usamaehsan / ltx-voice-one

LTX voice: text to speech with voice design or a saved voice_id, one warm pool (merged ltx-voice + lock).

247 runs
Public

usamaehsan / longcat-avatar

Talking avatar: one portrait photo + speech audio -> lip-synced talking video (LongCat-Video-Avatar 1.6, MIT). 8-step distilled, 25 fps, audio muxed in.

0 runs
Public

usamaehsan / klein-4b-lora-lab

Research only: train and test a LoRA on FLUX.2 klein 4B (Apache 2.0) edit pairs in one run.

4 runs
Public

usamaehsan / hunyuan3d-fast

Test: Hunyuan3D-2 with baked weights (cold-start)

29 runs
Public

usamaehsan / flux2-klein-4b-edit-fastboot

Test only: flux2-klein-4b-edit with a slimmer setup (cold-start test). Use usamaehsan/flux2-klein-4b-edit.

29 runs
Public

usamaehsan / whisper-ears

Whisper turbo transcript + audio X-ray in one pass: speaker turns, tone per line, laughs/coughs/sighs with times, 5-clip custom sound detectors, and an LLM-ready report.

4 runs
Public

usamaehsan / llm-ears

Research: gives a frozen LLM (Qwen3-8B) ears through a closed-form linear bridge from a frozen Whisper large-v3 encoder. No gradient training. Experiment mode measures WER on LibriSpeech.

9 runs
Public

usamaehsan / ltx-voice-speed-test

Speed/cost test copy of usamaehsan/ltx-voice (designed voices from text, no audio input). Not for production.

342 runs
Public

usamaehsan / ltx-voice-cheap-test

TEST ONLY: cost experiments for the LTX-2.5 voice model (batching, vocoder precision). Not for any site.

15 runs
Public

usamaehsan / ltx-voice-lock-test

Test: LTX-2.5 voice with fixed library voices (voice_id). Designed voices made by the model itself, no audio input, no cloning.

121 runs
Public

usamaehsan / ltx-av

LTX-2.5 22B distilled: fast expressive text-to-speech (default) plus optional text/image/audio-to-video with native audio, in one model. Designed voices from text, no cloning.

14 runs
Public

usamaehsan / ltx-voice

LTX-2.5 voice only: expressive text-to-speech from the audio half of LTX-2.5 (no video). Designed voices from a text prompt, no voice cloning.

1.7K runs
Public

usamaehsan / qwen3-tts-voice-design-test

TEST ONLY - do not use. Throwaway test of a faster build of usamaehsan/qwen3-tts-voice-design.

3 runs
Public

usamaehsan / qwen3-tts-voice-design

Text-to-speech in a new voice designed from a text description (10 languages). Qwen3-TTS VoiceDesign, Apache-2.0. No audio input, no cloning; descriptions that name a real person are refused.

14 runs
Public

usamaehsan / chatterbox-tts-v18

Fast batched multilingual text-to-speech (23 languages) on Chatterbox Multilingual. Preset voice library, no voice cloning, no watermark, max_seconds cap that stops at a sentence end.

11 runs
Public

usamaehsan / chatterbox-mtl-v18-test

TEST ONLY - do not use. Throwaway test of chatterbox-tts-v18.

10 runs
Public

usamaehsan / supertonic-3-tts

Fast multilingual text-to-speech (31 languages, 10 preset voices, no cloning). Supertonic 3 weights, OpenRAIL-M: outputs must be disclosed as machine generated; see the README for the use restrictions.

65 runs
Public

usamaehsan / ace-step-bgmusic

Cheap fast instrumental background music (ACE-Step 1.5 turbo, MIT)

21 runs
Public

usamaehsan / chatterbox-mtl-batched

Chatterbox Multilingual V3 (MIT) with batched sentence synthesis: a whole story is decoded in one pass instead of chunk by chunk. Voice cloning from a short reference, 23 languages.

159 runs
Public

usamaehsan / qwen-image-edit-2511-nunchaku

Qwen-Image-Edit-2511 Lightning, Nunchaku SVDQ INT4 (official nunchaku 1.2.1 + 2511 shim)

24 runs
Public

usamaehsan / qwen-image-edit-2511-lab

Qwen-Image-Edit-2511 cost lab: FP8 + torch.compile + SageAttention, tunable steps/reference size

128.7K runs
Public

usamaehsan / qwen-image-edit-2511-fast

Qwen-Image-Edit-2511 with the 4-step Lightning LoRA fused offline, FP8 on L40S.

37 runs
Public

usamaehsan / ernie-image-turbo-fast-h100

ERNIE-Image-Turbo tuned for cost: FP8 + torch.compile + lean forward, 1-8 steps, optional hires refine

372 runs
Public

usamaehsan / ernie-image-turbo-fast

ERNIE-Image-Turbo tuned for cost: FP8 + torch.compile + lean forward, 1-8 steps, optional hires refine

52 runs
Public

usamaehsan / z-image-turbo

Z-Image-Turbo text-to-image, 8 steps

1 run
Public

usamaehsan / ernie-image-turbo

ERNIE-Image-Turbo text-to-image, 8 steps, strong text rendering

66 runs
Public

usamaehsan / llada-image-turbo

LLaDA-Image-Turbo text-to-image (fp8), strong text rendering

15 runs
Public

usamaehsan / mage-flow-edit-turbo

Mage-Flow-Edit Turbo (4B, MIT) - instruction-based image editing in 4 steps.

704 runs
Public

usamaehsan / boogu-image-0.1-edit-turbo

image edit bench

5 runs
Public

usamaehsan / firered-image-edit-1.1

image edit bench

17 runs
Public

usamaehsan / flux-kontext-fastest

FLUX.1 Kontext dev, int4 + turbo 8-step. Cheapest quality image edits on L40S.

123 runs
Public

usamaehsan / ltx-2.5

2.5K runs
Public

usamaehsan / ltx-25-distilled

7 runs
Public

usamaehsan / flux2-klein-4b-edit-fp8

FLUX.2 klein 4B image edit, fp8 quantized for max speed on L40S

31 runs
Public

usamaehsan / flux2-klein-4b-edit

93K runs
Public

usamaehsan / qwen-image-edit-fastest-2

400+ images in 1$ 1024 resolution// 2s /img on L40S GPU, check description and examples

68K runs
Public

usamaehsan / qwen-image-edit-fastest

300+ images /1$ approximately - check examples. Quality is good even at 2 steps

262 runs
Public

usamaehsan / qwen-image-4bit

good for simple tasks - running on l40s

83 runs
Public

usamaehsan / flux-multicontrol-inpaint

0 runs
Public

usamaehsan / voices

2.2K runs
Public

usamaehsan / voice

9 runs
Public

usamaehsan / flux-controlnet

11 runs
Public

usamaehsan / flux-multi-controlnet

Fast FLUX DEV -> Flux Controlnet Canny, Controlnet Depth , Controlnet Line Art, Controlnet Upscaler - You can use just one controlnet or All - LORAs: HyperFlex LoRA , Add Details LoRA , Realism LoRA

340K runs
Public

usamaehsan / flux-multicontrolnet

multi controlnet union pro <-

174 runs
Public

usamaehsan / juggernaut-xl-x-adapters-x-lightning

34 runs
Public

usamaehsan / instant-id-x-playground-v2.5-xl-lightning

19 runs
Public

usamaehsan / multi-controlnet-x-ip-adapter-vision-v2

6.1K runs
Public

usamaehsan / swap-sd

Experimental & for non-commercial use only

6.6K runs
Public

usamaehsan / instant-id-x-juggernaut

94.5K runs
Public

usamaehsan / instant-id-x-yamermix-v8

1.4K runs
Public

usamaehsan / instant-id-x-copax-timeless-xl

multi Instant ID + Pose

4.1K runs
Public

usamaehsan / instant-id-1

0 runs
Public

usamaehsan / instant-id

fast instant-id

1.3K runs
Public

usamaehsan / instant-id-x-better

22 runs
Public

usamaehsan / controlnet-x-realistic-vision

83 runs
Public

usamaehsan / controlnet-x-ip-adapter-realistic-vision-v5

Inpainting || multi-controlnet || single-controlnet || ip-adapter || ip adapter face || ip adapter plus || No ip adapter

683.2K runs
Public

usamaehsan / controlnet-x-majic-mix-realistic-x-ip-adapter

works with inpainting and multi-controlnet + single-controlnet || ip-adapter + without ip adapter

24K runs
Public

usamaehsan / controlnet-lineart-brightness-tile-inpainting

controlnet-lineart-brightness-tile-inpainting + low res fix with tile

720 runs
Public

usamaehsan / lineart-x-brightness-x-tile-x-inpainting-x-realistic-vision-v5

0 runs
Public

usamaehsan / multi-controlnet-x-consistency-decoder-x-realestic-vision-v5

Multi-Controlnet + consistency-decoder + INPAINTING + realestic-vision-v5 + Prompt-Weight + Single-Controlnet

3.4K runs
Public

usamaehsan / controlnet-lineart-inpainting-x-realistic-vision-v5

518 runs
Public

usamaehsan / realistic-vision-v5-inpainting

Better than SDXL Inpainting

3.2K runs
Public

usamaehsan / controlnet-1.1-x-realistic-vision-v2.0

controlnet 1.1 lineart x realistic-vision-v2.0 (updated to v5)

5.8M runs
Public

usamaehsan / dual-style-gan

0 runs
Public