<h2 id="add-as-a-new-version-for-qwen-image-2.1-qwen-image-2.1-is-licensed-for-non-commercial-use-only.-this-version-cannot-be-used-commercially.-about-this-version"><span style="background-color:rgb(26, 27, 30);color:rgb(193, 194, 197);font-family:-apple-system, BlinkMacSystemFont, &quot;Segoe UI&quot;, Roboto, Helvetica, Arial, sans-serif, &quot;Apple Color Emoji&quot;, &quot;Segoe UI Emoji&quot;;font-size:16px">Add as a new VERSION for Qwen Image 2.1 ⚠️ Qwen Image 2.1 is licensed for non-commercial use only. This version cannot be used commercially. ## About this version</h2>The candid amateur iPhone look, now for Qwen Image 2.1. It takes away the staged studio light and gives you a plain phone photo: everyday exposure, natural skin with freckles and pores, real rooms.Trigger: <code>cndamiph</code> at the start of the prompt.What changes on the same seed and prompt- dramatic studio light → flat everyday light- posed, retouched look → a casual moment- night scenes keep the street lamp or window light and stay readable- hands and skin look younger and less wrinkled than plain Qwen 2.1 at the same settings<hr /><span style="background-color:rgb(26, 27, 30);color:rgb(193, 194, 197);font-family:-apple-system, BlinkMacSystemFont, &quot;Segoe UI&quot;, Roboto, Helvetica, Arial, sans-serif, &quot;Apple Color Emoji&quot;, &quot;Segoe UI Emoji&quot;;font-size:16px">Free MOSS Image LoRA for the candid amateur iPhone Workflows, prompts and full test sheets: Skool <a target="_blank" rel="ugc" href="https://www.skool.com/artfat-ai-6792">https://www.skool.com/artfat-ai-6792</a> · Discord <a target="_blank" rel="ugc" href="https://discord.gg/WWSe9zSSQ">https://discord.gg/WWSe9zSSQ</a> · YouTube <a target="_blank" rel="ugc" href="https://www.youtube.com/@ArtfatAi">https://www.youtube.com/@ArtfatAi</a>A style LoRA for MOSS Image that takes away the polished stock-photo look and gives you a real phone photo instead. Skin keeps its pores and freckles. Light comes from somewhere you can see. The background stays sharp like on a phone, rooms have their everyday clutter, and people are caught mid-moment instead of posing.It works on people, couples, groups, food, pets, streets and interiors, in daylight, golden hour and at night, SFW and NSFW.Trigger: <code>cndamiph</code> at the start of the prompt.What changes compared to plain MOSS Base (same seed, same prompt)- stock / editorial look → amateur phone photo- shallow DSLR blur → deep phone sharpness- glossy made-up faces → natural skin, freckles, real age- night scenes keep the lamp or neon light instead of a flat flash- signs, shirts and notes stay readable### Recommended setup (used for the gallery)- MOSS Image Base bf16 + cndamiph 1.0 + an 8-step turbo LoRA by lodestones (Apache-2.0): <a target="_blank" rel="ugc" href="https://huggingface.co/lodestones/Kromoss">https://huggingface.co/lodestones/Kromoss</a>- <code>8-steps-dmd2-lora</code> — the newest one (out 20 Oct). DMD with an extra GAN stage, gives a sharper, more contrasty picture.Download: <a target="_blank" rel="ugc" href="https://huggingface.co/lodestones/Kromoss/resolve/main/8-steps-dmd2-lora.safetensors?download=true">https://huggingface.co/lodestones/Kromoss/resolve/main/8-steps-dmd2-lora.safetensors?download=true</a>- <code>8-steps-dmd-lora</code> — the first one, used for this gallery at strength 0.8.Download: <a target="_blank" rel="ugc" href="https://huggingface.co/lodestones/Kromoss/resolve/main/8-steps-dmd-lora.safetensors?download=true">https://huggingface.co/lodestones/Kromoss/resolve/main/8-steps-dmd-lora.safetensors?download=true</a>- Use one of them, not both. Both work with cndamiph, pick the one you like.<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/2f2b3403-3bdf-4e52-8291-222ed905ebe3/original=true/2f2b3403-3bdf-4e52-8291-222ed905ebe3.jpeg" />- Difference on the same seed and prompt (both at 0.8): DMD2 is about 14% sharper (cardboard, paper bag and fruit skin show it most). The amateur look stays the same: freckles, side sun, sharp background, no plastic skin. Small background details can come out different. Comparison sheet: <code>02_grids/14_S1_market_dmd_vs_dmd2.jpg</code>.- If you skip the SeedVR2 upscale, take DMD2: on close portraits it is about 30% sharper on its own. With SeedVR2 on top the gap shrinks to about 10%, so there both are fine.- Keep DMD2 at 0.8 too. At 1.0 it changes the face more (eye colour, blush) and adds a little shine to the skin. Close-up sheet: <code>02_grids/15_portraits_dmd_vs_dmd2_crops.jpg</code>.- The same seed does not give the same picture with the other turbo LoRA: the composition and the pose shift a little. If you liked a seed on one of them, stay on that one.- 8 steps · CFG 1 · sampler res_6s · scheduler bong_tangent (RES4LYF)- optional last pass: downscale ×0.5 → SeedVR2 3B upscale to 2560 px, color correction lab. It adds the fine phone-sharp detail and leaves the picture as it is.res_6s is a 6-stage sampler, so 8 steps are about 48 model calls. Still far less than a 50-step CFG 3 run, and sharper than plain 8 steps.### Other modes| Mode | Steps | CFG | Sampler / scheduler | LoRA strength ||---|---|---|---|---|| Fast, plain sampler | 8 + DMD 0.8 | 1 | er_sde / simple | 0.8 || Without the speed LoRA | 50 | 3 | er_sde / simple | 0.8 || Without the speed LoRA, faster | 25 | 3 | er_sde / simple | 0.8 |Base model: MOSS Image Base, bf16. Quantized int8 weights noticeably weaken the LoRA, so use bf16 if you can.### Tips- Write prompts as plain sentences: who, where, what light, what is lying around.- Put any text you want in the picture in "double quotes".- Name the light and its side ("a warm bedside lamp on the right").- Write "plain unbranded" for clothes and shoes if you do not want logos.- Without the LoRA loaded, remove the trigger word, or the base model may print it as text.- On 8 steps, busy group scenes and fine skin come out softer and people can look a few years younger. 50 steps gives the most detail.- Left / right is not always followed. That comes from the base model.### Promo videosThe two videos in the gallery were animated with MiniMax H3 straight from this LoRA's own stills.Music: "Cruising" by Aisake, Dosi and "Bad Habit (feat. Zaug) - Phonk Version" by Zaug, Jéja. Music provided by NoCopyrightSounds (NCS).### Credits- 8-step turbo LoRAs <code>8-steps-dmd-lora</code>, <code>8-steps-dmd2-lora</code>) by lodestones — <a target="_blank" rel="ugc" href="https://huggingface.co/lodestones/Kromoss">https://huggingface.co/lodestones/Kromoss</a> (Apache-2.0). Thanks for making MOSS Image fast.- Base model: MOSS Image by OpenMOSS — <a target="_blank" rel="ugc" href="https://huggingface.co/OpenMOSS-Team/MOSS-Image-Base">https://huggingface.co/OpenMOSS-Team/MOSS-Image-Base</a>- Upscale: SeedVR2 · sampler: RES4LYF (res_6s / bong_tangent)Trained on 80 original images made for this LoRA, captioned in plain prose. MOSS Image Base, rank 32.All people shown are fictional adults.

Candid Amateur iPhone (MOSS Image | QWEN 2.1)

# cndamiph for Qwen Image 2.1: new version on the existing page⚠️ Qwen Image 2.1 is licensed for non-commercial use only. This version cannot be used commercially.Add as a new VERSION of <a target="_blank" rel="ugc" href="https://civitai.com/models/3012015">https://civitai.com/models/3012015</a> so downloads add up on one page.Version name: <code>Qwen Image 2.1</code>Base model: pick Qwen Image 2.1 in the Civitai list.File: <code>00_lora/cndamiph_Candid_Amateur_iPhone_Qwen21_v1.safetensors</code>Trigger: <code>cndamiph</code>## Before publishing (user)- Qwen 2.1 uses a non-commercial Research Licence. Check that Civitai monetisation of this version is allowed.- Page title: add Qwen 2.1, for example <code>Candid Amateur iPhone - cndamiph | MOSS + Qwen 2.1 LoRA</code>.## About this version (EN, paste)The candid amateur iPhone look, now for Qwen Image 2.1. It takes away the staged studio light and gives you a plain phone photo: everyday exposure, natural skin with freckles and pores, real rooms.Trigger: <code>cndamiph</code> at the start of the prompt.What changes on the same seed and prompt- dramatic studio light → flat everyday light- posed, retouched look → a casual moment- night scenes keep the street lamp or window light and stay readable- hands and skin look younger and less wrinkled than plain Qwen 2.1 at the same settingsSetup used for the gallery- Base model: Qwen Image 2.1 bf16 <code>qwenImage21_21_bf16</code>), setup guide: <a target="_blank" rel="ugc" href="https://docs.comfy.org/tutorials/image/qwen/qwen-image-2-1">https://docs.comfy.org/tutorials/image/qwen/qwen-image-2-1</a>- Text encoder: <code>qwen3vl_8b_int8_convrot_heretic</code> · VAE: <code>qwen_image_2.1_vae_bf16</code>- cndamiph 0.9- Turbo LoRA: Qwen-Image-2.1-Turbo-LoRA r128 at 0.95: <a target="_blank" rel="ugc" href="https://civitai.com/models/2997646?modelVersionId=3400002">https://civitai.com/models/2997646?modelVersionId=3400002</a>- 20 steps · CFG 3 · euler · simple · 1024×1792 (9:16)- Final pass: skin detail model <code>1x-ITF-SkinDiffDetail-Lite-v1</code>, scale ×0.5, then SeedVR2 3B <code>seedvr2_ema_3b-Q4_K_M</code>) to 2340×4096, colour correction lab: <a target="_blank" rel="ugc" href="https://github.com/numz/ComfyUI-SeedVR2_VideoUpscaler">https://github.com/numz/ComfyUI-SeedVR2_VideoUpscaler</a>Tested on: Qwen Image 2.1 only, with this turbo LoRA at these settings. Without a turbo LoRA and with other turbo LoRAs it was not tested.Tips- Write plain sentences: who, where, which light, what is lying around.- Name the light and where it comes from.- Skip words like "cinematic" or "professional", they pull the picture back to the studio look.- Without the LoRA loaded, remove the trigger word, or the model may print it as text.- Fine white lines on nail tips are from the base setup: they also appear without this LoRA.Trained on the same dataset as the previous versions.All people shown are fictional adults.

Files with SHA256: a1199d1725c1440e4f03f3dda44b13530c38ef769594c602b92565bfb0985af4