Model
Trends
.ai
Model
Trends
.ai
the best open source ai models
Run Locally
lenovo_qwen21.safetensors
76 MB · SafeTensor · fp16
Downloads are served by Civitai. Some creators ask for a Civitai login first.
AD
Install / Run on Graydient
Requires membership
<lenovo-qwen2>
About This Model
QWEN2 · LoRAs
Created by
Danrisi
on Civitai
by Danrisi - Lenovo UltraReal Qwen2.1 - My recommendations: 3-4 cfg (but if image become slop, then change to 1) beta scheduler, res_2m / res_2s / res_multistep (2s best quality, multistep the fastest, 2m balance)
Creator notes
--Qwen2.1 Me recommendations: 3-4 cfg (but if image become slop, then change to 1) beta scheduler, res_2m / res_2s / res_multistep (2s best quality, multistep the fastest, 2m balance) I'll post my flow a bit later when finish uploading other loras P.S: im in a hurry so more exmaples will be soon for all my loras --Krea2 Actually i tested with different combinations raw and turbo. For best quality i use raw with cfg4, for fast result i use raw, but witth cfg1 and turbo lora (it really gives better quality then kreo2 turbo model). U can use with other loras freely, also works good with nicegirls lora and nsfw loras. recommended weight 0.8 for raw and 1.2-2 for turbo --Ideogram4 Works good with for nsfw images. Also updated my repo for better lora control One more. Made cool nodes with cursor (i have no clue how some of them to use) for ideogram --Anima1.0 Trained on top of my last ultrareal_finetune_base1 checkpoint for a slight realism boost. I also "vibecoded" a few experimental nodes for Anima (pretty sure something similar already exists, but here we are): Consider this a temporary realism upgrade until I train the next major fine-tune. --Anima0.5 Trained on anima3. Recommended strength: 0.6. Works best with block filtering — I created a ComfyUI nodepack for this: . Examples generated alongside my other LoRA — nicegirls. Experimental version. Results may vary depending on prompt and block weight settings. --Flux2 I use it with res2m+beta57, guidance 4, and it works very well. The quality is similar to my Qwen Lenovo, but I noticed that Flux2 is more flexible and has better prompt adherence. Recommend to use with strength 0.85-0.9 -- Z-image Turbo Actually i'm not sure that my workflow is correct, i believe the result could be better Recommend to use with strength 0.80-0.9 I used euler + sgm_uniform with 4 guidance P.S: at this moment for ComfyUI u need this pack to load lora properly --Chroma My first try to train lora that enhance realism in Chroma. I'll upload my workflow today a lil bit later (or atm u can just take it from images) cause there some nuances about settings. But from my observations i noticed that for fast gen dpmpp2m + beta with cfg 3 works good . More experimental settigns are res_2s_rkmk2e + beta57 and cfg 3, more accurate gens, better limbs and fingers, but gives a bit weird grain on very small details + plus this method is pretty long --Qwen Works perfectly and much better then other versions. Gives extremely "live" images with amateurish quality with dramatic light and shadows, some blur and with vibe of 2000s street photography You can take workflow here Thanx to . i understood that it's possible (and even have better effect) to use lora with values 1.5 - 2.0. P.S.: almost all example images generate with both loras (NiceGirls) --Wan This is the first release — mainly a test to explore Wan's capabilities. Note: In this initial version, facial details are somewhat lacking. For better results, I recommend using it alongside the by my friend, which significantly enhances facial features. --Flux Who needs a fancy name when the shadows and highlights do all the talking? This experimental LoRA is the scrappy cousin of my Samsung one—same punchy light-and-shadow mojo, but trained on a chaotic mix of pics from my ancient phones (so no Samsung for now)
8,898 downloads · 257 likes on Civitai
SHA256
7F1E95C3EC1E9C7CEA197F7B6F80F601AF8E6B479F6EAD78AB16DF542F447C0E
ModelTrends.ai Model ID
#27515
Flag content
Example renders
Prompts and settings shared by the people who made these renders on Civitai. Pick a render to see how it was made.
Settings
Sampler
er_sde beta
Steps
20
Guidance
4
Seed
371673297792523
Size
3072x4608
Clip skip
1
Weight used
1
Prompt
rewritten_prompt": "The image is a tall Soviet agitprop lithograph poster with angular figurative drawing, forceful diagonal composition, and scarlet, charcoal, ochre, and aged cream inks. The paper has a coarse fibrous surface, slightly uneven ink coverage, and a narrow cream border. Across the upper band, monumental cream English lettering reads "HIDING PROMPTS IS A DESPICABLE ACT", arranged in three tightly stacked lines integrated with the angular composition. Behind the figures, a great scarlet wedge cuts from the upper right toward the lower left through a fractured charcoal background. Across the upper-left distance, factory chimneys, steel girders, and serrated industrial rooftops form a compact silhouette beneath bands of ochre smoke. In the middle distance, a procession of workers carrying plain red banners advances along an ascending diagonal, their simplified silhouettes establishing collective movement and depth. At the lower left, a stocky bourgeois caricature crouches behind a tilted desk, his torso bent almost horizontally as he attempts to conceal a thick book beneath his black frock coat. His left hand pins the book against his belly while his right hand fumbles with the open door of a small iron safe. The exposed dark book cover bears the clearly legible cream word "PROMPT". His striped trousers bunch sharply at the knees, one shoe slips on scattered papers, and his top hat tumbles toward the bottom edge. His head twists back toward the approaching workers, with raised brows, a tense jaw, and an expression of exposed deceit. From the upper right into the centre, a monumental adult factory worker steps forward with a wide, grounded stance, his rolled sleeves revealing strongly modelled forearms. His left arm extends across the central diagonal, its open hand pointing directly toward the concealed book, while his right arm rises with a clenched fist above his shoulder. Immediately behind him, a woman worker in a scarlet headscarf leans forward and reaches toward the open safe, her other hand holding an unfurled cream sheet covered with rows of small, indistinct printing. A third worker braces a tall red banner pole, its strong diagonal linking the industrial skyline to the foreground confrontation. Across the lower-right foreground, the desk, safe, scattered sheets, and overlapping legs form interlocking angular shapes, with clear separation between each figure’s limbs. Broad cream rays fan outward behind the advancing workers, while broken black bars frame the crouching hoarder. The lighting is graphic and directional, with warm cream highlights on the workers’ faces and hands and cold charcoal shadows enclosing the concealed book and safe. The overall composition combines industrial depth, emphatic bodily gestures, restrained lithographic colour, and a severe public accusation against the concealment of prompts. <lora:NSFW Qwen by TheseAlpacas V2:0.8> <lora:lenovo_qwen21:1.0>
Negative prompt
rewritten_prompt": "The image is a tall Soviet agitprop lithograph poster with angular figurative drawing, forceful diagonal composition, and scarlet, charcoal, ochre, and aged cream inks. The paper has a coarse fibrous surface, slightly uneven ink coverage, and a narrow cream border. Across the upper band, monumental cream English lettering reads "HIDING PROMPTS IS A DESPICABLE ACT", arranged in three tightly stacked lines integrated with the angular composition. Behind the figures, a great scarlet wedge cuts from the upper right toward the lower left through a fractured charcoal background. Across the upper-left distance, factory chimneys, steel girders, and serrated industrial rooftops form a compact silhouette beneath bands of ochre smoke. In the middle distance, a procession of workers carrying plain red banners advances along an ascending diagonal, their simplified silhouettes establishing collective movement and depth. At the lower left, a stocky bourgeois caricature crouches behind a tilted desk, his torso bent almost horizontally as he attempts to conceal a thick book beneath his black frock coat. His left hand pins the book against his belly while his right hand fumbles with the open door of a small iron safe. The exposed dark book cover bears the clearly legible cream word "PROMPT". His striped trousers bunch sharply at the knees, one shoe slips on scattered papers, and his top hat tumbles toward the bottom edge. His head twists back toward the approaching workers, with raised brows, a tense jaw, and an expression of exposed deceit. From the upper right into the centre, a monumental adult factory worker steps forward with a wide, grounded stance, his rolled sleeves revealing strongly modelled forearms. His left arm extends across the central diagonal, its open hand pointing directly toward the concealed book, while his right arm rises with a clenched fist above his shoulder. Immediately behind him, a woman worker in a scarlet headscarf leans forward and reaches toward the open safe, her other hand holding an unfurled cream sheet covered with rows of small, indistinct printing. A third worker braces a tall red banner pole, its strong diagonal linking the industrial skyline to the foreground confrontation. Across the lower-right foreground, the desk, safe, scattered sheets, and overlapping legs form interlocking angular shapes, with clear separation between each figure’s limbs. Broad cream rays fan outward behind the advancing workers, while broken black bars frame the crouching hoarder. The lighting is graphic and directional, with warm cream highlights on the workers’ faces and hands and cold charcoal shadows enclosing the concealed book and safe. The overall composition combines industrial depth, emphatic bodily gestures, restrained lithographic colour, and a severe public accusation against the concealment of prompts.
Settings
Sampler
res_2s
Steps
50
Guidance
4
Seed
1022383080139453
Size
1088x1440
Prompt
l3n0v0. A woman with long brown hair sits in profile on a stone ledge, overlooking a wide river during a vivid sunset. They are dressed in a dark long-sleeved top with fingerless gloves, sheer black stockings, and chunky platform shoes, carrying a black backpack adorned with a silver metallic charm. In the distance, a large suspension bridge spans the calm water, silhouetted against a cityscape under a sky filled with glowing orange and gold cumulus clouds. The scene is bathed in warm, soft-focus sunset backlighting that casts deep shadows and reflects brilliant amber tones across the water's surface. The image exhibits a slight grain typical of high-ISO digital photography, creating an atmospheric, melancholic, and serene mood.
Settings
Sampler
res_2s
Steps
50
Guidance
4
Seed
243249609094506
Size
1248x1664
Prompt
l3n0v0. A low-angle digital photo shoot on iphone 4, muted colors with a grey-brown color cast, and soft, diffused natural low lighting, taken in an outdoor setting on an overcast day in autumn forest, shows a 20 years old ukrainian girl with no makeup, thin lips, straight nose and natural brows and brown ponytail with side-swept bangs, in the foreground with bare tree branches against the sky in the background, visible freckles on her nose, wearing a pink turtleneck with brown trench coat with high collars, with white wired earbuds in her ears, holding the camera for a selfie and looking directly down into the lens with a neutral expression and her mouth closed with lit cigarette between her lips, dense smoke casted from cigarette
Settings
Sampler
Euler
Steps
25
Guidance
1
Seed
593103825222985
Size
1760x2368
Prompt
l3n0v0. A high-angle, outdoor shot captures a young woman with auburn hair crouching on a concrete sidewalk, leaning toward a ginger tabby cat. The person wears a light-colored jacket with dark blue panels and holds a black smartphone in their hands. The cat sits on the edge of the pavement, near the curb, with its head tilted upward as if investigating the person. The scene is illuminated by flat, natural daylight, casting soft shadows that contribute to a calm, gentle mood. The image has a slightly grainy texture and low contrast typical of a mobile phone capture in daylight. The surrounding ground features scattered autumn leaves and a square metal grate, with the edge of a vehicle tire visible in the upper right corner.
Settings
Sampler
res_2m
Steps
50
Guidance
3
Seed
565980907395658
Size
1248x1664
Prompt
l3n0v0. 20-year-old girl with very pale, smooth skin sitting in the passenger seat of a car, wearing thin wire-rimmed glasses, long blonde hair, slightly wavy, parted in the middle, casual style, wearing a white T-shirt with denim overalls, side profile, looking towards the camera, indoor car setting, seatbelt visible. Background shows motion blur of a highway, streaks of red and white light, suggesting car in motion, shadowed foreground, dark, underexposed, high iso
Settings
Sampler
res_2s
Steps
50
Guidance
4
Seed
380419676823203
Size
1664x1248
Prompt
This amateur photo is a chaotic close-up snapshot of a stunned The subject is a young East Asian woman, approximately 20 years old, with pale, clear skin featuring natural texture and a visible mole on her left cheek. Her hair is dark black, pulled up into messy ponytail with significant static and frizz, loose strands falling chaotically over her forehead and eyes. She is making a playful expression, winking with her right eye closed and left eye open. She is wearing a nondescript, casual grey t-shirt, barely visible at the bottom of the frame. The background is a cluttered, messy bedroom corner, featuring a blurred white dresser stacked with miscellaneous blue bottles and toiletries, and an unmade bed with rumpled blue linens. The lighting is the defining feature: a single, intense, blindingly horizontal shaft of sunlight strikes directly across her eyes, glowing white-hot and completely obscuring her gaze with overexposure. This creates a harsh, thick volumetric light shaft that cuts through the otherwise dim, cool-toned room. Floating dust motes are visible dancing in the beam, and the image has a raw, grainy, high-ISO texture typical of early digital cameras.
Settings
Sampler
res_2m
Steps
50
Guidance
3
Seed
328993414186607
Size
1248x1664
Prompt
l3n0v0, amateur photo, low-lit, shot on cheap mobile phone, evening, high iso, shadowed foreground, dark. A 20-year-old Eastern European-looking woman casually dressed in an oversized pink T-shirt with text "sample text sample text sample text", outdoors, her gaze directed to the side, serious expression, hold cup of coffee, her blonde hair loosely tied back and she has fringes that frames her face. minimal makeup visible. she is standing on the street near soviet-era storey buildings, trees, parked cars near. Dull, overcast lighting
Settings
Sampler
res_2s
Steps
50
Guidance
4
Seed
523757614166268
Size
1088x1440
Prompt
l3n0v0, A medium full-body outdoor snapshot taken on an overcast winter day. A young woman with exceptionally long, straight light brown hair and green eyes is standing directly in front of a dense pine tree heavily weighed down by thick patches of white snow. She is squinting her eyes shut and making a playful duck face or pout expression. She is wearing a loose, oversized dark grey graphic t-shirt and grey jeans. Her hair flows over her shoulders, reaching down past her waist. The background shows a hint of a residential brick building with a bright blue balcony accent under dull winter lighting. The image features desaturated tones, low-contrast flat daylight shadows, slight mobile digital compression, and an unpolished, casual camera roll snapshot aesthetic.
AI Models for Image, Video & Text Generation
lenovo qwen2 is a LoRA for the Qwen2 family listed on ModelTrends.ai, a read-only catalog of open source AI image, video and text models. Compare it with other Qwen2 models, check its heat score to see how it is trending, and open it on PirateDiffusion or BitVector to try it.
Browse by Model Family
Browse all models