosteneffizienz wichtig sind.
- #27
Hy3
Tencent | 262,144 token context | $0.13/M input, $0.53/M output. Hy3 is a 295B-parameter Mixture-of-Experts model from Tencent (21B active, 192 experts with top-8 routing) built for reasoning, agentic workflows, and real-world production…Tencent | 262,144 token context | $0.13/M input, $0.53/M output. Hy3 is a 295B-parameter Mixture-of-Experts model from Tencent (21B active, 192 experts with top-8 routing) built for reasoning, agentic workflows, and real-world production use. It supports a configurable reasoning effort: a direct no-think mode by default, plus low and high chain-of-thought modes for complex math, coding, and multi-step problems. With a 256K context window, Hy3 targets long-horizon tasks, including improved coreference resolution, multi-turn constraint tracking, and stable tool-calling that generalizes across agent scaffoldings. Tencent positions it as a reliable, cost-effective option across coding, document processing, financial analysis, game development, and frontend design, with a strong emphasis on grounded, anti-hallucination behavior that answers when grounded and flags when evidence is missing rather than fabricating.
- #28
ebara_pony
Ebara Pony V3 by Shareman writes: positive: masterpiece, best quality, score_9, score_8_up, score_7_up,source_anime, - #29
- #30
Kimi K3
MoonshotAI | 1,048,576 token context | $0.30/M input, $11.94/M output. Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic…MoonshotAI | 1,048,576 token context | $0.30/M input, $11.94/M output. Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at navigating large repositories, using tools, debugging, and iterating against images, logs, tests, and runtime feedback. Its architecture uses KDA and Attention Residuals for computational efficiency.
- #31
MiMo V2.5
Xiaomi | 1.050.000 Token Kontext | $0,14/M Eingabe, $0,28/M Ausgabe. MiMo-V2.5 ist ein natives omnimodales Modell von Xiaomi. Es liefert Pro-Level agentische Leistung bei etwa der Hälfte der Inferenzkosten und übertrifft MiMo-V2-Omni in…Xiaomi | 1.050.000 Token Kontext | $0,14/M Eingabe, $0,28/M Ausgabe. MiMo-V2.5 ist ein natives omnimodales Modell von Xiaomi. Es liefert Pro-Level agentische Leistung bei etwa der Hälfte der Inferenzkosten und übertrifft MiMo-V2-Omni in multimodaler Wahrnehmung bei Bild- und Videoverstehensaufgaben. Sein 1M-Kontextfenster unterstützt komplette Dokumente, erweiterte Gespräche und komplexe Aufgaben-Kontexte in einem Durchlauf, was es ideal für die Integration in Agenten-Frameworks macht, bei denen starkes Reasoning, reichhaltige Wahrnehmung und Kosteneffizienz wichtig sind.
- #32
extremely detailed (no trigger) sliders.ntcai.xyz
Extremely detailed - sliders / ntcai.xyz by ntc. Make everything extremely detailed or bland (negative). Examples at 4-5 strength Trained for 6000 instances with sliders - #33
GLM 5.2
Z.ai | 1,048,576 token context | $0.04/M input, $9.00/M output. GLM 5.2 is a large-scale reasoning model from Z.ai. It supports text input and output with a 1M-token context window, and is suited for long-horizon agent workflows,…Z.ai | 1,048,576 token context | $0.04/M input, $9.00/M output. GLM 5.2 is a large-scale reasoning model from Z.ai. It supports text input and output with a 1M-token context window, and is suited for long-horizon agent workflows, project-level software engineering, and complex multi-step automation. Reasoning efforts high and xhigh are supported; xhigh maps to max reasoning. It is particularly strong at coding and tool use across long-running tasks, able to maintain engineering context and follow standards consistently through a full development workflow, from requirements to multi-platform deployment, in a single task.
- #34
MiniMax M3
MiniMax | 1.048.576 Token Kontext | $0,30/M Eingabe, $1,20/M Ausgabe. MiniMax-M3 ist ein multimodales Grundlagenmodell von MiniMax. Es unterstützt Text-, Bild- und Videoeingaben mit Textausgabe, ein 1M-Token-Kontextfenster und eignet sich…MiniMax | 1.048.576 Token Kontext | $0,30/M Eingabe, $1,20/M Ausgabe. MiniMax-M3 ist ein multimodales Grundlagenmodell von MiniMax. Es unterstützt Text-, Bild- und Videoeingaben mit Textausgabe, ein 1M-Token-Kontextfenster und eignet sich für Langzeit-agentische Arbeit, Coding und Tool-Nutzung. Es basiert auf MiniMax Sparse Attention (MSA), das die vollständige Aufmerksamkeit durch KV-Blockauswahl ersetzt, um die Berechnung pro Token bei langem Kontext zu reduzieren – etwa 1/20 der Kosten der vorherigen Generation bei 1M Tokens, mit deutlich schnellerem Prefill und Dekodierung bei gleichbleibender Qualität in den meisten Aufgaben. Es wurde als natives multimodales Modell auf verschachtelten Daten trainiert und für mehrstufige, produktionsähnliche Zusammenarbeit über ein interaktives User-Simulator-Framework abgestimmt. Das Modell ist auf nachhaltige, mehrstufige Aufgaben ausgelegt statt auf Einzeldurchläufe.
- #35
![[KREA 2] Detail Slider](https://media.modeltrends.ai/concepts/41546/thumb_civitai_None.webp)
[KREA 2] Detail Slider
by alcaitiff - [KREA 2] Detail Slider - #36
MiMo V2.6 Pro
Xiaomi | 1.050.000 Token Kontext | $0,43/M Eingabe, $0,87/M Ausgabe. MiMo-V2.6-Pro ist das Flaggschiff-Grundlagenmodell von Xiaomi. Entwickelt mit über 1 Billion Parametern, ist es darauf ausgelegt, die Leistungsgrenze für die…Xiaomi | 1.050.000 Token Kontext | $0,43/M Eingabe, $0,87/M Ausgabe. MiMo-V2.6-Pro ist das Flaggschiff-Grundlagenmodell von Xiaomi. Entwickelt mit über 1 Billion Parametern, ist es darauf ausgelegt, die Leistungsgrenze für die anspruchsvollsten Arbeitslasten zu verschieben. Das Modell verfügt über ein 1M-Token-Kontextfenster und native multimodale Fähigkeiten. Optimiert für agentische Workflows liefert es Spitzenleistungen in den Bereichen Programmierung, visuelle Verarbeitung, allgemeine und Forschungsanwendungen und glänzt bei komplexen, langfristigen Aufgaben mit robuster Generalisierung über eine Vielzahl von Agenten-Anwendungen.
- #37
- #38
DeepSeek V4 Pro 0813
DeepSeek | 1,048,576 token context | $1.32/M input, $3.96/M output. DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro. - #39
Laguna S 2.1
Poolside | 1.048.576 Token Kontext | $0,09/M Eingabe, $0,18/M Ausgabe. Laguna S 2.1 ist das neueste Coding-Agentenmodell von PoolsideOpens in new tab. Laguna S 2.1 ist ein Modell mit 118 Mrd. Gesamtparametern und 8 Mrd. aktiven Parametern,…Poolside | 1.048.576 Token Kontext | $0,09/M Eingabe, $0,18/M Ausgabe. Laguna S 2.1 ist das neueste Coding-Agentenmodell von PoolsideOpens in new tab. Laguna S 2.1 ist ein Modell mit 118 Mrd. Gesamtparametern und 8 Mrd. aktiven Parametern, erzielt 70,2 % auf Terminal-Bench 2.1 und 40,4 % auf DeepSWE und gehört damit zu den stärksten Coding-Modellen seiner Kategorie. Open-Weight unter der OpenMDW-1.1-Lizenz. Laguna S 2.1 ist für Software-Engineering- und agentische Coding-Anwendungsfälle konzipiert, und Sie sind verantwortlich dafür, zu bestätigen, dass es für Ihre beabsichtigte Anwendung geeignet ist. Laguna S 2.1 unterliegt der OpenMDW-1.1-LizenzOpens in new tab und sollte im Einklang mit Poolside's Acceptable Use PolicyOpens in new tab verwendet werden. Wir raten davon ab, die Sicherheitsvorkehrungen von Laguna S 2.1 zu umgehen, ohne substantiell gleichwertige Maßnahmen zu implementieren, die für Ihren Anwendungsfall angemessen sind. Bitte melden Sie Sicherheitslücken oder Sicherheitsbedenken an [email protected]. Wenn Sie Laguna S 2.1 kostenlos nutzen, können wir Ihre Eingaben und Ausgaben verwenden, um unsere Modelle zu trainieren und zu verbessern.
- #40
lyh_anime_Flux
Flux.1 D checkpoint, hosted on Yodayo with 23,546 generation runs there. The model is also listed on Civitai. - #41
Background Detail Enhancer
Background Detail Enhancer by ZyloO - #42
- #43
Nemotron 3.5 Lightning
NVIDIA | 262.144 Token Kontext | $0,07/M Eingabe, $0,20/M Ausgabe. NVIDIA Nemotron 3.5 Lightning ist ein offenes Mixture-of-Experts-Modell von NVIDIA mit 3 Milliarden aktiven Parametern von insgesamt 30 Milliarden. Es eignet sich für…NVIDIA | 262.144 Token Kontext | $0,07/M Eingabe, $0,20/M Ausgabe. NVIDIA Nemotron 3.5 Lightning ist ein offenes Mixture-of-Experts-Modell von NVIDIA mit 3 Milliarden aktiven Parametern von insgesamt 30 Milliarden. Es eignet sich für hochdurchsatzfähige agentische Arbeitslasten und spezialisierte Aufgaben, die von domänenspezifischer Anpassung profitieren.
- #44
playground2
This is the 1024 Aesthetic version of the general purpose Playground 2 concept, a rebuild of SDXL. Try it as a second opinion when you don't like what gives you. It can handle realism as well as paintings and ilustrations - #45
DeepSeek V4 Pro 0423
DeepSeek | 1,048,576 token context | $0.96/M input, $1.91/M output. DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It…DeepSeek | 1,048,576 token context | $0.96/M input, $1.91/M output. DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding, and long-horizon agent workflows, with strong performance across knowledge, math, and software engineering benchmarks. Built on the same architecture as DeepSeek V4 Flash, it introduces a hybrid attention system for efficient long-context processing. Reasoning efforts high and xhigh are supported; xhigh maps to max reasoning. It is well suited for complex workloads such as full-codebase analysis, multi-step automation, and large-scale information synthesis, where both capability and efficiency are critical
- #46
Chroma
Chroma checkpoint, hosted on Yodayo with 36,370 generation runs there. The model is also listed on Civitai. - #47
gpt oss 120b
OpenAI | 131.072 Token Kontext | $0,15/M Eingabe, $0,60/M Ausgabe. gpt-oss-120b ist ein offenes Gewicht, 117 Milliarden Parameter Mixture-of-Experts (MoE) Sprachmodell von OpenAI, entwickelt für hochgradiges Reasoning, agentische und…OpenAI | 131.072 Token Kontext | $0,15/M Eingabe, $0,60/M Ausgabe. gpt-oss-120b ist ein offenes Gewicht, 117 Milliarden Parameter Mixture-of-Experts (MoE) Sprachmodell von OpenAI, entwickelt für hochgradiges Reasoning, agentische und allgemeine Produktionsanwendungen. Es aktiviert 5,1 Milliarden Parameter pro Vorwärtsdurchlauf und ist optimiert für den Betrieb auf einer einzelnen H100 GPU mit nativer MXFP4-Quantisierung. Das Modell unterstützt konfigurierbare Reasoning-Tiefe, vollen Chain-of-Thought-Zugang und native Werkzeugnutzung, einschließlich Funktionsaufrufen, Browsing und strukturierter Ausgabeerzeugung.
- #48
level4
Level4 by AreThoseLevel4Plates is the creator of and this one, made popular for its stunning photos of athletes. Level4 is great for beginners, because it responds well to simple prompts, but to get a realistic photo out of it may take…Level4 by AreThoseLevel4Plates is the creator of and this one, made popular for its stunning photos of athletes. Level4 is great for beginners, because it responds well to simple prompts, but to get a realistic photo out of it may take more work, and there are better options. As a semi-realistic general model it's efforlessly great for portraits, cars, landscapes. The creator demos it as the go-to model for creating female athletes. Try the #nfix recipe with it or #cinematic
- #49
Realism Enhancer Krea2
by HearmemanAI - Realism Enhancer Krea2 - #50
Heat ist unser interner Trendwert von kühl bis 9999°. Er bewegt sich täglich mit Nutzungs- und Beliebtheitssignalen aus den Communities und Diensten rund um jedes Modell. Die Rangliste umfasst Basismodelle, LoRAs, Embeddings und Textmodelle aller Familien im Katalog.
Nach Modellfamilie stöbern
